Search Results for author: Junyi Jessy Li

Found 77 papers, 48 papers with code

The Role of Context and Uncertainty in Shallow Discourse Parsing

no code implementations COLING 2022 Katherine Atwell, Remi Choi, Junyi Jessy Li, Malihe Alikhani

We find that including annotator accuracy and confidence improves model accuracy, and incorporating confidence in the model’s temperature function can lead to models with significantly better-calibrated confidence measures.

Discourse Parsing

Large Language Models Produce Responses Perceived to be Empathic

no code implementations26 Mar 2024 Yoon Kyung Lee, Jina Suh, Hongli Zhan, Junyi Jessy Li, Desmond C. Ong

Large Language Models (LLMs) have demonstrated surprising performance on many tasks, including writing supportive messages that display empathy.

Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion

no code implementations16 Nov 2023 Smriti Singh, Cornelia Caragea, Junyi Jessy Li

Situations and events evoke emotions in humans, but to what extent do they inform the prediction of emotion detection models?

QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing

1 code implementation23 Oct 2023 Yating Wu, Ritika Mangla, Greg Durrett, Junyi Jessy Li

Questions Under Discussion (QUD) is a versatile linguistic framework in which discourse progresses as continuously asking questions and answering them.

Discourse Parsing Language Modelling +3

Evaluating Subjective Cognitive Appraisals of Emotions from Large Language Models

1 code implementation22 Oct 2023 Hongli Zhan, Desmond C. Ong, Junyi Jessy Li

The emotions we experience involve complex processes; besides physiological aspects, research in psychology has studied cognitive appraisals where people assess their situations subjectively, according to their own values (Scherer, 2005).

Multilingual Code Co-Evolution Using Large Language Models

1 code implementation27 Jul 2023 Jiyang Zhang, Pengyu Nie, Junyi Jessy Li, Milos Gligoric

In this paper, we target a novel task: translating code changes from one programming language to another using large language models (LLMs).

Unsupervised Extractive Summarization of Emotion Triggers

1 code implementation2 Jun 2023 Tiberiu Sosea, Hongli Zhan, Junyi Jessy Li, Cornelia Caragea

Second, we develop new unsupervised learning models that can jointly detect emotions and summarize their triggers.

Abstractive Text Summarization Extractive Summarization +1

Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias

1 code implementation25 May 2023 Venkata S Govindarajan, Kyle Mahowald, David I. Beaver, Junyi Jessy Li

While existing work on studying bias in NLP focues on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior.

counterfactual Specificity

Using Natural Language Explanations to Rescale Human Judgments

1 code implementation24 May 2023 Manya Wadhwa, Jifan Chen, Junyi Jessy Li, Greg Durrett

The rise of large language models (LLMs) has brought a critical need for high-quality human-labeled data, particularly for processes like human feedback and evaluation.

Question Answering

Multilingual Simplification of Medical Texts

1 code implementation21 May 2023 Sebastian Joseph, Kathryn Kazanas, Keziah Reina, Vishnesh J. Ramanathan, Wei Xu, Byron C. Wallace, Junyi Jessy Li

This work addresses this limitation via multilingual simplification, i. e., directly simplifying complex texts into simplified texts in multiple languages.

Sentence Text Simplification

Elaborative Simplification as Implicit Questions Under Discussion

no code implementations17 May 2023 Yating Wu, William Sheffield, Kyle Mahowald, Junyi Jessy Li

Automated text simplification, a technique useful for making text more accessible to people such as children and emergent bilinguals, is often thought of as a monolingual translation task from complex sentences to simplified sentences using encoder-decoder models.

Question Generation Question-Generation +1

Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)

1 code implementation10 May 2023 Chantal Shaib, Millicent L. Li, Sebastian Joseph, Iain J. Marshall, Junyi Jessy Li, Byron C. Wallace

Large language models, particularly GPT-3, are able to produce high quality summaries of general domain news articles in few- and zero-shot settings.

Learning Deep Semantics for Test Completion

1 code implementation20 Feb 2023 Pengyu Nie, Rahul Banerjee, Junyi Jessy Li, Raymond J. Mooney, Milos Gligoric

We formalize the novel task of test completion to automatically complete the next statement in a test method based on the context of prior statements and the code under test.

Code Completion Code Generation

Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts

1 code implementation22 Oct 2022 Hongli Zhan, Tiberiu Sosea, Cornelia Caragea, Junyi Jessy Li

This paper takes a novel angle, namely, emotion detection and trigger summarization, aiming to both detect perceived emotions in text, and summarize events and their appraisals that trigger each emotion.

Emotion Detection and Trigger Summarization

Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion

1 code implementation12 Oct 2022 Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, Junyi Jessy Li

Human evaluation results show that QUD dependency parsing is possible for language models trained with this crowdsourced, generalizable annotation scheme.

