Searcharxiv⌕ Search

arXiv subjects

Junyi Jessy Li

Publications and source records attributed to Junyi Jessy Li.

At least 91 records · Page 5Linked to original sources

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks

Developing methods to adversarially challenge NLP systems is a promising avenue for improving both model performance and interpretability. Here, we describe the approach of the team "longhorns" on Task 1 of the The First Workshop on Dynamic Adversarial Data Collection (DADC), which asked teams to manually fool a model on an Extractive Question Answering task. Our team finished first, with a model error rate of 62%. We advocate for a systematic, linguistically informed approach to formulating adversarial questions, and we describe the results of our pilot experiments, as well as our official submission.

cs.CL↗

ProtoTEx: Explaining Model Decisions with Prototype Tensors

We present ProtoTEx, a novel white-box NLP classification architecture based on prototype networks. ProtoTEx faithfully explains model decisions based on prototype tensors that encode latent clusters of training examples. At inference time, classification decisions are based on the distances between the input text and the prototype tensors, explained via the training examples most similar to the most influential prototypes. We also describe a novel interleaved training algorithm that effectively handles classes characterized by the absence of indicative features. On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERT-large with the added benefit of providing faithful explanations. A user study also shows that prototype-based explanations help non-experts to better recognize propaganda in online news.

cs.CL↗

Political Ideology and Polarization of Policy Positions: A Multi-dimensional Approach

Analyzing ideology and polarization is of critical importance in advancing our grasp of modern politics. Recent research has made great strides towards understanding the ideological bias (i.e., stance) of news media along the left-right spectrum. In this work, we instead take a novel and more nuanced approach for the study of ideology based on its left or right positions on the issue being discussed. Aligned with the theoretical accounts in political science, we treat ideology as a multi-dimensional construct, and introduce the first diachronic dataset of news articles whose ideological positions are annotated by trained political scientists and linguists at the paragraph level. We showcase that, by controlling for the author's stance, our method allows for the quantitative and temporal measurement and analysis of polarization as a multidimensional ideological distance. We further present baseline models for ideology prediction, outlining a challenging task distinct from stance detection.

cs.CL↗

Evaluating Factuality in Text Simplification

Automated simplification models aim to make input texts more readable. Such methods have the potential to make complex information accessible to a wider audience, e.g., providing access to recent medical literature which might otherwise be impenetrable for a lay reader. However, such models risk introducing errors into automatically simplified texts, for instance by inserting statements unsupported by the corresponding original text, or by omitting key information. Providing more readable but inaccurate versions of texts may in many cases be worse than providing no such access at all. The problem of factual accuracy (and the lack thereof) has received heightened attention in the context of summarization models, but the factuality of automatically simplified texts has not been investigated. We introduce a taxonomy of errors that we use to analyze both references drawn from standard simplification datasets and state-of-the-art model outputs. We find that errors often appear in both that are not captured by existing evaluation metrics, motivating a need for research into ensuring the factual accuracy of automated simplification models.

cs.CL↗

Impact of Evaluation Methodologies on Code Summarization

There has been a growing interest in developing machine learning (ML) models for code summarization tasks, e.g., comment generation and method naming. Despite substantial increase in the effectiveness of ML models, the evaluation methodologies, i.e., the way people split datasets into training, validation, and test sets, were not well studied. Specifically, no prior work on code summarization considered the timestamps of code and comments during evaluation. This may lead to evaluations that are inconsistent with the intended use cases. In this paper, we introduce the time-segmented evaluation methodology, which is novel to the code summarization research community, and compare it with the mixed-project and cross-project methodologies that have been commonly used. Each methodology can be mapped to some use cases, and the time-segmented methodology should be adopted in the evaluation of ML models for code summarization. To assess the impact of methodologies, we collect a dataset of (code, comment) pairs with timestamps to train and evaluate several recent ML models for code summarization. Our experiments show that different methodologies lead to conflicting evaluation results. We invite the community to expand the set of methodologies used in evaluations.

cs.SE↗

Learning to Describe Solutions for Bug Reports Based on Developer Discussions

When a software bug is reported, developers engage in a discussion to collaboratively resolve it. While the solution is likely formulated within the discussion, it is often buried in a large amount of text, making it difficult to comprehend and delaying its implementation. To expedite bug resolution, we propose generating a concise natural language description of the solution by synthesizing relevant content within the discussion, which encompasses both natural language and source code. We build a corpus for this task using a novel technique for obtaining noisy supervision from repository changes linked to bug reports, with which we establish benchmarks. We also design two systems for generating a description during an ongoing discussion by classifying when sufficient context for performing the task emerges in real-time. With automated and human evaluation, we find this task to form an ideal testbed for complex reasoning in long, bimodal dialogue context.

