Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and computation-intensive to suit low- capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted considerable research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.
We propose a novel framework for predicting the factuality of reporting of news media outlets by studying the user attention cycles in their YouTube channels. In particular, we design a rich set of features derived from the temporal evolution of the number of views, likes, dislikes, and comments for a video, which we then aggregate to the channel level. We develop and release a dataset for the task, containing observations of user attention on YouTube channels for 489 news media. Our experiments demonstrate both complementarity and sizable improvements over state-of-the-art textual representations.
With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first global infodemic. Fighting this infodemic is currently ranked very high on the list of priorities of the World Health Organization, with dangers ranging from promoting fake cures, rumors, and conspiracy theories to spreading xenophobia and panic. With this in mind, we studied how COVID-19 is discussed in Bulgarian social media in terms of factuality, harmfulness, propaganda, and framing. We found that most Bulgarian tweets contain verifiable factual claims, are factually true, are of potential public interest, are not harmful, and are too trivial to fact-check; moreover, zooming into harmful tweets, we found that they spread not only rumors but also panic. We further analyzed articles shared in Bulgarian partisan pro/con-COVID-19 Facebook groups and found that propaganda is more prevalent in skeptical articles, which use doubt, flag waving, and slogans to convey their message; in contrast, concerned ones appeal to emotions, fear, and authority; moreover, skeptical articles frame the issue as one of quality of life, policy, legality, economy, and politics, while concerned articles focus on health & safety. We release our manually and automatically analyzed datasets to enable further research.
While COVID-19 vaccines are finally becoming widely available, a second pandemic that revolves around the circulation of anti-vaxxer “fake news” may hinder efforts to recover from the first one. With this in mind, we performed an extensive analysis of Arabic and English tweets about COVID-19 vaccines, with focus on messages originating from Qatar. We found that Arabic tweets contain a lot of false information and rumors, while English tweets are mostly factual. However, English tweets are much more propagandistic than Arabic ones. In terms of propaganda techniques, about half of the Arabic tweets express doubt, and 1/5 use loaded language, while English tweets are abundant in loaded language, exaggeration, fear, name-calling, doubt, and flag-waving. Finally, in terms of framing, Arabic tweets adopt a health and safety perspective, while in English economic concerns dominate.
Online users today are exposed to misleading and propagandistic news articles and media posts on a daily basis. To counter thus, a number of approaches have been designed aiming to achieve a healthier and safer online news and media consumption. Automatic systems are able to support humans in detecting such content; yet, a major impediment to their broad adoption is that besides being accurate, the decisions of such systems need also to be interpretable in order to be trusted and widely adopted by users. Since misleading and propagandistic content influences readers through the use of a number of deception techniques, we propose to detect and to show the use of such techniques as a way to offer interpretability. In particular, we define qualitatively descriptive features and we analyze their suitability for detecting deception techniques. We further show that our interpretable features can be easily combined with pre-trained language models, yielding state-of-the-art results.
In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.
With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first global infodemic. Fighting this infodemic has been declared one of the most important focus areas of the World Health Organization, with dangers ranging from promoting fake cures, rumors, and conspiracy theories to spreading xenophobia and panic. Addressing the issue requires solving a number of challenging problems such as identifying messages containing claims, determining their check-worthiness and factuality, and their potential to do harm as well as the nature of that harm, to mention just a few. To address this gap, we release a large dataset of 16K manually annotated tweets for fine-grained disinformation analysis that (i) focuses on COVID-19, (ii) combines the perspectives and the interests of journalists, fact-checkers, social media platforms, policy makers, and society, and (iii) covers Arabic, Bulgarian, Dutch, and English. Finally, we show strong evaluation results using pretrained Transformers, thus confirming the practical utility of the dataset in monolingual vs. multilingual, and single task vs. multitask settings.
Internet memes have become powerful means to transmit political, psychological, and socio-cultural ideas. Although memes are typically humorous, recent days have witnessed an escalation of harmful memes used for trolling, cyberbullying, and abuse. Detecting such memes is challenging as they can be highly satirical and cryptic. Moreover, while previous work has focused on specific aspects of memes such as hate speech and propaganda, there has been little work on harm in general. Here, we aim to bridge this gap. In particular, we focus on two tasks: (i)detecting harmful memes, and (ii) identifying the social entities they target. We further extend the recently released HarMeme dataset, which covered COVID-19, with additional memes and a new topic: US politics. To solve these tasks, we propose MOMENTA (MultimOdal framework for detecting harmful MemEs aNd Their tArgets), a novel multimodal deep neural network that uses global and local perspectives to detect harmful memes. MOMENTA systematically analyzes the local and the global perspective of the input meme (in both modalities) and relates it to the background context. MOMENTA is interpretable and generalizable, and our experiments show that it outperforms several strong rivaling approaches.
With the continuing spread of misinformation and disinformation online, it is of increasing importance to develop combating mechanisms at scale in the form of automated systems that support multiple languages. One task of interest is claim veracity prediction, which can be addressed using stance detection with respect to relevant documents retrieved online. To this end, we present our new Arabic Stance Detection dataset (AraStance) of 4,063 claim–article pairs from a diverse set of sources comprising three fact-checking websites and one news website. AraStance covers false and true claims from multiple domains (e.g., politics, sports, health) and several Arab countries, and it is well-balanced between related and unrelated documents with respect to the claims. We benchmark AraStance, along with two other stance detection datasets, using a number of BERT-based models. Our best model achieves an accuracy of 85% and a macro F1 score of 78%, which leaves room for improvement and reflects the challenging nature of AraStance and the task of stance detection in general.
