Junyi Jessy Li

I am an Assistant Professor in the Linguistics Department at The University of Texas at Austin where I work on computational linguistics and natural language processing. More specifically, my research focuses on discourse, pragmatics, and NLP in social contexts. I obtained my Ph.D. from the Department of Computer and Information Science at the University of Pennsylvania in 2017, advised by Ani Nenkova. Usually, I go by Jessy.

Some of the topics that I am currently researching include:

• Discourse organization: A text is more than the sum of its sentences; what else is going on and what are the implications for existing models? We investigate some of the high-level devices at play, including discourse (rhetorical) structure, language specificity, and pragmatic functions.
• Text intelligibility: Language is often subject to change depending on the context in which communication takes place. We work towards finding discourse aspects that impact text intelligibility for a target audience and addressing them in generation models.
• Language and society: We seek to understand how people use language in social media to achieve their communication goals, and how major events impact language use in both conventional media and social media.
• Language and code: Together with researchers in UT’s CS and ECE departments, we model natural language (e.g., comments, method names) and linguistic characteristics (e.g., coreference) in programming languages and software repositories.

Recent Activities

• Invited talk at the University of Houston NLP seminar, Apr 2021
• Invited talk at Georgia Tech NLP seminar, Mar 2021
• Invited talk at University of Pittsburgh NLP Seminar, Mar 2021
• Invited talk at UMD CLIPS colloquium, Feb 2021
• Invited talk at Valkyrie Intelligence, Jan 2021
• Invited talk at Salesforce Research, Dec 2020
• Co-organizer of the 2nd Workshop on Computational Approaches to Discourse (CODI) co-located w/ EMNLP 2021
• Co-organizer of the The First Workshop on Natural Language Processing for Programming (NLP4Prog) co-located w/ ACL-IJCNLP 2021
• Publication chair and board member of SIGDIAL
• Senior Area Chair of Disourse and Pragmatics and best paper selection committee at NAACL 2021; Area Chair of Machine Learning at ACL-IJCNLP 2021; Senior PC member of AAAI 2021; Area Chair of Dialog Systems at NLPCC 2021; PC member of EACL 2021, EMNLP 2021, UnImplicit 2021
• Standing reviewer of TACL and CL

Publications

• Did they answer? Subjective acts and intents in conversational discourse [data and code]
  Elisa Ferracane, Greg Durrett, Junyi Jessy Li and Katrin Erk
  North American Chapter of the Association for Computational Linguistics (NAACL), 2021, to appear.

• Paragraph-level Simplification of Medical Texts
  Ashwin Devaraj, Iain Marshall, Byron Wallace and Junyi Jessy Li
  North American Chapter of the Association for Computational Linguistics (NAACL), 2021, to appear.

• Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
  Neha Srikanth and Junyi Jessy Li
  ArXiv Preprint.

• Roosterize: Suggesting Lemma Names for Coq Verification Projects Using Deep Learning [bib and code]
  Pengyu Nie, Karl Palmskog, Junyi Jessy Li, Milos Gligoric
  International Conference on Software Engineering, Demonstrations Track (ICSE DEMO), 2021

• How to apply for financial aid: Exploring perplexity and jargon in texts for non-expert audiences
  Laura Manor, Yiran Su, Zachary W. Taylor and Junyi Jessy Li
  Society for Computation in Linguistics (SCiL) abstract, 2021

• Deep Just-In-Time Inconsistency Detection Between Comments and Source Code [bib, code and data]
  Sheena Panthaplackel, Junyi Jessy Li, Milos Gligoric, and Raymond J. Mooney
  The AAAI Conference on Artificial Intelligence (AAAI), 2021

• Assessing Discourse Relations in Language Generation from GPT-2 [bib]
  Wei-Jen Ko and Junyi Jessy Li
  International Conference on Natural Language Generation (INLG), 2020

• Inquisitive Question Generation for High Level Text Comprehension [bib] [data]
  Wei-Jen Ko, Te-Yuan Chen, Yiyan Huang, Greg Durrett and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

• Help! Need Advice on Identifying Advice [bib] [code and data]
  Venkata Subrahmanyan Govindarajan, Benjamin Chen, Rebecca Warholic, Katrin Erk and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020

• On the Naturalness of Hardware Descriptions [bib, code and data]
  Jaeseong Lee, Pengyu Nie, Junyi Jessy Li, and Milos Gligoric
  Symposium on the Foundations of Software Engineering (FSE), 2020

• Detecting Perceived Emotions in Hurricane Disasters [bib] [code and data]
  Shrey Desai, Cornelia Caragea and Junyi Jessy Li
  Association for Computational Linguistics (ACL), 2020

• Learning to Update Natural Language Comments Based on Code Changes [bib] [code and data]
  Sheena Panthaplackel, Pengyu Nie, Milos Gligoric, Junyi Jessy Li and Raymond Mooney
  Association for Computational Linguistics (ACL), 2020