cs.CL↗

How Do We Answer Complex Questions: Discourse Structure of Long-form Answers

Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions. To better understand this complex and understudied task, we study the functional structure of long-form answers collected from three datasets, ELI5, WebGPT and Natural Questions. Our main goal is to understand how humans organize information to craft complex answers. We develop an ontology of six sentence-level functional roles for long-form answers, and annotate 3.9k sentences in 640 answer paragraphs. Different answer collection methods manifest in different discourse structures. We further analyze model-generated answers -- finding that annotators agree less with each other when annotating model-generated answers compared to annotating human-written answers. Our annotated data enables training a strong classifier that can be used for automatic analysis. We hope our work can inspire future research on discourse-level modeling and evaluation of long-form QA systems.

cs.CL↗

Training Dynamics for Text Summarization Models

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.

cs.CL↗

The Case for Claim Difficulty Assessment in Automatic Fact Checking

Fact-checking is the process of evaluating the veracity of claims (i.e., purported facts). In this opinion piece, we raise an issue that has received little attention in prior work -- that some claims are far more difficult to fact-check than others. We discuss the implications this has for both practical fact-checking and research on automated fact-checking, including task formulation and dataset design. We report a manual analysis undertaken to explore factors underlying varying claim difficulty and identify several distinct types of difficulty. We motivate this new claim difficulty prediction task as beneficial to both automated fact-checking and practical fact-checking organizations.

cs.CL↗

Evaluation Toolkit For Robustness Testing Of Automatic Essay Scoring Systems

Automatic scoring engines have been used for scoring approximately fifteen million test-takers in just the last three years. This number is increasing further due to COVID-19 and the associated automation of education and testing. Despite such wide usage, the AI-based testing literature of these "intelligent" models is highly lacking. Most of the papers proposing new models rely only on quadratic weighted kappa (QWK) based agreement with human raters for showing model efficacy. However, this effectively ignores the highly multi-feature nature of essay scoring. Essay scoring depends on features like coherence, grammar, relevance, sufficiency and, vocabulary. To date, there has been no study testing Automated Essay Scoring: AES systems holistically on all these features. With this motivation, we propose a model agnostic adversarial evaluation scheme and associated metrics for AES systems to test their natural language understanding capabilities and overall robustness. We evaluate the current state-of-the-art AES models using the proposed scheme and report the results on five recent models. These models range from feature-engineering-based approaches to the latest deep learning algorithms. We find that AES models are highly overstable. Even heavy modifications(as much as 25%) with content unrelated to the topic of the questions do not decrease the score produced by the models. On the other hand, irrelevant content, on average, increases the scores, thus showing that the model evaluation strategy and rubrics should be reconsidered. We also ask 200 human raters to score both an original and adversarial response to seeing if humans can detect differences between the two and whether they agree with the scores assigned by auto scores.

cs.CL↗

AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses

Deep-learning based Automatic Essay Scoring (AES) systems are being actively used by states and language testing agencies alike to evaluate millions of candidates for life-changing decisions ranging from college applications to visa approvals. However, little research has been put to understand and interpret the black-box nature of deep-learning based scoring algorithms. Previous studies indicate that scoring models can be easily fooled. In this paper, we explore the reason behind their surprising adversarial brittleness. We utilize recent advances in interpretability to find the extent to which features such as coherence, content, vocabulary, and relevance are important for automated scoring mechanisms. We use this to investigate the oversensitivity i.e., large change in output score with a little change in input essay content) and overstability i.e., little change in output scores with large changes in input essay content) of AES. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models with rich contextual embeddings such as BERT, behave like bag-of-words models. A few words determine the essay score without the requirement of any context making the model largely overstable. This is in stark contrast to recent probing studies on pre-trained representation learning models, which show that rich linguistic features such as parts-of-speech and morphology are encoded by them. Further, we also find that the models have learnt dataset biases, making them oversensitive. To deal with these issues, we propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies. We find that our proposed models are able to detect unusual attribution patterns and flag adversarial samples successfully.

cs.CL↗

Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification

Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions. However, adding content can often be useful when difficult concepts and reasoning need to be explained. In this work, we present the first data-driven study of content addition in text simplification, which we call elaborative simplification. We introduce a new annotated dataset of 1.3K instances of elaborative simplification in the Newsela corpus, and analyze how entities, ideas, and concepts are elaborated through the lens of contextual specificity. We establish baselines for elaboration generation using large-scale pre-trained language models, and demonstrate that considering contextual specificity during generation can improve performance. Our results illustrate the complexities of elaborative simplification, suggesting many interesting directions for future work.

cs.CL↗

Roosterize: Suggesting Lemma Names for Coq Verification Projects Using Deep Learning

