Soroush Vosoughi


2023

pdf bib
Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models
Sean Xie | Soroush Vosoughi | Saeed Hassanpour
Findings of the Association for Computational Linguistics: EMNLP 2023

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after inference time, and have limitations such as their focus on low-level features and lack of explainability at higher-level text units. In this work, we introduce proto-lm, a prototypical network-based white-box framework that allows LLMs to learn immediately interpretable embeddings during the fine-tuning stage while maintaining competitive performance. Our method’s applicability and interpretability are demonstrated through experiments on a wide range of NLP tasks, and our results indicate a new possibility of creating interpretable models without sacrificing performance. This novel approach to interpretability in LLMs can pave the way for more interpretable models without the need to sacrifice performance. We release our code at https://github.com/yx131/proto-lm.

pdf bib
Intersectional Stereotypes in Large Language Models: Dataset and Analysis
Weicheng Ma | Brian Chiang | Tong Wu | Lili Wang | Soroush Vosoughi
Findings of the Association for Computational Linguistics: EMNLP 2023

Despite many stereotypes targeting intersectional demographic groups, prior studies on stereotypes within Large Language Models (LLMs) primarily focus on broader, individual categories. This research bridges this gap by introducing a novel dataset of intersectional stereotypes, curated with the assistance of the ChatGPT model and manually validated. Moreover, this paper offers a comprehensive analysis of intersectional stereotype propagation in three contemporary LLMs by leveraging this dataset. The findings underscore the urgency of focusing on intersectional biases in ongoing efforts to reduce stereotype prevalence in LLMs.

pdf bib
Deciphering Stereotypes in Pre-Trained Language Models
Weicheng Ma | Henry Scheible | Brian Wang | Goutham Veeramachaneni | Pratim Chowdhary | Alan Sun | Andrew Koulogeorge | Lili Wang | Diyi Yang | Soroush Vosoughi
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Warning: This paper contains content that is stereotypical and may be upsetting. This paper addresses the issue of demographic stereotypes present in Transformer-based pre-trained language models (PLMs) and aims to deepen our understanding of how these biases are encoded in these models. To accomplish this, we introduce an easy-to-use framework for examining the stereotype-encoding behavior of PLMs through a combination of model probing and textual analyses. Our findings reveal that a small subset of attention heads within PLMs are primarily responsible for encoding stereotypes and that stereotypes toward specific minority groups can be identified using attention maps on these attention heads. Leveraging these insights, we propose an attention-head pruning method as a viable approach for debiasing PLMs, without compromising their language modeling capabilities or adversely affecting their performance on downstream tasks.

pdf bib
Length Does Matter: Summary Length can Bias Summarization Metrics
Xiaobo Guo | Soroush Vosoughi
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Establishing the characteristics of an effective summary is a complicated and often subjective endeavor. Consequently, the development of metrics for the summarization task has become a dynamic area of research within natural language processing. In this paper, we reveal that existing summarization metrics exhibit a bias toward the length of generated summaries. Our thorough experiments, conducted on a variety of datasets, metrics, and models, substantiate these findings. The results indicate that most metrics tend to favor longer summaries, even after accounting for other factors. To address this issue, we introduce a Bayesian normalization technique that effectively diminishes this bias. We demonstrate that our approach significantly improves the concordance between human annotators and the majority of metrics in terms of summary coherence.

pdf bib
Improving Syntactic Probing Correctness and Robustness with Control Tasks
Weicheng Ma | Brian Wang | Hefan Zhang | Lili Wang | Rolando Coto-Solano | Saeed Hassanpour | Soroush Vosoughi
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Syntactic probing methods have been used to examine whether and how pre-trained language models (PLMs) encode syntactic features. However, the probing methods are usually biased by the PLMs’ memorization of common word co-occurrences, even if they do not form syntactic relations. This paper presents a random-word-substitution and random-label-matching control task to reduce these biases and improve the robustness of syntactic probing methods. Our control tasks are also shown to notably improve the consistency of probing results between different probing methods and make the methods more robust with respect to the text attributes of the probing instances. Our control tasks make syntactic probing methods better at reconstructing syntactic features and more generalizable to unseen text domains. Our experiments show that our proposed control tasks are effective on different PLMs, probing methods, and syntactic features.