• An Annotated Dataset of Discourse Modes in Hindi Stories [bib] [data]
  Swapnil Dhanwal, Hritwik Dutta, Hitesh Nankani, Nilay Shrivastava, Yaman Kumar, Junyi Jessy Li, Debanjan Mahata, Rakesh Gosangi, Haimin Zhang, Rajiv Ratn Shah and Amanda Stent
  International Conference on Language Resources and Evaluation (LREC), 2020

• Deep Generation of Coq Lemma Names Using Elaborated Terms [bib, code and data]
  Pengyu Nie, Karl Palmskog, Junyi Jessy Li and Milos Gligoric
  International Joint Conference on Automated Reasoning (IJCAR), 2020

• Learning to Format Coq Code Using Language Models
  Pengyu Nie, Karl Palmskog, Junyi Jessy Li, and Milos Gligoric
  The Coq Workshop, 2020

• Discourse Level Factors for Sentence Deletion in Text Simplification
  Yang Zhong, Chao Jiang, Wei Xu and Junyi Jessy Li
  The AAAI Conference on Artificial Intelligence (AAAI), 2020

• Associating Natural Language Comment and Source Code Entities [bib, code and data]
  Sheena Panthaplackel, Milos Gligoric, Raymond Mooney and Junyi Jessy Li
  The AAAI Conference on Artificial Intelligence (AAAI), 2020

• Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis [bib] [code and data]
  Shrey Desai, Barea Sinno, Alex Rosenfeld and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019

• Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification [bib]
  Hsin-Ping Huang and Junyi Jessy Li
  Conference on Computational Natural Language Learning (CoNLL), 2019

• A Framework for Writing Trigger-Action Todo Comments in Executable Format [bib] [code]
  Pengyu Nie, Rishabh Rai, Junyi Jessy Li, Sarfraz Khurshid, Raymond Mooney and Milos Gligoric
  Symposium on the Foundations of Software Engineering (FSE), 2019 (ACM SIGSOFT Distinguished Paper Award)

• Evaluating Discourse in Structured Text Representations [bib] [code]
  Elisa Ferracane, Greg Durrett, Junyi Jessy Li and Katrin Erk
  Association for Computational Linguistics (ACL), 2019

• Linguistically-Informed Specificity and Semantic Plausibility for Dialog Generation [bib] [code]
  Wei-Jen Ko, Greg Durrett and Junyi Jessy Li
  North American Chapter of the Association for Computational Linguistics (NAACL), 2019

• Plain English Summarization of Contracts [bib] [data]
  Laura Manor and Junyi Jessy Li
  NAACL Workshop on Natural Legal Language Processing (NLLP), 2019

• From News to Medical: Cross-domain Discourse Segmentation [bib] [code and data]
  Elisa Ferracane, Titan Page, Junyi Jessy Li and Katrin Erk
  NAACL Workshop on Rhetorical Structure Theory and Related Formalisms (DISRPT), 2019

• Domain Agnostic Real-Valued Specificity Prediction [bib] [code and data]
  Wei-Jen Ko, Greg Durrett and Junyi Jessy Li
  The AAAI Conference on Artificial Intelligence (AAAI), 2019

• Predicting and Analyzing Language Specificity in Social Media Posts [bib] [code and data]
  Yifan Gao, Yang Zhong, Daniel Preoţiuc-Pietro and Junyi Jessy Li
  The AAAI Conference on Artificial Intelligence (AAAI), 2019

• Why Swear? Analyzing and Inferring the Intentions of Vulgar Expressions [bib] [data] [video by Isabel Cachola]
  Eric Holgate, Isabel Cachola, Daniel Preoţiuc-Pietro and Junyi Jessy Li
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018

• Expressively vulgar: The socio-dynamics of vulgarity and its effects on sentiment analysis in social media [bib] [data/code]
  Isabel Cachola, Eric Holgate, Daniel Preoţiuc-Pietro and Junyi Jessy Li
  International Conference on Computational Linguistics (COLING), 2018 (Area Chair Favorite)

• A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature [bib] [webpage]
  Benjamin Nye, Junyi Jessy Li, Roma Patel, Yinfei Yang, Iain Marshall, Ani Nenkova and Byron Wallace
  Association for Computational Linguistics (ACL), 2018

• Natural Language Processing and Program Analysis for Supporting Todo Comments as Software Evolves [bib]
  Pengyu Nie, Junyi Jessy Li, Sarfraz Khurshid, Raymond Mooney, and Milos Gligoric
  AAAI Workshop on NLP for Software Engineering (NL4SE), 2018

• Aggregating and Predicting Sequence Labels from Crowd Annotations [bib] [code] [data]
  An Thanh Nguyen, Byron Wallace, Junyi Jessy Li, Ani Nenkova, and Matthew Lease
  Association for Computational Linguistics (ACL), 2017