We present the results and the main findings of the NLP4IF-2021 shared tasks. Task 1 focused on fighting the COVID-19 infodemic in social media, and it was offered in Arabic, Bulgarian, and English. Given a tweet, it asked to predict whether that tweet contains a verifiable claim, and if so, whether it is likely to be false, is of general interest, is likely to be harmful, and is worthy of manual fact-checking; also, whether it is harmful to society, and whether it requires the attention of policy makers. Task 2 focused on censorship detection, and was offered in Chinese. A total of ten teams submitted systems for task 1, and one team participated in task 2; nine teams also submitted a system description paper. Here, we present the tasks, analyze the results, and discuss the system submissions and the methods they used. Most submissions achieved sizable improvements over several baselines, and the best systems used pre-trained Transformers and ensembles. The data, the scorers and the leaderboards for the tasks are available at http://gitlab.com/NLP4IF/nlp4if-2021.
This paper describes Slav-NER: the 3rd Multilingual Named Entity Challenge in Slavic languages. The tasks involve recognizing mentions of named entities in Web documents, normalization of the names, and cross-lingual linking. The Challenge covers six languages and five entity types, and is organized as part of the 8th Balto-Slavic Natural Language Processing Workshop, co-located with the EACL 2021 Conference. Ten teams participated in the competition. Performance for the named entity recognition task reached 90% F-measure, much higher than reported in the first edition of the Challenge. Seven teams covered all six languages, and five teams participated in the cross-lingual entity linking task. Detailed valuation information is available on the shared task web page.
Propaganda can be defined as a form of communication that aims to influence the opinions or the actions of people towards a specific goal; this is achieved by means of well-defined rhetorical and psychological devices. Propaganda, in the form we know it today, can be dated back to the beginning of the 17th century. However, it is with the advent of the Internet and the social media that propaganda has started to spread on a much larger scale than before, thus becoming major societal and political issue. Nowadays, a large fraction of propaganda in social media is multimodal, mixing textual with visual content. With this in mind, here we propose a new multi-label multimodal task: detecting the type of propaganda techniques used in memes. We further create and release a new corpus of 950 memes, carefully annotated with 22 propaganda techniques, which can appear in the text, in the image, or in both. Our analysis of the corpus shows that understanding both modalities together is essential for detecting these techniques. This is further confirmed in our experiments with several state-of-the-art multimodal models.
While pre-trained language models (PLMs) are the go-to solution to tackle many natural language processing problems, they are still very limited in their ability to capture and to use common-sense knowledge. In fact, even if information is available in the form of approximate (soft) logical rules, it is not clear how to transfer it to a PLM in order to improve its performance for deductive reasoning tasks. Here, we aim to bridge this gap by teaching PLMs how to reason with soft Horn rules. We introduce a classification task where, given facts and soft rules, the PLM should return a prediction with a probability for a given hypothesis. We release the first dataset for this task, and we propose a revised loss function that enables the PLM to learn how to predict precise probabilities for the task. Our evaluation results show that the resulting fine-tuned models achieve very high performance, even on logical rules that were unseen at training. Moreover, we demonstrate that logical notions expressed by the rules are transferred to the fine-tuned model, yielding state-of-the-art results on external datasets.
Stance detection concerns the classification of a writer’s viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with respect to a claim vs. an (implicit) topic. Moreover, task definitions vary, which includes the label inventory, the data collection, and the annotation protocol. All these aspects hinder cross-domain studies, as they require changes to standard domain adaptation approaches. In this paper, we perform an in-depth analysis of 16 stance detection datasets, and we explore the possibility for cross-domain learning from them. Moreover, we propose an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels. In particular, we combine domain adaptation techniques such as mixture of experts and domain-adversarial training with label embeddings, and we demonstrate sizable performance gains over strong baselines, both (i) in-domain, i.e., for seen targets, and (ii) out-of-domain, i.e., for unseen targets. Finally, we perform an exhaustive analysis of the cross-domain results, and we highlight the important factors influencing the model performance.
We describe SemEval-2021 task 6 on Detection of Persuasion Techniques in Texts and Images: the data, the annotation guidelines, the evaluation setup, the results, and the participating systems. The task focused on memes and had three subtasks: (i) detecting the techniques in the text, (ii) detecting the text spans where the techniques are used, and (iii) detecting techniques in the entire meme, i.e., both in the text and in the image. It was a popular task, attracting 71 registrations, and 22 teams that eventually made an official submission on the test set. The evaluation results for the third subtask confirmed the importance of both modalities, the text and the image. Moreover, some teams reported benefits when not just combining the two modalities, e.g., by using early or late fusion, but rather modeling the interaction between them in a joint model.
We explore the task of predicting the leading political ideology or bias of news articles. First, we collect and release a large dataset of 34,737 articles that were manually annotated for political ideology –left, center, or right–, which is well-balanced across both topics and media. We further use a challenging experimental setup where the test examples come from media that were not seen during training, which prevents the model from learning to detect the source of the target news article instead of predicting its political ideology. From a modeling perspective, we propose an adversarial media adaptation, as well as a specially adapted triplet loss. We further add background information about the source, and we show that it is quite helpful for improving article-level prediction. Our experimental results show very sizable improvements over using state-of-the-art pre-trained Transformers in this challenging setup.
We propose EXAMS – a new benchmark dataset for cross-lingual and multilingual question answering for high school examinations. We collected more than 24,000 high-quality high school exam questions in 16 languages, covering 8 language families and 24 school subjects from Natural Sciences and Social Sciences, among others.EXAMS offers unique fine-grained evaluation framework across multiple languages and subjects, which allows precise analysis and comparison of the proposed models. We perform various experiments with existing top-performing multilingual pre-trained models and show that EXAMS offers multiple challenges that require multilingual knowledge and reasoning in multiple domains. We hope that EXAMS will enable researchers to explore challenging reasoning and knowledge transfer methods and pre-trained models for school question answering in various languages which was not possible by now. The data, code, pre-trained models, and evaluation are available at http://github.com/mhardalov/exams-qa.
