Language models (LMs) are pretrained on diverse data sources—news, discussion forums, books, online encyclopedias. A significant portion of this data includes facts and opinions which, on one hand, celebrate democracy and diversity of ideas, and on the other hand are inherently socially biased. Our work develops new methods to (1) measure media biases in LMs trained on such corpora, along social and economic axes, and (2) measure the fairness of downstream NLP models trained on top of politically biased LMs. We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks. Our findings reveal that pretrained LMs do have political leanings which reinforce the polarization present in pretraining corpora, propagating social biases into hate speech predictions and media biases into misinformation detectors. We discuss the implications of our findings for NLP research and propose future directions to mitigate unfairness.

NLP research on public opinion manipulation campaigns has primarily focused on detecting overt strategies such as fake news and disinformation. However, information manipulation in the ongoing Russia-Ukraine war exemplifies how governments and media also employ more nuanced strategies. We release a new dataset, VoynaSlov, containing 38M+ posts from Russian media outlets on Twitter and VKontakte, as well as public activity and responses, immediately preceding and during the 2022 Russia-Ukraine war. We apply standard and recently-developed NLP models on VoynaSlov to examine agenda setting, framing, and priming, several strategies underlying information manipulation, and reveal variation across media outlet control, social media platform, and time. Our examination of these media effects and extensive discussion of current approaches’ limitations encourage further development of NLP models for understanding information manipulation in emerging crises, as well as other real-world and interdisciplinary tasks.

Online platforms and communities establish their own norms that govern what behavior is acceptable within the community. Substantial effort in NLP has focused on identifying unacceptable behaviors and, recently, on forecasting them before they occur. However, these efforts have largely focused on toxicity as the sole form of community norm violation. Such focus has overlooked the much larger set of rules that moderators enforce. Here, we introduce a new dataset focusing on a more complete spectrum of community norms and their violations in the local conversational and global community contexts. We introduce a series of models that use this data to develop context- and community-sensitive norm violation detection, showing that these changes give high performance.

Much work in cross-lingual transfer learning explored how to select better transfer languages for multilingual tasks, primarily focusing on typological and genealogical similarities between languages. We hypothesize that these measures of linguistic proximity are not enough when working with pragmatically-motivated tasks, such as sentiment analysis. As an alternative, we introduce three linguistic features that capture cross-cultural similarities that manifest in linguistic patterns and quantify distinct aspects of language pragmatics: language context-level, figurative language, and the lexification of emotion concepts. Our analyses show that the proposed pragmatic features do capture cross-cultural similarities and align well with existing work in sociolinguistics and linguistic anthropology. We further corroborate the effectiveness of pragmatically-driven transfer in the downstream task of choosing transfer languages for cross-lingual sentiment analysis.

This paper describes our approach to the task of identifying offensive languages in a multilingual setting. We investigate two data augmentation strategies: using additional semi-supervised labels with different thresholds and cross-lingual transfer with data selection. Leveraging the semi-supervised dataset resulted in performance improvements compared to the baseline trained solely with the manually-annotated dataset. We propose a new metric, Translation Embedding Distance, to measure the transferability of instances for cross-lingual data selection. We also introduce various preprocessing steps tailored for social media text along with methods to fine-tune the pre-trained multilingual BERT (mBERT) for offensive language identification. Our multilingual systems achieved competitive results in Greek, Danish, and Turkish at OffensEval 2020.

Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations. To improve the translation of phrases, phrase-based NMT systems have been proposed; these typically combine word-based NMT with external phrase dictionaries or with phrase tables from phrase-based statistical MT systems. These solutions introduce a significant overhead of additional resources and computational costs. In this paper, we introduce a phrase-based NMT model built upon continuous-output NMT, in which the decoder generates embeddings of words or phrases. The model uses a fertility module, which guides the decoder to generate embeddings of sequences of varying lengths. We show that our model learns to translate phrases better, performing on par with state of the art phrase-based NMT. Since our model does not resort to softmax computation over a huge vocabulary of phrases, its training time is about 112x faster than the baseline.