2022

pdf bib
EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
Weicheng Ma | Samiha Datta | Lili Wang | Soroush Vosoughi
Findings of the Association for Computational Linguistics: ACL 2022

While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and does not examine cultural differences among speakers of the same language. To address this problem and augment NLP models with cultural background features, we collect, annotate, manually validate, and benchmark EnCBP, a finer-grained news-based cultural background prediction dataset in English. Through language modeling (LM) evaluations and manual analyses, we confirm that there are noticeable differences in linguistic expressions among five English-speaking countries and across four states in the US. Additionally, our evaluations on nine syntactic (CoNLL-2003), semantic (PAWS-Wiki, QNLI, STS-B, and RTE), and psycholinguistic tasks (SST-5, SST-2, Emotion, and Go-Emotions) show that, while introducing cultural background information does not benefit the Go-Emotions task due to text domain conflicts, it noticeably improves deep learning (DL) model performance on other tasks. Our findings strongly support the importance of cultural background modeling to a wide variety of NLP tasks and demonstrate the applicability of EnCBP in culture-related research.

pdf bib
Aligning Generative Language Models with Human Values
Ruibo Liu | Ge Zhang | Xinyu Feng | Soroush Vosoughi
Findings of the Association for Computational Linguistics: NAACL 2022

Although current large-scale generative language models (LMs) can show impressive insights about factual knowledge, they do not exhibit similar success with respect to human values judgements (e.g., whether or not the generations of an LM are moral). Existing methods learn human values either by directly mimicking the behavior of human data, or rigidly constraining the generation space to human-chosen tokens. These methods are inherently limited in that they do not consider the contextual and abstract nature of human values and as a result often fail when dealing with out-of-domain context or sophisticated and abstract human values. This paper proposes SENSEI, a new reinforcement learning based method that can embed human values judgements into each step of language generation. SENSEI deploys an Actor-Critic framework, where the Critic is a reward distributor that simulates the reward assignment procedure of humans, while the Actor guides the generation towards the maximum reward direction. Compared with five existing methods in three human values alignment datasets, SENSEI not only achieves higher alignment performance in terms of both automatic and human evaluations, but also shows improvements on robustness and transfer learning on unseen human values.

pdf bib
Capturing Topic Framing via Masked Language Modeling
Xiaobo Guo | Weicheng Ma | Soroush Vosoughi
Findings of the Association for Computational Linguistics: EMNLP 2022

Differential framing of issues can lead to divergent world views on important issues. This is especially true in domains where the information presented can reach a large audience, such as traditional and social media. Scalable and reliable measurement of such differential framing is an important first step in addressing them. In this work, based on the intuition that framing affects the tone and word choices in written language, we propose a framework for modeling the differential framing of issues through masked token prediction via large-scale fine-tuned language models (LMs). Specifically, we explore three key factors for our framework: 1) prompt generation methods for the masked token prediction; 2) methods for normalizing the output of fine-tuned LMs; 3) robustness to the choice of pre-trained LMs used for fine-tuning. Through experiments on a dataset of articles from traditional media outlets covering five diverse and politically polarized topics, we show that our framework can capture differential framing of these topics with high reliability.

pdf bib
Dartmouth at SemEval-2022 Task 6: Detection of Sarcasm
Rishik Lad | Weicheng Ma | Soroush Vosoughi
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper introduces the result of Team Dartmouth’s experiments on each of the five subtasks for the detection of sarcasm in English and Arabic tweets. This detection was framed as a classification problem, and our contributions are threefold: we developed an English binary classifier system with RoBERTa, an Arabic binary classifier with XLM-RoBERTa, and an English multilabel classifier with BERT. Preprocessing steps are taken with labeled input data prior to tokenization, such as extracting and appending verbs/adjectives or representative/significant keywords to the end of an input tweet to help the models better understand and generalize sarcasm detection. We also discuss the results of simple data augmentation techniques to improve the quality of the given training dataset as well as an alternative approach to the question of multilabel sequence classification. Ultimately, our systems place us in the top 14 participants for each of the five subtasks.

pdf bib
DartmouthCS at SemEval-2022 Task 8: Predicting Multilingual News Article Similarity with Meta-Information and Translation
Joseph Hajjar | Weicheng Ma | Soroush Vosoughi
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