Naming conventions are an important concern in large verification projects using proof assistants, such as Coq. In particular, lemma names are used by proof engineers to effectively understand and modify Coq code. However, providing accurate and informative lemma names is a complex task, which is currently often carried out manually. Even when lemma naming is automated using rule-based tools, generated names may fail to adhere to important conventions not specified explicitly. We demonstrate a toolchain, dubbed Roosterize, which automatically suggests lemma names in Coq projects. Roosterize leverages a neural network model trained on existing Coq code, thus avoiding manual specification of naming conventions. To allow proof engineers to conveniently access suggestions from Roosterize during Coq project development, we integrated the toolchain into the popular Visual Studio Code editor. Our evaluation shows that Roosterize substantially outperforms strong baselines for suggesting lemma names and is useful in practice. The demo video for Roosterize can be viewed at: https://youtu.be/HZ5ac7Q14rc.

cs.PL↗

Learning to Generate Code Comments from Class Hierarchies

Descriptive code comments are essential for supporting code comprehension and maintenance. We propose the task of automatically generating comments for overriding methods. We formulate a novel framework which accommodates the unique contextual and linguistic reasoning that is required for performing this task. Our approach features: (1) incorporating context from the class hierarchy; (2) conditioning on learned, latent representations of specificity to generate comments that capture the more specialized behavior of the overriding method; and (3) unlikelihood training to discourage predictions which do not conform to invariant characteristics of the comment corresponding to the overridden method. Our experiments show that the proposed approach is able to generate comments for overriding methods of higher quality compared to prevailing comment generation techniques.

cs.CL↗

Paragraph-level Simplification of Medical Texts

We consider the problem of learning to simplify medical texts. This is important because most reliable, up-to-date information in biomedicine is dense with jargon and thus practically inaccessible to the lay audience. Furthermore, manual simplification does not scale to the rapidly growing body of biomedical literature, motivating the need for automated approaches. Unfortunately, there are no large-scale resources available for this task. In this work we introduce a new corpus of parallel texts in English comprising technical and lay summaries of all published evidence pertaining to different clinical topics. We then propose a new metric based on likelihood scores from a masked language model pretrained on scientific texts. We show that this automated measure better differentiates between technical and lay summaries than existing heuristics. We introduce and evaluate baseline encoder-decoder Transformer models for simplification and propose a novel augmentation to these in which we explicitly penalize the decoder for producing "jargon" terms; we find that this yields improvements over baselines in terms of readability.

cs.CL↗

Did they answer? Subjective acts and intents in conversational discourse

Discourse signals are often implicit, leaving it up to the interpreter to draw the required inferences. At the same time, discourse is embedded in a social context, meaning that interpreters apply their own assumptions and beliefs when resolving these inferences, leading to multiple, valid interpretations. However, current discourse data and frameworks ignore the social aspect, expecting only a single ground truth. We present the first discourse dataset with multiple and subjective interpretations of English conversation in the form of perceived conversation acts and intents. We carefully analyze our dataset and create computational models to (1) confirm our hypothesis that taking into account the bias of the interpreters leads to better predictions of the interpretations, (2) and show disagreements are nuanced and require a deeper understanding of the different contextual factors. We share our dataset and code at http://github.com/elisaF/subjective_discourse.

cs.CL↗

My Teacher Thinks The World Is Flat! Interpreting Automatic Essay Scoring Mechanism

Significant progress has been made in deep-learning based Automatic Essay Scoring (AES) systems in the past two decades. However, little research has been put to understand and interpret the black-box nature of these deep-learning based scoring models. Recent work shows that automated scoring systems are prone to even common-sense adversarial samples. Their lack of natural language understanding capability raises questions on the models being actively used by millions of candidates for life-changing decisions. With scoring being a highly multi-modal task, it becomes imperative for scoring models to be validated and tested on all these modalities. We utilize recent advances in interpretability to find the extent to which features such as coherence, content and relevance are important for automated scoring mechanisms and why they are susceptible to adversarial samples. We find that the systems tested consider essays not as a piece of prose having the characteristics of natural flow of speech and grammatical structure, but as `word-soups' where a few words are much more important than the other words. Removing the context surrounding those few important words causes the prose to lose the flow of speech and grammar, however has little impact on the predicted score. We also find that since the models are not semantically grounded with world-knowledge and common sense, adding false facts such as ``the world is flat'' actually increases the score instead of decreasing it.

cs.CL↗

Deep Just-In-Time Inconsistency Detection Between Comments and Source Code

Natural language comments convey key aspects of source code such as implementation, usage, and pre- and post-conditions. Failure to update comments accordingly when the corresponding code is modified introduces inconsistencies, which is known to lead to confusion and software bugs. In this paper, we aim to detect whether a comment becomes inconsistent as a result of changes to the corresponding body of code, in order to catch potential inconsistencies just-in-time, i.e., before they are committed to a code base. To achieve this, we develop a deep-learning approach that learns to correlate a comment with code changes. By evaluating on a large corpus of comment/code pairs spanning various comment types, we show that our model outperforms multiple baselines by significant margins. For extrinsic evaluation, we show the usefulness of our approach by combining it with a comment update model to build a more comprehensive automatic comment maintenance system which can both detect and resolve inconsistent comments based on code changes.

cs.SE↗