Deep neural networks have become the standard approach to building reliable Natural Language Processing (NLP) applications, ranging from Neural Machine Translation (NMT) to dialogue systems. However, improving accuracy by increasing the model size requires a large number of hardware computations, which can slow down NLP applications significantly at inference time. To address this issue, we propose a novel vector-vector-matrix architecture (VVMA), which greatly reduces the latency at inference time for NMT. This architecture takes advantage of specialized hardware that has low-latency vector-vector operations and higher-latency vector-matrix operations. It also reduces the number of parameters and FLOPs for virtually all models that rely on efficient matrix multipliers without significantly impacting accuracy. We present empirical results suggesting that our framework can reduce the latency of sequence-to-sequence and Transformer models used for NMT by a factor of four. Finally, we show evidence suggesting that our VVMA extends to other domains, and we discuss novel hardware for its efficient use.
The rise of social media has democratized content creation and has made it easy for everybody to share and spread information online. On the positive side, this has given rise to citizen journalism, thus enabling much faster dissemination of information compared to what was possible with newspapers, radio, and TV. On the negative side, stripping traditional media from their gate-keeping role has left the public unprotected against the spread of misinformation, which could now travel at breaking-news speed over the same democratic channel. This has given rise to the proliferation of false information specifically created to affect individual people’s beliefs, and ultimately to influence major events such as political elections. There are strong indications that false information was weaponized at an unprecedented scale during Brexit and the 2016 U.S. presidential elections. “Fake news,” which can be defined as fabricated information that mimics news media content in form but not in organizational process or intent, became the Word of the Year for 2017, according to Collins Dictionary. Thus, limiting the spread of “fake news” and its impact has become a major focus for computer scientists, journalists, social media companies, and regulatory authorities. The tutorial will offer an overview of the broad and emerging research area of disinformation, with focus on the latest developments and research directions.
We present the results and the main findings of SemEval-2020 Task 11 on Detection of Propaganda Techniques in News Articles. The task featured two subtasks. Subtask SI is about Span Identification: given a plain-text document, spot the specific text fragments containing propaganda. Subtask TC is about Technique Classification: given a specific text fragment, in the context of a full document, determine the propaganda technique it uses, choosing from an inventory of 14 possible propaganda techniques. The task attracted a large number of participants: 250 teams signed up to participate and 44 made a submission on the test set. In this paper, we present the task, analyze the results, and discuss the system submissions and the methods they used. For both subtasks, the best systems used pre-trained Transformers and ensembles.
We present the results and the main findings of SemEval-2020 Task 12 on Multilingual Offensive Language Identification in Social Media (OffensEval-2020). The task included three subtasks corresponding to the hierarchical taxonomy of the OLID schema from OffensEval-2019, and it was offered in five languages: Arabic, Danish, English, Greek, and Turkish. OffensEval-2020 was one of the most popular tasks at SemEval-2020, attracting a large number of participants across all subtasks and languages: a total of 528 teams signed up to participate in the task, 145 teams submitted official runs on the test data, and 70 teams submitted system description papers.
We describe our system for SemEval-2020 Task 11 on Detection of Propaganda Techniques in News Articles. We developed ensemble models using RoBERTa-based neural architectures, additional CRF layers, transfer learning between the two subtasks, and advanced post-processing to handle the multi-label nature of the task, the consistency between nested spans, repetitions, and labels from similar spans in training. We achieved sizable improvements over baseline fine-tuned RoBERTa models, and the official evaluation ranked our system 3rd (almost tied with the 2nd) out of 36 teams on the span identification subtask with an F1 score of 0.491, and 2nd (almost tied with the 1st) out of 31 teams on the technique classification subtask with an F1 score of 0.62.
Discovering the stances of media outlets and influential people on current, debatable topics is important for social statisticians and policy makers. Many supervised solutions exist for determining viewpoints, but manually annotating training data is costly. In this paper, we propose a cascaded method that uses unsupervised learning to ascertain the stance of Twitter users with respect to a polarizing topic by leveraging their retweet behavior; then, it uses supervised learning based on user labels to characterize both the general political leaning of online media and of popular Twitter users, as well as their stance with respect to the target polarizing topic. We evaluate the model by comparing its predictions to gold labels from the Media Bias/Fact Check website, achieving 82.6% accuracy.
Predicting the political bias and the factuality of reporting of entire news outlets are critical elements of media profiling, which is an understudied but an increasingly important research direction. The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim, either manually or automatically. Thus, it has been proposed to profile entire news outlets and to look for those that are likely to publish fake or biased content. This makes it possible to detect likely “fake news” the moment they are published, by simply checking the reliability of their source. From a practical perspective, political bias and factuality of reporting have a linguistic aspect but also a social context. Here, we study the impact of both, namely (i) what was written (i.e., what was published by the target medium, and how it describes itself in Twitter) vs. (ii) who reads it (i.e., analyzing the target medium’s audience on social media). We further study (iii) what was written about the target medium (in Wikipedia). The evaluation results show that what was written matters most, and we further show that putting all information sources together yields huge improvements over the current state-of-the-art.
The recent proliferation of ”fake news” has triggered a number of responses, most notably the emergence of several manual fact-checking initiatives. As a result and over time, a large number of fact-checked claims have been accumulated, which increases the likelihood that a new claim in social media or a new statement by a politician might have already been fact-checked by some trusted fact-checking organization, as viral claims often come back after a while in social media, and politicians like to repeat their favorite statements, true or false, over and over again. As manual fact-checking is very time-consuming (and fully automatic fact-checking has credibility issues), it is important to try to save this effort and to avoid wasting time on claims that have already been fact-checked. Interestingly, despite the importance of the task, it has been largely ignored by the research community so far. Here, we aim to bridge this gap. In particular, we formulate the task and we discuss how it relates to, but also differs from, previous work. We further create a specialized dataset, which we release to the research community. Finally, we present learning-to-rank experiments that demonstrate sizable improvements over state-of-the-art retrieval and textual similarity approaches.