This paper presents our approach for tackling SemEval-2022 Task 8: Multilingual News Article Similarity. Our experiments show that even by using multi-lingual pre-trained language models (LMs), translating the text into the same language yields the best evaluation performance. We also find that stylometric features of the text and meta-information of the news articles can be predicted based on the text with low error rates, and these predictions could be used to improve the predictions of the overall similarity scores. These findings suggest substantial correlations between authorship information and topical similarity estimation, which sheds light on future stylometric and topic modeling research.

pdf bib
TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations
Prashanth Vijayaraghavan | Soroush Vosoughi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recently, several studies on propaganda detection have involved document and fragment-level analyses of news articles. However, there are significant data and modeling challenges dealing with fine-grained detection of propaganda on social media. In this work, we present TWEETSPIN, a dataset containing tweets that are weakly annotated with different fine-grained propaganda techniques, and propose a neural approach to detect and categorize propaganda tweets across those fine-grained categories. These categories include specific rhetorical and psychological techniques, ranging from leveraging emotions to using logical fallacies. Our model relies on multi-view representations of the input tweet data to (a) extract different aspects of the input text including the context, entities, their relationships, and external knowledge; (b) model their mutual interplay; and (c) effectively speed up the learning process by requiring fewer training examples. Our method allows for representation enrichment leading to better detection and categorization of propaganda on social media. We verify the effectiveness of our proposed method on TWEETSPIN and further probe how the implicit relations between the views impact the performance. Our experiments show that our model is able to outperform several benchmark methods and transfer the knowledge to relatively low-resource news domains.

pdf bib
Embedding Hallucination for Few-shot Language Fine-tuning
Yiren Jian | Chongyang Gao | Soroush Vosoughi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Few-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language model can cause severe over-fitting. In this paper, we propose an Embedding Hallucination (EmbedHalluc) method, which generates auxiliary embedding-label pairs to expand the fine-tuning dataset. The hallucinator is trained by playing an adversarial game with the discriminator, such that the hallucinated embedding is indiscriminative to the real ones in the fine-tuning dataset. By training with the extended dataset, the language learner effectively learns from the diverse hallucinated embeddings to overcome the over-fitting issue. Experiments demonstrate that our proposed method is effective in a wide range of language tasks, outperforming current fine-tuning methods. Further, we show that EmbedHalluc outperforms other methods that address this over-fitting problem, such as common data augmentation, semi-supervised pseudo-labeling, and regularization.

pdf bib
Contrastive Learning for Prompt-based Few-shot Language Learners
Yiren Jian | Chongyang Gao | Soroush Vosoughi
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

The impressive performance of GPT-3 using natural language prompts and in-context learning has inspired work on better fine-tuning of moderately-sized models under this paradigm. Following this line of work, we present a contrastive learning framework that clusters inputs from the same class for better generality of models trained with only limited examples. Specifically, we propose a supervised contrastive framework that clusters inputs from the same class under different augmented “views” and repel the ones from different classes. We create different “views” of an example by appending it with different language prompts and contextual demonstrations. Combining a contrastive loss with the standard masked language modeling (MLM) loss in prompt-based few-shot learners, the experimental results show that our method can improve over the state-of-the-art methods in a diverse set of 15 language tasks. Our framework makes minimal assumptions on the task or the base model, and can be applied to many recent methods with little modification.

2021

pdf bib
Text Augmentation in a Multi-Task View
Jason Wei | Chengyu Huang | Shiqi Xu | Soroush Vosoughi
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Traditional data augmentation aims to increase the coverage of the input distribution by generating augmented examples that strongly resemble original samples in an online fashion where augmented examples dominate training. In this paper, we propose an alternative perspective—a multi-task view (MTV) of data augmentation—in which the primary task trains on original examples and the auxiliary task trains on augmented examples. In MTV data augmentation, both original and augmented samples are weighted substantively during training, relaxing the constraint that augmented examples must resemble original data and thereby allowing us to apply stronger augmentation functions. In empirical experiments using four common data augmentation techniques on three benchmark text classification datasets, we find that using the MTV leads to higher and more robust performance than traditional augmentation.

