This is an internal, incomplete preview of a proposed change to the ACL Anthology.
For efficiency reasons, we generate only three BibTeX files per volume, and the preview may be incomplete in other ways, or contain mistakes.
Do not treat this content as an official publication.
Euphemisms are found across the world’s languages, making them a universal linguistic phenomenon. As such, euphemistic data may have useful properties for computational tasks across languages. In this study, we explore this premise by training a multilingual transformer model (XLM-RoBERTa) to disambiguate potentially euphemistic terms (PETs) in multilingual and cross-lingual settings. In line with current trends, we demonstrate that zero-shot learning across languages takes place. We also show cases where multilingual models perform better on the task compared to monolingual models by a statistically significant margin, indicating that multilingual data presents additional opportunities for models to learn about cross-lingual, computational properties of euphemisms. In a follow-up analysis, we focus on universal euphemistic “categories” such as death and bodily functions among others. We test to see whether cross-lingual data of the same domain is more important than within-language data of other domains to further understand the nature of the cross-lingual transfer.
This paper presents the Multilingual Euphemism Detection Shared Task for the Fourth Workshop on Figurative Language Processing (FigLang 2024) held in conjunction with NAACL 2024. Participants were invited to attempt the euphemism detection task on four different languages (American English, global Spanish, Yorùbá, and Mandarin Chinese): given input text containing a potentially euphemistic term (PET), determine if its use is euphemistic or not. We present the expanded datasets used for the shared task, summarize each team’s methods and findings, and analyze potential implications for future research.
Africa has over 2000 indigenous languages but they are under-represented in NLP research due to lack of datasets. In recent years, there have been progress in developing labelled corpora for African languages. However, they are often available in a single domain and may not generalize to other domains. In this paper, we focus on the task of sentiment classification for cross-domain adaptation. We create a new dataset, Nollywood movie reviews for five languages widely spoken in Nigeria (English, Hausa, Igbo, Nigerian Pidgin, and Yoruba). We provide an extensive empirical evaluation using classical machine learning methods and pre-trained language models. By leveraging transfer learning, we compare the performance of cross-domain adaptation from Twitter domain, and cross-lingual adaptation from English language. Our evaluation shows that transfer from English in the same target domain leads to more than 5% improvement in accuracy compared to transfer from Twitter in the same language. To further mitigate the domain difference, we leverage machine translation from English to other Nigerian languages, which leads to a further improvement of 7% over cross-lingual evaluation. While machine translation to low-resource languages are often of low quality, our analysis shows that sentiment related words are often preserved.
In this paper, we share our best performing submission to the Arabic AI Tasks Evaluation Challenge (ArAIEval) at ArabicNLP 2023. Our focus was on Task 1, which involves identifying persuasion techniques in excerpts from tweets and news articles. The persuasion technique in Arabic texts was detected using a training loop with XLM-RoBERTa, a language-agnostic text representation model. This approach proved to be potent, leveraging fine-tuning of a multilingual language model. In our evaluation of the test set, we achieved a micro F1 score of 0.64 for subtask A of the competition.
Transformers have been shown to work well for the task of English euphemism disambiguation, in which a potentially euphemistic term (PET) is classified as euphemistic or non-euphemistic in a particular context. In this study, we expand on the task in two ways. First, we annotate PETs for vagueness, a linguistic property associated with euphemisms, and find that transformers are generally better at classifying vague PETs, suggesting linguistic differences in the data that impact performance. Second, we present novel euphemism corpora in three different languages: Yoruba, Spanish, and Mandarin Chinese. We perform euphemism disambiguation experiments in each language using multilingual transformer models mBERT and XLM-RoBERTa, establishing preliminary results from which to launch future work.
This paper presents a linguistically driven proof of concept for finding potentially euphemistic terms, or PETs. Acknowledging that PETs tend to be commonly used expressions for a certain range of sensitive topics, we make use of distri- butional similarities to select and filter phrase candidates from a sentence and rank them using a set of simple sentiment-based metrics. We present the results of our approach tested on a corpus of sentences containing euphemisms, demonstrating its efficacy for detecting single and multi-word PETs from a broad range of topics. We also discuss future potential for sentiment-based methods on this task.
This paper presents The Shared Task on Euphemism Detection for the Third Workshop on Figurative Language Processing (FigLang 2022) held in conjunction with EMNLP 2022. Participants were invited to investigate the euphemism detection task: given input text, identify whether it contains a euphemism. The input data is a corpus of sentences containing potentially euphemistic terms (PETs) collected from the GloWbE corpus, and are human-annotated as containing either a euphemistic or literal usage of a PET. In this paper, we present the results and analyze the common themes, methods and findings of the participating teams.
Euphemisms have not received much attention in natural language processing, despite being an important element of polite and figurative language. Euphemisms prove to be a difficult topic, not only because they are subject to language change, but also because humans may not agree on what is a euphemism and what is not. Nonetheless, the first step to tackling the issue is to collect and analyze examples of euphemisms. We present a corpus of potentially euphemistic terms (PETs) along with example texts from the GloWbE corpus. Additionally, we present a subcorpus of texts where these PETs are not being used euphemistically, which may be useful for future applications. We also discuss the results of multiple analyses run on the corpus. Firstly, we find that sentiment analysis on the euphemistic texts supports that PETs generally decrease negative and offensive sentiment. Secondly, we observe cases of disagreement in an annotation task, where humans are asked to label PETs as euphemistic or not in a subset of our corpus text examples. We attribute the disagreement to a variety of potential reasons, including if the PET was a commonly accepted term (CAT).