Dependency Parsing Question Answering +1

News Summarization and Evaluation in the Era of GPT-3

1 code implementation26 Sep 2022 Tanya Goyal, Junyi Jessy Li, Greg Durrett

Finally, we evaluate models on a setting beyond generic summarization, specifically keyword-based summarization, and show how dominant fine-tuning approaches compare to prompting.

News Summarization Text Summarization

How people talk about each other: Modeling Generalized Intergroup Bias and Emotion

2 code implementations14 Sep 2022 Venkata S Govindarajan, Katherine Atwell, Barea Sinno, Malihe Alikhani, David I. Beaver, Junyi Jessy Li

Current studies of bias in NLP rely mainly on identifying (unwanted or negative) bias towards a specific demographic group.

Text Simplification of College Admissions Instructions: A Professionally Simplified and Verified Corpus

no code implementations COLING 2022 Zachary W. Taylor, Maximus H. Chu, Junyi Jessy Li

We present PSAT (Professionally Simplified Admissions Texts), a dataset with 112 admissions instructions randomly selected from higher education institutions across the US.

Sentence Text Simplification

CoditT5: Pretraining for Source Code and Natural Language Editing

1 code implementation10 Aug 2022 Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie, Junyi Jessy Li, Milos Gligoric

Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits.

Bug fixing Language Modelling +1

SNaC: Coherence Error Detection for Narrative Summarization

1 code implementation19 May 2022 Tanya Goyal, Junyi Jessy Li, Greg Durrett

In this work, we introduce SNaC, a narrative coherence evaluation framework rooted in fine-grained annotations for long summaries.

Benchmarking Coherence Evaluation +1

Evaluating Factuality in Text Simplification

1 code implementation ACL 2022 Ashwin Devaraj, William Sheffield, Byron C. Wallace, Junyi Jessy Li

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.

Text Simplification

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

1 code implementation ACL 2022 Fangyuan Xu, Junyi Jessy Li, Eunsol Choi

Long-form answers, consisting of multiple sentences, can provide nuanced and comprehensive answers to a broader set of questions.

Natural Questions Sentence

Discourse Comprehension: A Question Answering Framework to Represent Sentence Connections

1 code implementation1 Nov 2021 Wei-Jen Ko, Cutter Dalton, Mark Simmons, Eliza Fisher, Greg Durrett, Junyi Jessy Li

While there has been substantial progress in text comprehension through simple factoid question answering, more holistic comprehension of a discourse still presents a major challenge (Dunietz et al., 2020).

Question Answering Reading Comprehension +1

Training Dynamics for Text Summarization Models

no code implementations Findings (ACL) 2022 Tanya Goyal, Jiacheng Xu, Junyi Jessy Li, Greg Durrett

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.

Hallucination News Summarization +1

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

no code implementations24 Sep 2021 Yaman Kumar Singla, Swapnil Parekh, Somesh Singh, Junyi Jessy Li, Rajiv Ratn Shah, Changyou Chen

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.

Representation Learning

The Case for Claim Difficulty Assessment in Automatic Fact Checking

no code implementations20 Sep 2021 Prakhar Singh, Anubrata Das, Junyi Jessy Li, Matthew Lease

Fact-checking is the process of evaluating the veracity of claims (i. e., purported facts).

Fact Checking

Emotion analysis and detection during COVID-19

no code implementations LREC 2022 Tiberiu Sosea, Chau Pham, Alexander Tekle, Cornelia Caragea, Junyi Jessy Li

Crises such as natural disasters, global pandemics, and social unrest continuously threaten our world and emotionally affect millions of people worldwide in distinct ways.

Domain Adaptation Emotion Recognition

Paragraph-level Simplification of Medical Texts

1 code implementation NAACL 2021 Ashwin Devaraj, Iain J. Marshall, Byron C. Wallace, Junyi Jessy Li

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.

Language Modelling

Did they answer? Subjective acts and intents in conversational discourse

1 code implementation NAACL 2021 Elisa Ferracane, Greg Durrett, Junyi Jessy Li, Katrin Erk

Discourse signals are often implicit, leaving it up to the interpreter to draw the required inferences.

valid

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

1 code implementation1 Mar 2021 Pengyu Nie, Karl Palmskog, Junyi Jessy Li, Milos Gligoric

Naming conventions are an important concern in large verification projects using proof assistants, such as Coq.

LEMMA

Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification

1 code implementation Findings (ACL) 2021 Neha Srikanth, Junyi Jessy Li

Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions.

Explanation Generation Sentence +2

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

1 code implementation4 Oct 2020 Sheena Panthaplackel, Junyi Jessy Li, Milos Gligoric, Raymond J. Mooney

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.