Recent events, such as the 2016 US Presidential Campaign, Brexit and the COVID-19 “infodemic”, have brought into the spotlight the dangers of online disinformation. There has been a lot of research focusing on fact-checking and disinformation detection. However, little attention has been paid to the specific rhetorical and psychological techniques used to convey propaganda messages. Revealing the use of such techniques can help promote media literacy and critical thinking, and eventually contribute to limiting the impact of “fake news” and disinformation campaigns. Prta (Propaganda Persuasion Techniques Analyzer) allows users to explore the articles crawled on a regular basis by highlighting the spans in which propaganda techniques occur and to compare them on the basis of their use of propaganda techniques. The system further reports statistics about the use of such techniques, overall and over time, or according to filtering criteria specified by the user based on time interval, keywords, and/or political orientation of the media. Moreover, it allows users to analyze any text or URL through a dedicated interface or via an API. The system is available online: https://www.tanbih.org/prta.
As offensive content has become pervasive in social media, there has been much research in identifying potentially offensive messages. However, previous work on this topic did not consider the problem as a whole, but rather focused on detecting very specific types of offensive content, e.g., hate speech, cyberbulling, or cyber-aggression. In contrast, here we target several different kinds of offensive content. In particular, we model the task hierarchically, identifying the type and the target of offensive messages in social media. For this purpose, we complied the Offensive Language Identification Dataset (OLID), a new dataset with tweets annotated for offensive content using a fine-grained three-layer annotation scheme, which we make publicly available. We discuss the main similarities and differences between OLID and pre-existing datasets for hate speech identification, aggression detection, and similar tasks. We further experiment with and we compare the performance of different machine learning models on OLID.
Recent work has shown that contextualized word representations derived from neural machine translation are a viable alternative to such from simple word predictions tasks. This is because the internal understanding that needs to be built in order to be able to translate from one language to another is much more comprehensive. Unfortunately, computational and memory limitations as of present prevent NMT models from using large word vocabularies, and thus alternatives such as subword units (BPE and morphological segmentations) and characters have been used. Here we study the impact of using different kinds of units on the quality of the resulting representations when used to model morphology, syntax, and semantics. We found that while representations derived from subwords are slightly better for modeling syntax, character-based representations are superior for modeling morphology and are also more robust to noisy input.
In the context of fake news, bias, and propaganda, we study two important but relatively under-explored problems: (i) trustworthiness estimation (on a 3-point scale) and (ii) political ideology detection (left/right bias on a 7-point scale) of entire news outlets, as opposed to evaluating individual articles. In particular, we propose a multi-task ordinal regression framework that models the two problems jointly. This is motivated by the observation that hyper-partisanship is often linked to low trustworthiness, e.g., appealing to emotions rather than sticking to the facts, while center media tend to be generally more impartial and trustworthy. We further use several auxiliary tasks, modeling centrality, hyper-partisanship, as well as left-vs.-right bias on a coarse-grained scale. The evaluation results show sizable performance gains by the joint models over models that target the problems in isolation.
We investigate the political roles of “Internet trolls” in social media. Political trolls, such as the ones linked to the Russian Internet Research Agency (IRA), have recently gained enormous attention for their ability to sway public opinion and even influence elections. Analysis of the online traces of trolls has shown different behavioral patterns, which target different slices of the population. However, this analysis is manual and labor-intensive, thus making it impractical as a first-response tool for newly-discovered troll farms. In this paper, we show how to automate this analysis by using machine learning in a realistic setting. In particular, we show how to classify trolls according to their political role —left, news feed, right— by using features extracted from social media, i.e., Twitter, in two scenarios: (i) in a traditional supervised learning scenario, where labels for trolls are available, and (ii) in a distant supervision scenario, where labels for trolls are not available, and we rely on more-commonly-available labels for news outlets mentioned by the trolls. Technically, we leverage the community structure and the text of the messages in the online social network of trolls represented as a graph, from which we extract several types of learned representations, i.e., embeddings, for the trolls. Experiments on the “IRA Russian Troll” dataset show that our methodology improves over the state-of-the-art in the first scenario, while providing a compelling case for the second scenario, which has not been explored in the literature thus far.
Stacking long short-term memory (LSTM) cells or gated recurrent units (GRUs) as part of a recurrent neural network (RNN) has become a standard approach to solving a number of tasks ranging from language modeling to text summarization. Although LSTMs and GRUs were designed to model long-range dependencies more accurately than conventional RNNs, they nevertheless have problems copying or recalling information from the long distant past. Here, we derive a phase-coded representation of the memory state, Rotational Unit of Memory (RUM), that unifies the concepts of unitary learning and associative memory. We show experimentally that RNNs based on RUMs can solve basic sequential tasks such as memory copying and memory recall much better than LSTMs/GRUs. We further demonstrate that by replacing LSTM/GRU with RUM units we can apply neural networks to real-world problems such as language modeling and text summarization, yielding results comparable to the state of the art.
We present the results and the main findings of SemEval-2019 Task 6 on Identifying and Categorizing Offensive Language in Social Media (OffensEval). The task was based on a new dataset, the Offensive Language Identification Dataset (OLID), which contains over 14,000 English tweets, and it featured three sub-tasks. In sub-task A, systems were asked to discriminate between offensive and non-offensive posts. In sub-task B, systems had to identify the type of offensive content in the post. Finally, in sub-task C, systems had to detect the target of the offensive posts. OffensEval attracted a large number of participants and it was one of the most popular tasks in SemEval-2019. In total, nearly 800 teams signed up to participate in the task and 115 of them submitted results, which are presented and analyzed in this report.