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.
Internet censorship imposes restrictions on what information can be publicized or viewed on the Internet. According to Freedom House’s annual Freedom on the Net report, more than half the world’s Internet users now live in a place where the Internet is censored or restricted. China has built the world’s most extensive and sophisticated online censorship system. In this paper, we describe a new corpus of censored and uncensored social media tweets from a Chinese microblogging website, Sina Weibo, collected by tracking posts that mention ‘sensitive’ topics or authored by ‘sensitive’ users. We use this corpus to build a neural network classifier to predict censorship. Our model performs with a 88.50% accuracy using only linguistic features. We discuss these features in detail and hypothesize that they could potentially be used for censorship circumvention.
This paper investigates censorship from a linguistic perspective. We collect a corpus of censored and uncensored posts on a number of topics, build a classifier that predicts censorship decisions independent of discussion topics. Our investigation reveals that the strongest linguistic indicator of censored content of our corpus is its readability.
Some expressions can be ambiguous between idiomatic and literal interpretations depending on the context they occur in, e.g., ‘sales hit the roof’ vs. ‘hit the roof of the car’. We present a novel method of classifying whether a given instance is literal or idiomatic, focusing on verb-noun constructions. We report state-of-the-art results on this task using an approach based on the hypothesis that the distributions of the contexts of the idiomatic phrases will be different from the contexts of the literal usages. We measure contexts by using projections of the words into vector space. For comparison, we implement Fazly et al. (2009)’s, Sporleder and Li (2009)’s, and Li and Sporleder (2010b)’s methods and apply them to our data. We provide experimental results validating the proposed techniques.
Our paper presents the details of a pilot study in which we tagged portions of the American National Corpus (ANC) for idioms composed of verb-noun constructions, prepositional phrases, and subordinate clauses. The three data sets we analyzed included 1,500-sentence samples from the spoken, the nonfiction, and the fiction portions of the ANC. Our paper provides the details of the tagset we developed, the motivation behind our choices, and the inter-annotator agreement measures we deemed appropriate for this task. In tagging the ANC for idiomatic expressions, our annotators achieved a high level of agreement (> .80) on the tags but a low level of agreement (< .00) on what constituted an idiom. These findings support the claim that identifying idiomatic and metaphorical expressions is a highly difficult and subjective task. In total, 135 idiom types and 154 idiom tokens were identified. Based on the total tokens found for each idiom class, we suggest that future research on idiom detection and idiom annotation include prepositional phrases as this class of idioms occurred frequently in the nonfiction and spoken samples of our corpus
Fusional languages have rich inflection. As a consequence, tagsets capturing their morphological features are necessarily large. A natural way to make a tagset manageable is to use a structured system. In this paper, we present a positional tagset for describing morphological properties of Russian. The tagset was inspired by the Czech positional system (Hajic, 2004). We have used preliminary versions of this tagset in our previous work (e.g., Hana et al. (2004, 2006); Feldman (2006); Feldman and Hana (2010)). Here, we both systematize and extend these preliminary versions (by adding information about animacy, aspect and reflexivity); give a more detailed description of the tagset and provide comparison with the Czech system. Each tag of the tagset consists of 16 positions, each encoding one morphological feature (part-of-speech, detailed part-of-speech, gender, animacy, number, case, possessor's gender and number, person, reflexivity, tense, aspect, degree of comparison, negation, voice, variant). The tagset contains approximately 2,000 tags.
This paper describes an ongoing project in which we are collecting a learner corpus of Arabic, developing a tagset for error annotation and performing Computer-aided Error Analysis (CEA) on the data. We adapted the French Interlanguage Database FRIDA tagset (Granger, 2003a) to the data. We chose FRIDA in order to follow a known standard and to see whether the changes needed to move from a French to an Arabic tagset would give us a measure of the distance between the two languages with respect to learner difficulty. The current collection of texts, which is constantly growing, contains intermediate and advanced-level student writings. We describe the need for such corpora, the learner data we have collected and the tagset we have developed. We also describe the error frequency distribution of both proficiency levels and the ongoing work.
This paper reports the principles behind designing a tagset to cover Russian morphosyntactic phenomena, modifications of the core tagset, and its evaluation. The tagset is based on the MULTEXT-East framework, while the decisions in designing it were aimed at achieving a balance between parameters important for linguists and the possibility to detect and disambiguate them automatically. The final tagset contains about 500 tags and achieves about 95% accuracy on the disambiguated portion of the Russian National Corpus. We have also produced a test set that can be shared with other researchers.
We take a novel approach to rapid, low-cost development of morpho-syntactically annotated resources without using parallel corpora or bilingual lexicons. The overall research question is how to exploit language resources and properties to facilitate and automate the creation of morphologically annotated corpora for new languages. This portability issue is especially relevant to minority languages, for which such resources are likely to remain unavailable in the foreseeable future. We compare the performance of our system on languages that belong to different language families (Romance vs. Slavic), as well as different language pairs within the same language family (Portuguese via Spanish vs. Catalan via Spanish). We show that across language families, the most difficult category is the category of nominals (the noun homonymy is challenging for morphological analysis and the order variation of adjectives within a sentence makes it challenging to create a realiable model), whereas different language families present different challenges with respect to their morpho-syntactic descriptions: for the Slavic languages, case is the most challenging category; for the Romance languages, gender is more challenging than case. In addition, we present an alternative evaluation metric for our system, where we measure how much human labor will be needed to convert the result of our tagging to a high precision annotated resource.