pdf bib
A Survey of Data Augmentation Approaches for NLP
Steven Y. Feng | Varun Gangal | Jason Wei | Sarath Chandar | Soroush Vosoughi | Teruko Mitamura | Eduard Hovy
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Modulating Language Models with Emotions
Ruibo Liu | Jason Wei | Chenyan Jia | Soroush Vosoughi
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks
Weicheng Ma | Renze Lou | Kai Zhang | Lili Wang | Soroush Vosoughi
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

A key problem in multi-task learning (MTL) research is how to select high-quality auxiliary tasks automatically. This paper presents GradTS, an automatic auxiliary task selection method based on gradient calculation in Transformer-based models. Compared to AUTOSEM, a strong baseline method, GradTS improves the performance of MT-DNN with a bert-base-cased backend model, from 0.33% to 17.93% on 8 natural language understanding (NLU) tasks in the GLUE benchmarks. GradTS is also time-saving since (1) its gradient calculations are based on single-task experiments and (2) the gradients are re-used without additional experiments when the candidate task set changes. On the 8 GLUE classification tasks, for example, GradTS costs on average 21.32% less time than AUTOSEM with comparable GPU consumption. Further, we show the robustness of GradTS across various task settings and model selections, e.g. mixed objectives among candidate tasks. The efficiency and efficacy of GradTS in these case studies illustrate its general applicability in MTL research without requiring manual task filtering or costly parameter tuning.

pdf bib
BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
Aadil Islam | Weicheng Ma | Soroush Vosoughi
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper describes a system submitted by team BigGreen to LCP 2021 for predicting the lexical complexity of English words in a given context. We assemble a feature engineering-based model with a deep neural network model founded on BERT. While BERT itself performs competitively, our feature engineering-based model helps in extreme cases, eg. separating instances of easy and neutral difficulty. Our handcrafted features comprise a breadth of lexical, semantic, syntactic, and novel phonological measures. Visualizations of BERT attention maps offer insight into potential features that Transformers models may learn when fine-tuned for lexical complexity prediction. Our ensembled predictions score reasonably well for the single word subtask, and we demonstrate how they can be harnessed to perform well on the multi word expression subtask too.

pdf bib
Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
Yakoob Khan | Weicheng Ma | Soroush Vosoughi
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

This paper describes our approach to the Toxic Spans Detection problem (SemEval-2021 Task 5). We propose BERToxic, a system that fine-tunes a pre-trained BERT model to locate toxic text spans in a given text and utilizes additional post-processing steps to refine the boundaries. The post-processing steps involve (1) labeling character offsets between consecutive toxic tokens as toxic and (2) assigning a toxic label to words that have at least one token labeled as toxic. Through experiments, we show that these two post-processing steps improve the performance of our model by 4.16% on the test set. We also studied the effects of data augmentation and ensemble modeling strategies on our system. Our system significantly outperformed the provided baseline and achieved an F1-score of 0.683, placing Lone Pine in the 17th place out of 91 teams in the competition. Our code is made available at https://github.com/Yakoob-Khan/Toxic-Spans-Detection

pdf bib
Linguistic Complexity Loss in Text-Based Therapy
Jason Wei | Kelly Finn | Emma Templeton | Thalia Wheatley | Soroush Vosoughi
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

The complexity loss paradox, which posits that individuals suffering from disease exhibit surprisingly predictable behavioral dynamics, has been observed in a variety of both human and animal physiological systems. The recent advent of online text-based therapy presents a new opportunity to analyze the complexity loss paradox in a novel operationalization: linguistic complexity loss in text-based therapy conversations. In this paper, we analyze linguistic complexity correlates of mental health in the online therapy messages sent between therapists and 7,170 clients who provided 30,437 corresponding survey responses on their anxiety. We found that when clients reported more anxiety, they showed reduced lexical diversity as estimated by the moving average type-token ratio. Therapists, on the other hand, used language of higher reading difficulty, syntactic complexity, and age of acquisition when clients were more anxious. Finally, we found that clients, and to an even greater extent, therapists, exhibited consistent levels of many linguistic complexity measures. These results demonstrate how linguistic analysis of text-based communication can be leveraged as a marker for anxiety, an exciting prospect in a time of both increased online communication and increased mental health issues.