We present SemEval-2019 Task 8 on Fact Checking in Community Question Answering Forums, which features two subtasks. Subtask A is about deciding whether a question asks for factual information vs. an opinion/advice vs. just socializing. Subtask B asks to predict whether an answer to a factual question is true, false or not a proper answer. We received 17 official submissions for subtask A and 11 official submissions for Subtask B. For subtask A, all systems improved over the majority class baseline. For Subtask B, all systems were below a majority class baseline, but several systems were very close to it. The leaderboard and the data from the competition can be found at http://competitions.codalab.org/competitions/20022.
We describe the system submitted by the Jack Ryder team to SemEval-2019 Task 4 on Hyperpartisan News Detection. The task asked participants to predict whether a given article is hyperpartisan, i.e., extreme-left or extreme-right. We proposed an approach based on BERT with fine-tuning, which was ranked 7th out 28 teams on the distantly supervised dataset, where all articles from a hyperpartisan/non-hyperpartisan news outlet are considered to be hyperpartisan/non-hyperpartisan. On a manually annotated test dataset, where human annotators double-checked the labels, we were ranked 29th out of 42 teams.
We describe our submission to SemEval-2019 Task 4 on Hyperpartisan News Detection. We rely on a variety of engineered features originally used to detect propaganda. This is based on the assumption that biased messages are propagandistic and promote a particular political cause or viewpoint. In particular, we trained a logistic regression model with features ranging from simple bag of words to vocabulary richness and text readability. Our system achieved 72.9% accuracy on the manually annotated testset, and 60.8% on the test data that was obtained with distant supervision. Additional experiments showed that significant performance gains can be achieved with better feature pre-processing.
Online media aim for reaching ever bigger audience and for attracting ever longer attention span. This competition creates an environment that rewards sensational, fake, and toxic news. To help limit their spread and impact, we propose and develop a news toxicity detector that can recognize various types of toxic content. While previous research primarily focused on English, here we target Bulgarian. We created a new dataset by crawling a website that for five years has been collecting Bulgarian news articles that were manually categorized into eight toxicity groups. Then we trained a multi-class classifier with nine categories: eight toxic and one non-toxic. We experimented with different representations based on ElMo, BERT, and XLM, as well as with a variety of domain-specific features. Due to the small size of our dataset, we created a separate model for each feature type, and we ultimately combined these models into a meta-classifier. The evaluation results show an accuracy of 59.0% and a macro-F1 score of 39.7%, which represent sizable improvements over the majority-class baseline (Acc=30.3%, macro-F1=5.2%).
Recently, reading comprehension models achieved near-human performance on large-scale datasets such as SQuAD, CoQA, MS Macro, RACE, etc. This is largely due to the release of pre-trained contextualized representations such as BERT and ELMo, which can be fine-tuned for the target task. Despite those advances and the creation of more challenging datasets, most of the work is still done for English. Here, we study the effectiveness of multilingual BERT fine-tuned on large-scale English datasets for reading comprehension (e.g., for RACE), and we apply it to Bulgarian multiple-choice reading comprehension. We propose a new dataset containing 2,221 questions from matriculation exams for twelfth grade in various subjects —history, biology, geography and philosophy—, and 412 additional questions from online quizzes in history. While the quiz authors gave no relevant context, we incorporate knowledge from Wikipedia, retrieving documents matching the combination of question + each answer option. Moreover, we experiment with different indexing and pre-training strategies. The evaluation results show accuracy of 42.23%, which is well above the baseline of 24.89%.
We propose a morphologically informed model for named entity recognition, which is based on LSTM-CRF architecture and combines word embeddings, Bi-LSTM character embeddings, part-of-speech (POS) tags, and morphological information. While previous work has focused on learning from raw word input, using word and character embeddings only, we show that for morphologically rich languages, such as Bulgarian, access to POS information contributes more to the performance gains than the detailed morphological information. Thus, we show that named entity recognition needs only coarse-grained POS tags, but at the same time it can benefit from simultaneously using some POS information of different granularity. Our evaluation results over a standard dataset show sizeable improvements over the state-of-the-art for Bulgarian NER.
We propose a multi-task deep-learning approach for estimating the check-worthiness of claims in political debates. Given a political debate, such as the 2016 US Presidential and Vice-Presidential ones, the task is to predict which statements in the debate should be prioritized for fact-checking. While different fact-checking organizations would naturally make different choices when analyzing the same debate, we show that it pays to learn from multiple sources simultaneously (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post) in a multi-task learning setup, even when a particular source is chosen as a target to imitate. Our evaluation shows state-of-the-art results on a standard dataset for the task of check-worthiness prediction.
The recent explosion of false claims in social media and on the Web in general has given rise to a lot of manual fact-checking initiatives. Unfortunately, the number of claims that need to be fact-checked is several orders of magnitude larger than what humans can handle manually. Thus, there has been a lot of research aiming at automating the process. Interestingly, previous work has largely ignored the growing number of claims about images. This is despite the fact that visual imagery is more influential than text and naturally appears alongside fake news. Here we aim at bridging this gap. In particular, we create a new dataset for this problem, and we explore a variety of features modeling the claim, the image, and the relationship between the claim and the image. The evaluation results show sizable improvements over the baseline. We release our dataset, hoping to enable further research on fact-checking claims about images.
The ongoing neural revolution in machine translation has made it easier to model larger contexts beyond the sentence-level, which can potentially help resolve some discourse-level ambiguities such as pronominal anaphora, thus enabling better translations. Unfortunately, even when the resulting improvements are seen as substantial by humans, they remain virtually unnoticed by traditional automatic evaluation measures like BLEU, as only a few words end up being affected. Thus, specialized evaluation measures are needed. With this aim in mind, we contribute an extensive, targeted dataset that can be used as a test suite for pronoun translation, covering multiple source languages and different pronoun errors drawn from real system translations, for English. We further propose an evaluation measure to differentiate good and bad pronoun translations. We also conduct a user study to report correlations with human judgments.
