Tanya Goyal


2022

pdf bib
Training Dynamics for Text Summarization Models
Tanya Goyal | Jiacheng Xu | Junyi Jessy Li | Greg Durrett
Findings of the Association for Computational Linguistics: ACL 2022

Pre-trained language models (e.g. BART) have shown impressive results when fine-tuned on large summarization datasets. However, little is understood about this fine-tuning process, including what knowledge is retained from pre-training time or how content selection and generation strategies are learnt across iterations. In this work, we analyze the training dynamics for generation models, focusing on summarization. Across different datasets (CNN/DM, XSum, MediaSum) and summary properties, such as abstractiveness and hallucination, we study what the model learns at different stages of its fine-tuning process. We find that a propensity to copy the input is learned early in the training process consistently across all datasets studied. On the other hand, factual errors, such as hallucination of unsupported facts, are learnt in the later stages, though this behavior is more varied across domains. Based on these observations, we explore complementary approaches for modifying training: first, disregarding high-loss tokens that are challenging to learn and second, disregarding low-loss tokens that are learnt very quickly in the latter stages of the training process. We show that these simple training modifications allow us to configure our model to achieve different goals, such as improving factuality or improving abstractiveness.

2021

pdf bib
Contemporary NLP Modeling in Six Comprehensive Programming Assignments
Greg Durrett | Jifan Chen | Shrey Desai | Tanya Goyal | Lucas Kabela | Yasumasa Onoe | Jiacheng Xu
Proceedings of the Fifth Workshop on Teaching NLP

We present a series of programming assignments, adaptable to a range of experience levels from advanced undergraduate to PhD, to teach students design and implementation of modern NLP systems. These assignments build from the ground up and emphasize full-stack understanding of machine learning models: initially, students implement inference and gradient computation by hand, then use PyTorch to build nearly state-of-the-art neural networks using current best practices. Topics are chosen to cover a wide range of modeling and inference techniques that one might encounter, ranging from linear models suitable for industry applications to state-of-the-art deep learning models used in NLP research. The assignments are customizable, with constrained options to guide less experienced students or open-ended options giving advanced students freedom to explore. All of them can be deployed in a fully autogradable fashion, and have collectively been tested on over 300 students across several semesters.

pdf bib
Annotating and Modeling Fine-grained Factuality in Summarization
Tanya Goyal | Greg Durrett
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statistical models for assessing factuality have been explored, there is no clear picture of what errors are most important to target or where current techniques are succeeding and failing. We explore both synthetic and human-labeled data sources for training models to identify factual errors in summarization, and study factuality at the word-, dependency-, and sentence-level. Our observations are threefold. First, exhibited factual errors differ significantly across datasets, and commonly-used training sets of simple synthetic errors do not reflect errors made on abstractive datasets like XSum. Second, human-labeled data with fine-grained annotations provides a more effective training signal than sentence-level annotations or synthetic data. Finally, we show that our best factuality detection model enables training of more factual XSum summarization models by allowing us to identify non-factual tokens in the training data.

2020

pdf bib
Evaluating Factuality in Generation with Dependency-level Entailment
Tanya Goyal | Greg Durrett
Findings of the Association for Computational Linguistics: EMNLP 2020

Despite significant progress in text generation models, a serious limitation is their tendency to produce text that is factually inconsistent with information in the input. Recent work has studied whether textual entailment systems can be used to identify factual errors; however, these sentence-level entailment models are trained to solve a different problem than generation filtering and they do not localize which part of a generation is non-factual. In this paper, we propose a new formulation of entailment that decomposes it at the level of dependency arcs. Rather than focusing on aggregate decisions, we instead ask whether the semantic relationship manifested by individual dependency arcs in the generated output is supported by the input. Human judgments on this task are difficult to obtain; we therefore propose a method to automatically create data based on existing entailment or paraphrase corpora. Experiments show that our dependency arc entailment model trained on this data can identify factual inconsistencies in paraphrasing and summarization better than sentence-level methods or those based on question generation, while additionally localizing the erroneous parts of the generation.

pdf bib
Neural Syntactic Preordering for Controlled Paraphrase Generation
Tanya Goyal | Greg Durrett
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past approaches struggle to cover this space of paraphrase possibilities in an interpretable manner. Our work, inspired by pre-ordering literature in machine translation, uses syntactic transformations to softly “reorder” the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. This model operates over a partially lexical, partially syntactic view of the sentence and can reorder big chunks. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order. Our evaluation, both automatic and human, shows that the proposed system retains the quality of the baseline approaches while giving a substantial increase in the diversity of the generated paraphrases.

2019

pdf bib
Embedding Time Expressions for Deep Temporal Ordering Models
Tanya Goyal | Greg Durrett
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Data-driven models have demonstrated state-of-the-art performance in inferring the temporal ordering of events in text. However, these models often overlook explicit temporal signals, such as dates and time windows. Rule-based methods can be used to identify the temporal links between these time expressions (timexes), but they fail to capture timexes’ interactions with events and are hard to integrate with the distributed representations of neural net models. In this paper, we introduce a framework to infuse temporal awareness into such models by learning a pre-trained model to embed timexes. We generate synthetic data consisting of pairs of timexes, then train a character LSTM to learn embeddings and classify the timexes’ temporal relation. We evaluate the utility of these embeddings in the context of a strong neural model for event temporal ordering, and show a small increase in performance on the MATRES dataset and more substantial gains on an automatically collected dataset with more frequent event-timex interactions.

2018

pdf bib
Frustrated, Polite, or Formal: Quantifying Feelings and Tone in Email
Niyati Chhaya | Kushal Chawla | Tanya Goyal | Projjal Chanda | Jaya Singh
Proceedings of the Second Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media

Email conversations are the primary mode of communication in enterprises. The email content expresses an individual’s needs, requirements and intentions. Affective information in the email text can be used to get an insight into the sender’s mood or emotion. We present a novel approach to model human frustration in text. We identify linguistic features that influence human perception of frustration and model it as a supervised learning task. The paper provides a detailed comparison across traditional regression and word distribution-based models. We report a mean-squared error (MSE) of 0.018 against human-annotated frustration for the best performing model. The approach establishes the importance of affect features in frustration prediction for email data. We further evaluate the efficacy of the proposed feature set and model in predicting other tone or affects in text, namely formality and politeness; results demonstrate a comparable performance against the state-of-the-art baselines.

2017

pdf bib
An Empirical Analysis of Edit Importance between Document Versions
Tanya Goyal | Sachin Kelkar | Manas Agarwal | Jeenu Grover
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In this paper, we present a novel approach to infer significance of various textual edits to documents. An author may make several edits to a document; each edit varies in its impact to the content of the document. While some edits are surface changes and introduce negligible change, other edits may change the content/tone of the document significantly. In this paper, we perform an analysis on the human perceptions of edit importance while reviewing documents from one version to the next. We identify linguistic features that influence edit importance and model it in a regression based setting. We show that the predicted importance by our approach is highly correlated with the human perceived importance, established by a Mechanical Turk study.