pdf bib
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Jason Wei | Chengyu Huang | Soroush Vosoughi | Yu Cheng | Shiqi Xu
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation—a technique particularly suitable for training with limited data—for this few-shot, highly-multiclass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can improve the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curriculum learning by first training on only original examples and then introducing augmented data as training progresses. We explore a two-stage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, improves performance, and remains robust to high amounts of noising from augmentation.

pdf bib
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks
Weicheng Ma | Kai Zhang | Renze Lou | Lili Wang | Soroush Vosoughi
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each mono-lingual Natural Language Processing (NLP) task and pruning the remaining heads leads to comparable or improved performance of the model. However, the impact of pruning attention heads is not yet clear in cross-lingual and multi-lingual tasks. Through extensive experiments, we show that (1) pruning a number of attention heads in a multi-lingual Transformer-based model has, in general, positive effects on its performance in cross-lingual and multi-lingual tasks and (2) the attention heads to be pruned can be ranked using gradients and identified with a few trial experiments. Our experiments focus on sequence labeling tasks, with potential applicability on other cross-lingual and multi-lingual tasks. For comprehensiveness, we examine two pre-trained multi-lingual models, namely multi-lingual BERT (mBERT) and XLM-R, on three tasks across 9 languages each. We also discuss the validity of our findings and their extensibility to truly resource-scarce languages and other task settings.

pdf bib
Language Model Augmented Relevance Score
Ruibo Liu | Jason Wei | Soroush Vosoughi
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Although automated metrics are commonly used to evaluate NLG systems, they often correlate poorly with human judgements. Newer metrics such as BERTScore have addressed many weaknesses in prior metrics such as BLEU and ROUGE, which rely on n-gram matching. These newer methods, however, are still limited in that they do not consider the generation context, so they cannot properly reward generated text that is correct but deviates from the given reference. In this paper, we propose Language Model Augmented Relevance Score (MARS), a new context-aware metric for NLG evaluation. MARS leverages off-the-shelf language models, guided by reinforcement learning, to create augmented references that consider both the generation context and available human references, which are then used as additional references to score generated text. Compared with seven existing metrics in three common NLG tasks, MARS not only achieves higher correlation with human reference judgements, but also differentiates well-formed candidates from adversarial samples to a larger degree.

pdf bib
Improvements and Extensions on Metaphor Detection
Weicheng Ma | Ruibo Liu | Lili Wang | Soroush Vosoughi
Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language

Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural language understanding (NLU) research. In this paper, we introduce a pre-trained Transformer-based model into MD. Our model outperforms the previous state-of-the-art models by large margins in our evaluations, with relative improvements on the F-1 score from 5.33% to 28.39%. Second, we extend MD to a classification task about the metaphoricity of an entire piece of text to make MD applicable in more general NLU scenes. Finally, we clean up the improper or outdated annotations in one of the MD benchmark datasets and re-benchmark it with our Transformer-based model. This approach could be applied to other existing MD datasets as well, since the metaphoricity annotations in these benchmark datasets may be outdated. Future research efforts are also necessary to build an up-to-date and well-annotated dataset consisting of longer and more complex texts.

2020

pdf bib
Multi-resolution Annotations for Emoji Prediction
Weicheng Ma | Ruibo Liu | Lili Wang | Soroush Vosoughi
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Emojis are able to express various linguistic components, including emotions, sentiments, events, etc. Predicting the proper emojis associated with text provides a way to summarize the text accurately, and it has been proven to be a good auxiliary task to many Natural Language Understanding (NLU) tasks. Labels in existing emoji prediction datasets are all passage-based and are usually under the multi-class classification setting. However, in many cases, one single emoji cannot fully cover the theme of a piece of text. It is thus useful to infer the part of text related to each emoji. The lack of multi-label and aspect-level emoji prediction datasets is one of the bottlenecks for this task. This paper annotates an emoji prediction dataset with passage-level multi-class/multi-label, and aspect-level multi-class annotations. We also present a novel annotation method with which we generate the aspect-level annotations. The annotations are generated heuristically, taking advantage of the self-attention mechanism in Transformer networks. We validate the annotations both automatically and manually to ensure their quality. We also benchmark the dataset with a pre-trained BERT model.