We study cross-lingual stance detection, which aims to leverage labeled data in one language to identify the relative perspective (or stance) of a given document with respect to a claim in a different target language. In particular, we introduce a novel contrastive language adaptation approach applied to memory networks, which ensures accurate alignment of stances in the source and target languages, and can effectively deal with the challenge of limited labeled data in the target language. The evaluation results on public benchmark datasets and comparison against current state-of-the-art approaches demonstrate the effectiveness of our approach.
Propaganda aims at influencing people’s mindset with the purpose of advancing a specific agenda. Previous work has addressed propaganda detection at document level, typically labelling all articles from a propagandistic news outlet as propaganda. Such noisy gold labels inevitably affect the quality of any learning system trained on them. A further issue with most existing systems is the lack of explainability. To overcome these limitations, we propose a novel task: performing fine-grained analysis of texts by detecting all fragments that contain propaganda techniques as well as their type. In particular, we create a corpus of news articles manually annotated at fragment level with eighteen propaganda techniques and propose a suitable evaluation measure. We further design a novel multi-granularity neural network, and we show that it outperforms several strong BERT-based baselines.
We introduce Tanbih, a news aggregator with intelligent analysis tools to help readers understanding what’s behind a news story. Our system displays news grouped into events and generates media profiles that show the general factuality of reporting, the degree of propagandistic content, hyper-partisanship, leading political ideology, general frame of reporting, and stance with respect to various claims and topics of a news outlet. In addition, we automatically analyse each article to detect whether it is propagandistic and to determine its stance with respect to a number of controversial topics.
We present the shared task on Fine-Grained Propaganda Detection, which was organized as part of the NLP4IF workshop at EMNLP-IJCNLP 2019. There were two subtasks. FLC is a fragment-level task that asks for the identification of propagandist text fragments in a news article and also for the prediction of the specific propaganda technique used in each such fragment (18-way classification task). SLC is a sentence-level binary classification task asking to detect the sentences that contain propaganda. A total of 12 teams submitted systems for the FLC task, 25 teams did so for the SLC task, and 14 teams eventually submitted a system description paper. For both subtasks, most systems managed to beat the baseline by a sizable margin. The leaderboard and the data from the competition are available at http://propaganda.qcri.org/nlp4if-shared-task/.
We address the problem of detecting duplicate questions in forums, which is an important step towards automating the process of answering new questions. As finding and annotating such potential duplicates manually is very tedious and costly, automatic methods based on machine learning are a viable alternative. However, many forums do not have annotated data, i.e., questions labeled by experts as duplicates, and thus a promising solution is to use domain adaptation from another forum that has such annotations. Here we focus on adversarial domain adaptation, deriving important findings about when it performs well and what properties of the domains are important in this regard. Our experiments with StackExchange data show an average improvement of 5.6% over the best baseline across multiple pairs of domains.
We present a study on predicting the factuality of reporting and bias of news media. While previous work has focused on studying the veracity of claims or documents, here we are interested in characterizing entire news media. This is an under-studied, but arguably important research problem, both in its own right and as a prior for fact-checking systems. We experiment with a large list of news websites and with a rich set of features derived from (i) a sample of articles from the target news media, (ii) its Wikipedia page, (iii) its Twitter account, (iv) the structure of its URL, and (v) information about the Web traffic it attracts. The experimental results show sizable performance gains over the baseline, and reveal the importance of each feature type.
We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question. We further use an auxiliary task to complement the previous two, i.e., (iii) find good answers with respect to the thread question in a question-comment thread. We use deep neural networks (DNNs) to learn meaningful task-specific embeddings, which we then incorporate into a conditional random field (CRF) model for the multitask setting, performing joint learning over a complex graph structure. While DNNs alone achieve competitive results when trained to produce the embeddings, the CRF, which makes use of the embeddings and the dependencies between the tasks, improves the results significantly and consistently across a variety of evaluation metrics, thus showing the complementarity of DNNs and structured learning.
We present an effective end-to-end memory network model that jointly (i) predicts whether a given document can be considered as relevant evidence for a given claim, and (ii) extracts snippets of evidence that can be used to reason about the factuality of the target claim. Our model combines the advantages of convolutional and recurrent neural networks as part of a memory network. We further introduce a similarity matrix at the inference level of the memory network in order to extract snippets of evidence for input claims more accurately. Our experiments on a public benchmark dataset, FakeNewsChallenge, demonstrate the effectiveness of our approach.
A reasonable approach for fact checking a claim involves retrieving potentially relevant documents from different sources (e.g., news websites, social media, etc.), determining the stance of each document with respect to the claim, and finally making a prediction about the claim’s factuality by aggregating the strength of the stances, while taking the reliability of the source into account. Moreover, a fact checking system should be able to explain its decision by providing relevant extracts (rationales) from the documents. Yet, this setup is not directly supported by existing datasets, which treat fact checking, document retrieval, source credibility, stance detection and rationale extraction as independent tasks. In this paper, we support the interdependencies between these tasks as annotations in the same corpus. We implement this setup on an Arabic fact checking corpus, the first of its kind.
We present ClaimRank, an online system for detecting check-worthy claims. While originally trained on political debates, the system can work for any kind of text, e.g., interviews or just regular news articles. Its aim is to facilitate manual fact-checking efforts by prioritizing the claims that fact-checkers should consider first. ClaimRank supports both Arabic and English, it is trained on actual annotations from nine reputable fact-checking organizations (PolitiFact, FactCheck, ABC, CNN, NPR, NYT, Chicago Tribune, The Guardian, and Washington Post), and thus it can mimic the claim selection strategies for each and any of them, as well as for the union of them all.