Inquisitive Question Generation for High Level Text Comprehension

1 code implementation EMNLP 2020 Wei-Jen Ko, Te-Yuan Chen, Yiyan Huang, Greg Durrett, Junyi Jessy Li

Inquisitive probing questions come naturally to humans in a variety of settings, but is a challenging task for automatic systems.

Question Generation Question-Generation +2

Learning to Format Coq Code Using Language Models

no code implementations18 Jun 2020 Pengyu Nie, Karl Palmskog, Junyi Jessy Li, Milos Gligoric

Should arguments to the rewrite tactic be separated by a single space?

An Annotated Dataset of Discourse Modes in Hindi Stories

no code implementations LREC 2020 Swapnil Dhanwal, Hritwik Dutta, Hitesh Nankani, Nilay Shrivastava, Yaman Kumar, Junyi Jessy Li, Debanjan Mahata, Rakesh Gosangi, Haimin Zhang, Rajiv Ratn Shah, Am Stent, a

In this paper, we present a new corpus consisting of sentences from Hindi short stories annotated for five different discourse modes argumentative, narrative, descriptive, dialogic and informative.

Descriptive Sentence

Detecting Perceived Emotions in Hurricane Disasters

1 code implementation ACL 2020 Shrey Desai, Cornelia Caragea, Junyi Jessy Li

Natural disasters (e. g., hurricanes) affect millions of people each year, causing widespread destruction in their wake.

Learning to Update Natural Language Comments Based on Code Changes

1 code implementation ACL 2020 Sheena Panthaplackel, Pengyu Nie, Milos Gligoric, Junyi Jessy Li, Raymond J. Mooney

We formulate the novel task of automatically updating an existing natural language comment based on changes in the body of code it accompanies.

Deep Generation of Coq Lemma Names Using Elaborated Terms

3 code implementations16 Apr 2020 Pengyu Nie, Karl Palmskog, Junyi Jessy Li, Milos Gligoric

Our results show that Roosterize substantially outperforms baselines for suggesting lemma names, highlighting the importance of using multi-input models and elaborated terms.

LEMMA

Associating Natural Language Comment and Source Code Entities

no code implementations13 Dec 2019 Sheena Panthaplackel, Milos Gligoric, Raymond J. Mooney, Junyi Jessy Li

Comments are an integral part of software development; they are natural language descriptions associated with source code elements.

Discourse Level Factors for Sentence Deletion in Text Simplification

no code implementations23 Nov 2019 Yang Zhong, Chao Jiang, Wei Xu, Junyi Jessy Li

We inspect various document and discourse factors associated with sentence deletion, using a new manually annotated sentence alignment corpus we collected.

Sentence Text Simplification

Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis

1 code implementation IJCNLP 2019 Shrey Desai, Barea Sinno, Alex Rosenfeld, Junyi Jessy Li

Insightful findings in political science often require researchers to analyze documents of a certain subject or type, yet these documents are usually contained in large corpora that do not distinguish between pertinent and non-pertinent documents.

text-classification Text Classification +1

Plain English Summarization of Contracts

1 code implementation WS 2019 Laura Manor, Junyi Jessy Li

We propose the task of summarizing such legal documents in plain English, which would enable users to have a better understanding of the terms they are accepting.

Extractive Summarization Text Summarization +1

Domain Agnostic Real-Valued Specificity Prediction

1 code implementation13 Nov 2018 Wei-Jen Ko, Greg Durrett, Junyi Jessy Li

Sentence specificity quantifies the level of detail in a sentence, characterizing the organization of information in discourse.

Dialogue Generation Informativeness +3

Why Swear? Analyzing and Inferring the Intentions of Vulgar Expressions

no code implementations EMNLP 2018 Eric Holgate, Isabel Cachola, Daniel Preo{\c{t}}iuc-Pietro, Junyi Jessy Li

Vulgar words are employed in language use for several different functions, ranging from expressing aggression to signaling group identity or the informality of the communication.

Hate Speech Detection

Aggregating and Predicting Sequence Labels from Crowd Annotations

1 code implementation ACL 2017 An Thanh Nguyen, Byron Wallace, Junyi Jessy Li, Ani Nenkova, Matthew Lease

Despite sequences being core to NLP, scant work has considered how to handle noisy sequence labels from multiple annotators for the same text.

named-entity-recognition Named Entity Recognition +2

Improving the Annotation of Sentence Specificity

no code implementations LREC 2016 Junyi Jessy Li, Bridget O{'}Daniel, Yi Wu, Wenli Zhao, Ani Nenkova

We found that the lack of specificity distributes evenly among immediate prior context, long distance prior context and no prior context.

Sentence Specificity

Cannot find the paper you are looking for? You can Submit a new open access paper.