278 citations · 576 across the 32 of their papers we have counts for
47 papers
Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching
Alissa Ostapenko, Shuly Wintner, Melinda Fricke +1
Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not…
Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
Monisha Jegadeesan, Sachin Kumar, John Wieting +1
We present a novel technique for zero-shot paraphrase generation. The key contribution is an end-to-end multilingual paraphrasing model that is trained using translated parallel co…
Detecting Community Sensitive Norm Violations in Online Conversations
Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan +4
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 unacce…
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Xinyi Wang, Yulia Tsvetkov, Sebastian Ruder +1
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate…
A Survey of Race, Racism, and Anti-Racism in NLP
Anjalie Field, Su Lin Blodgett, Zeerak Waseem +1
Despite inextricable ties between race and language, little work has considered race in NLP research and development. In this work, we survey 79 papers from the ACL anthology that…
Machine Translation into Low-resource Language Varieties
Sachin Kumar, Antonios Anastasopoulos, Shuly Wintner +1
State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional variet…
An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translation
Lidia Kidane, Sachin Kumar, Yulia Tsvetkov
It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, often requiring large amounts of auxiliary data to achieve comp…
Evaluating the Morphosyntactic Well-formedness of Generated Texts
Adithya Pratapa, Antonios Anastasopoulos, Shruti Rijhwani +4
Text generation systems are ubiquitous in natural language processing applications. However, evaluation of these systems remains a challenge, especially in multilingual settings. I…
SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers
Dheeraj Rajagopal, Vidhisha Balachandran, Eduard Hovy +1
We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers…
Controlled Analyses of Social Biases in Wikipedia Bios
Anjalie Field, Chan Young Park, Kevin Z. Lin +1
Social biases on Wikipedia, a widely-read global platform, could greatly influence public opinion. While prior research has examined man/woman gender bias in biography articles, po…
Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
Zirui Wang, Yulia Tsvetkov, Orhan Firat +1
Massively multilingual models subsuming tens or even hundreds of languages pose great challenges to multi-task optimization. While it is a common practice to apply a language-agnos…
Fortifying Toxic Speech Detectors Against Veiled Toxicity
Xiaochuang Han, Yulia Tsvetkov
Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestatio…
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
Zirui Wang, Zachary C. Lipton, Yulia Tsvetkov
Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits a…
Automatic Extraction of Rules Governing Morphological Agreement
Aditi Chaudhary, Antonios Anastasopoulos, Adithya Pratapa +4
Creating a descriptive grammar of a language is an indispensable step for language documentation and preservation. However, at the same time it is a tedious, time-consuming task. I…
Multilingual Contextual Affective Analysis of LGBT People Portrayals in Wikipedia
Chan Young Park, Xinru Yan, Anjalie Field +1
Specific lexical choices in narrative text reflect both the writer's attitudes towards people in the narrative and influence the audience's reactions. Prior work has examined descr…
LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification
Sopan Khosla, Rishabh Joshi, Ritam Dutt +2
In this paper we describe our submission for the task of Propaganda Span Identification in news articles. We introduce a BERT-BiLSTM based span-level propaganda classification mode…
Controlling Dialogue Generation with Semantic Exemplars
Prakhar Gupta, Jeffrey P. Bigham, Yulia Tsvetkov +1
Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A…
A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards
Zi-Yi Dou, Sachin Kumar, Yulia Tsvetkov
Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, prima…
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks
Jimin Sun, Hwijeen Ahn, Chan Young Park +2
Much work in cross-lingual transfer learning explored how to select better transfer languages for multilingual tasks, primarily focusing on typological and genealogical similaritie…
Demoting Racial Bias in Hate Speech Detection
Mengzhou Xia, Anjalie Field, Yulia Tsvetkov
In current hate speech datasets, there exists a high correlation between annotators' perceptions of toxicity and signals of African American English (AAE). This bias in annotated t…
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions
Xiaochuang Han, Byron C. Wallace, Yulia Tsvetkov
Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or th…
A Computational Analysis of Polarization on Indian and Pakistani Social Media
Aman Tyagi, Anjalie Field, Priyank Lathwal +2
Between February 14, 2019 and March 4, 2019, a terrorist attack in Pulwama, Kashmir followed by retaliatory airstrikes led to rising tensions between India and Pakistan, two nuclea…
Unsupervised Discovery of Implicit Gender Bias
Anjalie Field, Yulia Tsvetkov
Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach…
Balancing Training for Multilingual Neural Machine Translation
Xinyi Wang, Yulia Tsvetkov, Graham Neubig
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more…