We present the results and the findings of the Second VarDial Evaluation Campaign on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects. The campaign was organized as part of the fifth edition of the VarDial workshop, collocated with COLING’2018. This year, the campaign included five shared tasks, including two task re-runs – Arabic Dialect Identification (ADI) and German Dialect Identification (GDI) –, and three new tasks – Morphosyntactic Tagging of Tweets (MTT), Discriminating between Dutch and Flemish in Subtitles (DFS), and Indo-Aryan Language Identification (ILI). A total of 24 teams submitted runs across the five shared tasks, and contributed 22 system description papers, which were included in the VarDial workshop proceedings and are referred to in this report.
In this article, we explore the potential of using sentence-level discourse structure for machine translation evaluation. We first design discourse-aware similarity measures, which use all-subtree kernels to compare discourse parse trees in accordance with the Rhetorical Structure Theory (RST). Then, we show that a simple linear combination with these measures can help improve various existing machine translation evaluation metrics regarding correlation with human judgments both at the segment level and at the system level. This suggests that discourse information is complementary to the information used by many of the existing evaluation metrics, and thus it could be taken into account when developing richer evaluation metrics, such as the WMT-14 winning combined metric DiscoTKparty. We also provide a detailed analysis of the relevance of various discourse elements and relations from the RST parse trees for machine translation evaluation. In particular, we show that (i) all aspects of the RST tree are relevant, (ii) nuclearity is more useful than relation type, and (iii) the similarity of the translation RST tree to the reference RST tree is positively correlated with translation quality.
We describe SemEval–2017 Task 3 on Community Question Answering. This year, we reran the four subtasks from SemEval-2016: (A) Question–Comment Similarity, (B) Question–Question Similarity, (C) Question–External Comment Similarity, and (D) Rerank the correct answers for a new question in Arabic, providing all the data from 2015 and 2016 for training, and fresh data for testing. Additionally, we added a new subtask E in order to enable experimentation with Multi-domain Question Duplicate Detection in a larger-scale scenario, using StackExchange subforums. A total of 23 teams participated in the task, and submitted a total of 85 runs (36 primary and 49 contrastive) for subtasks A–D. Unfortunately, no teams participated in subtask E. A variety of approaches and features were used by the participating systems to address the different subtasks. The best systems achieved an official score (MAP) of 88.43, 47.22, 15.46, and 61.16 in subtasks A, B, C, and D, respectively. These scores are better than the baselines, especially for subtasks A–C.
This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a two-point and on a five-point ordinal scale, and quantification of the distribution of sentiment towards a topic across a number of tweets: again on a two-point and on a five-point ordinal scale. Compared to 2016, we made two changes: (i) we introduced a new language, Arabic, for all subtasks, and (ii) we made available information from the profiles of the Twitter users who posted the target tweets. The task continues to be very popular, with a total of 48 teams participating this year.
We propose to use question answering (QA) data from Web forums to train chat-bots from scratch, i.e., without dialog data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbot systems. The evaluation shows that the model achieves a MAP of 63.5% on the extrinsic task. Moreover, our manual evaluation demonstrates that the model can answer correctly 49.5% of the questions when they are similar in style to how questions are asked in the forum, and 47.3% of the questions, when they are more conversational in style.
In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new corpus of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.
It is completely amazing! Fake news and “click baits” have totally invaded the cyberspace. Let us face it: everybody hates them for three simple reasons. Reason #2 will absolutely amaze you. What these can achieve at the time of election will completely blow your mind! Now, we all agree, this cannot go on, you know, somebody has to stop it. So, we did this research, and trust us, it is totally great research, it really is! Make no mistake. This is the best research ever! Seriously, come have a look, we have it all: neural networks, attention mechanism, sentiment lexicons, author profiling, you name it. Lexical features, semantic features, we absolutely have it all. And we have totally tested it, trust us! We have results, and numbers, really big numbers. The best numbers ever! Oh, and analysis, absolutely top notch analysis. Interested? Come read the shocking truth about fake news and clickbait in the Bulgarian cyberspace. You won’t believe what we have found!
Given the constantly growing proliferation of false claims online in recent years, there has been also a growing research interest in automatically distinguishing false rumors from factually true claims. Here, we propose a general-purpose framework for fully-automatic fact checking using external sources, tapping the potential of the entire Web as a knowledge source to confirm or reject a claim. Our framework uses a deep neural network with LSTM text encoding to combine semantic kernels with task-specific embeddings that encode a claim together with pieces of potentially relevant text fragments from the Web, taking the source reliability into account. The evaluation results show good performance on two different tasks and datasets: (i) rumor detection and (ii) fact checking of the answers to a question in community question answering forums.
We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning algorithms. This is an under-explored research direction, which can allow better parameter tuning. In this paper, we achieve this goal by selecting a subset of the available sentence pairs, which are more suitable for specific combinations of optimizers, objective functions, and evaluation measures. We demonstrate the potential of the idea with the pairwise ranking optimization (PRO) optimizer, which is known to yield too short translations. We show that the learning problem can be alleviated by tuning on a subset of the development set, selected based on sentence length. In particular, using the longest 50% of the tuning sentences, we achieve two-fold tuning speedup, and improvements in BLEU score that rival those of alternatives, which fix BLEU+1’s smoothing instead.
We address information credibility in community forums, in a setting in which the credibility of an answer posted in a question thread by a particular user has to be predicted. First, we motivate the problem and we create a publicly available annotated English corpus by crowdsourcing. Second, we propose a large set of features to predict the credibility of the answers. The features model the user, the answer, the question, the thread as a whole, and the interaction between them. Our experiments with ranking SVMs show that the credibility labels can be predicted with high performance according to several standard IR ranking metrics, thus supporting the potential usage of this layer of credibility information in practical applications. The features modeling the profile of the user (in particular trollness) turn out to be most important, but embedding features modeling the answer and the similarity between the question and the answer are also very relevant. Overall, half of the gap between the baseline performance and the perfect classifier can be covered using the proposed features.