pdf bib
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Ruibo Liu | Guangxuan Xu | Chenyan Jia | Weicheng Ma | Lili Wang | Soroush Vosoughi
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Data augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text augmentation framework, Data Boost, which augments data through reinforcement learning guided conditional generation. We evaluate Data Boost on three diverse text classification tasks under five different classifier architectures. The result shows that Data Boost can boost the performance of classifiers especially in low-resource data scenarios. For instance, Data Boost improves F1 for the three tasks by 8.7% on average when given only 10% of the whole data for training. We also compare Data Boost with six prior text augmentation methods. Through human evaluations (N=178), we confirm that Data Boost augmentation has comparable quality as the original data with respect to readability and class consistency.

pdf bib
What Are People Asking About COVID-19? A Question Classification Dataset
Jerry Wei | Chengyu Huang | Soroush Vosoughi | Jason Wei
Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020

We present COVID-Q, a set of 1,690 questions about COVID-19 from 13 sources, which we annotate into 15 question categories and 207 question clusters. The most common questions in our dataset asked about transmission, prevention, and societal effects of COVID, and we found that many questions that appeared in multiple sources were not answered by any FAQ websites of reputable organizations such as the CDC and FDA. We post our dataset publicly at https://github.com/JerryWei03/COVID-Q. For classifying questions into 15 categories, a BERT baseline scored 58.1% accuracy when trained on 20 examples per category, and for a question clustering task, a BERT + triplet loss baseline achieved 49.5% accuracy. We hope COVID-Q can help either for direct use in developing applied systems or as a domain-specific resource for model evaluation.

pdf bib
An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
Lili Wang | Chongyang Gao | Jason Wei | Weicheng Ma | Ruibo Liu | Soroush Vosoughi
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

The field of NLP has seen unprecedented achievements in recent years. Most notably, with the advent of large-scale pre-trained Transformer-based language models, such as BERT, there has been a noticeable improvement in text representation. It is, however, unclear whether these improvements translate to noisy user-generated text, such as tweets. In this paper, we present an experimental survey of a wide range of well-known text representation techniques for the task of text clustering on noisy Twitter data. Our results indicate that the more advanced models do not necessarily work best on tweets and that more exploration in this area is needed.

pdf bib
Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification
Chris Miller | Soroush Vosoughi
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

Relation and event extraction is an important task in natural language processing. We introduce a system which uses contextualized knowledge graph completion to classify relations and events between known entities in a noisy text environment. We report results which show that our system is able to effectively extract relations and events from a dataset of wet lab protocols.

pdf bib
Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
Dylan Whang | Soroush Vosoughi
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)

We describe the systems developed for the WNUT-2020 shared task 2, identification of informative COVID-19 English Tweets. BERT is a highly performant model for Natural Language Processing tasks. We increased BERT’s performance in this classification task by fine-tuning BERT and concatenating its embeddings with Tweet-specific features and training a Support Vector Machine (SVM) for classification (henceforth called BERT+). We compared its performance to a suite of machine learning models. We used a Twitter specific data cleaning pipeline and word-level TF-IDF to extract features for the non-BERT models. BERT+ was the top performing model with an F1-score of 0.8713.

2017

pdf bib
Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning
Prashanth Vijayaraghavan | Soroush Vosoughi | Deb Roy
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Twitter should be an ideal place to get a fresh read on how different issues are playing with the public, one that’s potentially more reflective of democracy in this new media age than traditional polls. Pollsters typically ask people a fixed set of questions, while in social media people use their own voices to speak about whatever is on their minds. However, the demographic distribution of users on Twitter is not representative of the general population. In this paper, we present a demographic classifier for gender, age, political orientation and location on Twitter. We collected and curated a robust Twitter demographic dataset for this task. Our classifier uses a deep multi-modal multi-task learning architecture to reach a state-of-the-art performance, achieving an F1-score of 0.89, 0.82, 0.86, and 0.68 for gender, age, political orientation, and location respectively.

2016

pdf bib
DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
Prashanth Vijayaraghavan | Ivan Sysoev | Soroush Vosoughi | Deb Roy
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

2015

pdf bib
Enhanced Twitter Sentiment Classification Using Contextual Information
Soroush Vosoughi | Helen Zhou | Deb Roy
Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis