Noisily labeled textual data is ample on internet platforms that allow user-created content. Training models, such as offensive language detection models for comment moderation, on such data may prove difficult as the noise in the labels prevents the model to converge. In this work, we propose to use active learning methods for the purposes of denoising training data for model training. The goal is to sample examples the most informative examples with noisy labels with active learning and send them to the oracle for reannotation thus reducing the overall cost of reannotation. In this setting we tested three existing active learning methods, namely DBAL, Variance of Gradients (VoG) and BADGE. The proposed approach to data denoising is tested on the problem of offensive language detection. We observe that active learning can be effectively used for the purposes of data denoising, however care should be taken when choosing the algorithm for this purpose.

Collaboration increasingly happens online. This is especially true for large groups working on global tasks, with collaborators all around the globe. The size and distributed nature of such groups makes decision-making challenging. This paper proposes a set of dialog acts for the study of decision-making mechanisms in such groups, and provides a new annotated dataset based on real-world data from the public mail-archives of one such organisation – the Internet Engineering Task Force (IETF). We provide an initial data analysis showing that this dataset can be used to better understand decision-making in such organisations. Finally, we experiment with a preliminary transformer-based dialog act tagging model.

Social science and psycholinguistic research have shown that power and status affect how people use language in a range of domains. Here, we investigate a similar question in a large, distributed, consensus-driven community with little traditional power hierarchy – the Internet Engineering Task Force (IETF), a collaborative organisation that designs internet standards. Our analysis based on lexical categories (LIWC) and BERT, shows that participants’ levels of influence can be predicted from their email text, and identify key linguistic differences (e.g., certain LIWC categories, such as “WE” are positively correlated with high-influence). We also identify the differences in language use for the same person before and after becoming influential.

Text simplification is a method for improving the accessibility of text by converting complex sentences into simple sentences. Multiple studies have been done to create datasets for text simplification. However, most of these datasets focus on high-resource languages only. In this work, we proposed a complex word dataset for Hindi, a language largely ignored in text simplification literature. We used various Hindi knowledge annotators for annotation to capture the annotator’s language knowledge. Our analysis shows a significant difference between native and non-native annotators’ perception of word complexity. We also built an automatic complex word classifier using a soft voting approach based on the predictions from tree-based ensemble classifiers. These models behave differently for annotations made by different categories of users, such as native and non-native speakers. Our dataset and analysis will help simplify Hindi text depending on the user’s language understanding. The dataset is available at https://zenodo.org/record/5229160.

In light of unprecedented increases in the popularity of the internet and social media, comment moderation has never been a more relevant task. Semi-automated comment moderation systems greatly aid human moderators by either automatically classifying the examples or allowing the moderators to prioritize which comments to consider first. However, the concept of inappropriate content is often subjective, and such content can be conveyed in many subtle and indirect ways. In this work, we propose CoRAL – a language and culturally aware Croatian Abusive dataset covering phenomena of implicitness and reliance on local and global context. We show experimentally that current models degrade when comments are not explicit and further degrade when language skill and context knowledge are required to interpret the comment.

Moderation of reader comments is a significant problem for online news platforms. Here, we experiment with models for automatic moderation, using a dataset of comments from a popular Croatian newspaper. Our analysis shows that while comments that violate the moderation rules mostly share common linguistic and thematic features, their content varies across the different sections of the newspaper. We therefore make our models topic-aware, incorporating semantic features from a topic model into the classification decision. Our results show that topic information improves the performance of the model, increases its confidence in correct outputs, and helps us understand the model’s outputs.

We present a system for zero-shot cross-lingual offensive language and hate speech classification. The system was trained on English datasets and tested on a task of detecting hate speech and offensive social media content in a number of languages without any additional training. Experiments show an impressive ability of both models to generalize from English to other languages. There is however an expected gap in performance between the tested cross-lingual models and the monolingual models. The best performing model (offensive content classifier) is available online as a REST API.

This paper presents tools and data sources collected and released by the EMBEDDIA project, supported by the European Union’s Horizon 2020 research and innovation program. The collected resources were offered to participants of a hackathon organized as part of the EACL Hackashop on News Media Content Analysis and Automated Report Generation in February 2021. The hackathon had six participating teams who addressed different challenges, either from the list of proposed challenges or their own news-industry-related tasks. This paper goes beyond the scope of the hackathon, as it brings together in a coherent and compact form most of the resources developed, collected and released by the EMBEDDIA project. Moreover, it constitutes a handy source for news media industry and researchers in the fields of Natural Language Processing and Social Science.

The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the “Hub and Spoke” architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations learned by the encoder, we use two kinds of analyses. First, we evaluate the encoder pre-trained on the different vision-and-language tasks on an existing “diagnostic task” designed to assess multimodal semantic understanding. Second, we carry out a battery of analyses aimed at studying how the encoder merges and exploits the two modalities.

We propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! game, a two-player game where the goal is to identify an object in a complex visual scene by asking a sequence of yes/no questions. Our visually-grounded encoder leverages synergies between guessing and asking questions, as it is trained jointly using multi-task learning. We further enrich our model via a cooperative learning regime. We show that the introduction of both the joint architecture and cooperative learning lead to accuracy improvements over the baseline system. We compare our approach to an alternative system which extends the baseline with reinforcement learning. Our in-depth analysis shows that the linguistic skills of the two models differ dramatically, despite approaching comparable performance levels. This points at the importance of analyzing the linguistic output of competing systems beyond numeric comparison solely based on task success.

Our goal is to explore how the abilities brought in by a dialogue manager can be included in end-to-end visually grounded conversational agents. We make initial steps towards this general goal by augmenting a task-oriented visual dialogue model with a decision-making component that decides whether to ask a follow-up question to identify a target referent in an image, or to stop the conversation to make a guess. Our analyses show that adding a decision making component produces dialogues that are less repetitive and that include fewer unnecessary questions, thus potentially leading to more efficient and less unnatural interactions.

In this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities. To this end, we propose an extension of the MS-COCO dataset, FOIL-COCO, which associates images with both correct and ‘foil’ captions, that is, descriptions of the image that are highly similar to the original ones, but contain one single mistake (‘foil word’). We show that current LaVi models fall into the traps of this data and perform badly on three tasks: a) caption classification (correct vs. foil); b) foil word detection; c) foil word correction. Humans, in contrast, have near-perfect performance on those tasks. We demonstrate that merely utilising language cues is not enough to model FOIL-COCO and that it challenges the state-of-the-art by requiring a fine-grained understanding of the relation between text and image.