We present the results of the VarDial Evaluation Campaign on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects, which we organized as part of the fourth edition of the VarDial workshop at EACL’2017. This year, we included four shared tasks: Discriminating between Similar Languages (DSL), Arabic Dialect Identification (ADI), German Dialect Identification (GDI), and Cross-lingual Dependency Parsing (CLP). A total of 19 teams submitted runs across the four tasks, and 15 of them wrote system description papers.
We describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The task asked participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence. We further provided a lemmatized target-language human-authored translation of the source sentence, and automatic word alignments between the source sentence words and the target-language lemmata. The aim of the task was to predict, for each target-language pronoun placeholder, the word that should replace it from a small, closed set of classes, using any type of information that can be extracted from the entire document. We offered four subtasks, each for a different language pair and translation direction: English-to-French, English-to-German, German-to-English, and Spanish-to-English. Five teams participated in the shared task, making submissions for all language pairs. The evaluation results show that most participating teams outperformed two strong n-gram-based language model-based baseline systems by a sizable margin.
We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to learn high-level features that are discriminative for the main learning task, and at the same time are invariant across the input languages. The evaluation results show sizable improvements for our cross-language adversarial neural network (CLANN) model over a strong non-adversarial system.
We present the results of the third edition of the Discriminating between Similar Languages (DSL) shared task, which was organized as part of the VarDial’2016 workshop at COLING’2016. The challenge offered two subtasks: subtask 1 focused on the identification of very similar languages and language varieties in newswire texts, whereas subtask 2 dealt with Arabic dialect identification in speech transcripts. A total of 37 teams registered to participate in the task, 24 teams submitted test results, and 20 teams also wrote system description papers. High-order character n-grams were the most successful feature, and the best classification approaches included traditional supervised learning methods such as SVM, logistic regression, and language models, while deep learning approaches did not perform very well.
Negation and modality are two important grammatical phenomena that have attracted recent research attention as they can contribute to extra-propositional meaning aspects, among with factuality, attribution, irony and sarcasm. These aspects go beyond analysis such as semantic role labeling, and modeling them is important as a step towards a higher level of language understanding, which is needed for practical applications such as sentiment analysis. In this talk, I will go beyond English, and I will discuss how negation and modality are expressed in other languages. I will also go beyond sentiment analysis and I will present some challenges that the two phenomena pose for machine translation (MT). In particular, I will demonstrate how contemporary MT systems fail on them, and I will discuss some possible solutions.
Sentiment polarity lexicons are key resources for sentiment analysis, and researchers have invested a lot of efforts in their manual creation. However, there has been a recent shift towards automatically extracted lexicons, which are orders of magnitude larger and perform much better. These lexicons are typically mined using bootstrapping, starting from very few seed words whose polarity is given, e.g., 50-60 words, and sometimes even just 5-6. Here we demonstrate that much higher-quality lexicons can be built by starting with hundreds of words and phrases as seeds, especially when they are in-domain. Thus, we combine (i) mid-sized high-quality manually crafted lexicons as seeds and (ii) bootstrapping, in order to build large-scale lexicons.
We present an interactive system to provide effective and efficient search capabilities in Community Question Answering (cQA) forums. The system integrates state-of-the-art technology for answer search with a Web-based user interface specifically tailored to support the cQA forum readers. The answer search module automatically finds relevant answers for a new question by exploring related questions and the comments within their threads. The graphical user interface presents the search results and supports the exploration of related information. The system is running live at http://www.qatarliving.com/betasearch/.
Every non-trivial text describes interactions and relations between people, institutions, activities, events and so on. What we know about the world consists in large part of such relations, and that knowledge contributes to the understanding of what texts refer to. Newly found relations can in turn become part of this knowledge that is stored for future use.To grasp a text’s semantic content, an automatic system must be able to recognize relations in texts and reason about them. This may be done by applying and updating previously acquired knowledge. We focus here in particular on semantic relations which describe the interactions among nouns and compact noun phrases, and we present such relations from both a theoretical and a practical perspective. The theoretical exploration sketches the historical path which has brought us to the contemporary view and interpretation of semantic relations. We discuss a wide range of relation inventories proposed by linguists and by language processing people. Such inventories vary by domain, granularity and suitability for downstream applications.On the practical side, we investigate the recognition and acquisition of relations from texts. In a look at supervised learning methods, we present available datasets, the variety of features which can describe relation instances, and learning algorithms found appropriate for the task. Next, we present weakly supervised and unsupervised learning methods of acquiring relations from large corpora with little or no previously annotated data. We show how enduring the bootstrapping algorithm based on seed examples or patterns has proved to be, and how it has been adapted to tackle Web-scale text collections. We also show a few machine learning techniques which can perform fast and reliable relation extraction by taking advantage of data redundancy and variability.
We describe the Arabic-English and English-Arabic statistical machine translation systems developed by the Qatar Computing Research Institute for the IWSLT’2013 evaluation campaign on spoken language translation. We used one phrase-based and two hierarchical decoders, exploring various settings thereof. We further experimented with three domain adaptation methods, and with various Arabic word segmentation schemes. Combining the output of several systems yielded a gain of up to 3.4 BLEU points over the baseline. Here we also describe a specialized normalization scheme for evaluating Arabic output, which was adopted for the IWSLT’2013 evaluation campaign.
We describe the system developed by the team of the National University of Singapore for the Chinese-English BTEC task of the IWSLT 2009 evaluation campaign. We adopted a state-of-the-art phrase-based statistical machine translation approach and focused on experiments with different Chinese word segmentation standards. In our official submission, we trained a separate system for each segmenter and we combined the outputs in a subsequent re-ranking step. Given the small size of the training data, we further re-trained the system on the development data after tuning. The evaluation results show that both strategies yield sizeable and consistent improvements in translation quality.