• Autism Quotient Scores Modulate the Perception and Production of Text Specificity in Adult Females
  Junyi Jessy Li, Julia Parish-Morris, Leila Bateman and Ani Nenkova
  International Meeting for Autism Research (IMFAR), abstract, 2017

• From Discourse Structure to Text Specificity: Studies of Coherence Preferences
  Junyi Jessy Li
  Ph.D. thesis, University of Pennsylvania, 2017

• The Role of Discourse Units in Near-Extractive Summarization [bib] [code] [data]
  Junyi Jessy Li, Kapil Thadani and Amanda Stent
  Special Interest Group on Discourse and Dialogue (SIGDIAL), 2016 (Best Paper Nominee)

• The Instantiation Discourse Relation: A Corpus Analysis of Its Properties and Improved Detection [bib]
  Junyi Jessy Li and Ani Nenkova
  North American Chapter of the Association for Computational Linguistics (NAACL), 2016

• Improving the Annotation of Sentence Specificity [bib] [data]
  Junyi Jessy Li, Bridget O’Daniel, Yi Wu, Wenli Zhao, Ani Nenkova
  International Conference on Language Resources and Evaluation (LREC), 2016

• Estimating Text Intelligibility via Information Packaging Analysis [bib]
  Junyi Jessy Li, AAAI/SIGAI Doctoral Consortium at AAAI 2016

• Detecting Content-Heavy Sentences: A Cross-Language Case Study [bib]
  Junyi Jessy Li and Ani Nenkova
  Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015

• Fast and Accurate Prediction of Sentence Specificity [bib] [code]
  Junyi Jessy Li and Ani Nenkova
  The AAAI Conference on Artificial Intelligence (AAAI), 2015

• Cross-lingual Discourse Relation Analysis: A corpus study and a semi-supervised classification system [bib]
  Junyi Jessy Li, Marine Carpuat and Ani Nenkova
  International Conference on Computational Linguistics (COLING), 2014

• Assessing the Discourse Factors that Influence the Quality of Machine Translation [bib]
  Junyi Jessy Li, Marine Carpuat and Ani Nenkova
  Association for Computational Linguistics (ACL), 2014

• Addressing Class Imbalance for Improved Recognition of Implicit Discourse Relations [bib]
  Junyi Jessy Li and Ani Nenkova
  Special Interest Group on Discourse and Dialogue (SIGDIAL), 2014

• Reducing Sparsity Improves the Recognition of Implicit Discourse Relations [bib]
  Junyi Jessy Li and Ani Nenkova
  Special Interest Group on Discourse and Dialogue (SIGDIAL), 2014

Students

• Current graduate students:
  • Wei-Jen Ko (PhD, co-advised with Greg Durrett)
  • Laura Manor (PhD)
  • Venkata Govindarajan (PhD, co-advised with David Beaver)
• Current undergraduate students:
  • Cutter Dalton, Linguistics.
  • Ashwin Devaraj, Computer Science.
  • Gauraang Dhamankar, Computer Science.
  • Eliza Fisher, Linguistics.
  • Arjun Kunjilwar, Computer Science.
  • Bernardo Oviedo, Computer Science.
  • Lokesh Pugalenthi, Computer Science and French.
  • Chau Pham, CRA DREU 2020, Colgate University.
• Former graduate students:
  • Elisa Ferracane PhD 2020, co-advised with Katrin Erk.
  • Neha Srikanth, MS thesis 2020, Computer Science.
  • Prakhar Singh (Spring 2020), MS, Computer Science, co-advised with Matt Lease.
  • Yiran (Erin) Su (Spring 2020), MS, Electrical and Computer Engineering.
  • Te-Yuan Chen (Spring 2020), MS, School of Information.
  • Yiyan Huang (Spring 2020), MS, School of Information.
  • Hsin-Ping Huang (Spring-Summer 2018), MS, Computer Science.
• Former undergraduate students:
  • Alexander Tekle (Electrical and Computer Engineering 2021 → Google).
  • Benjamin Chen (Computer Science 2020 → Amazon).
  • Shrey Desai (Computer Science 2020, Dean’s Honored Graduate, Lala Fay & Claude DeVan Watts Endowed Presidential Scholarship, Undergraduate Research Fellowship, CRA Outstanding Undergraduate Researcher 2020 Honorable Mention → Facebook).
  • Isabel Cachola (Maths 2019, Dean’s Honored Graduate, Aspire Research Excellence Award, Undergraduate Research Fellowship → AI2 Young Investigator, PhD student at JHU)
  • Yifan Gao (Maths 2019 → masters student at JHU).
  • Rebecca Warholic (CRA DREU 2019, Smith College → graduate program at McGill)
  • Yang Zhong (Maths 2019 → PhD student at U Pittsburgh).
  • Victor Mena (Linguistics 2018)

Teaching

• Spring 2021:
  • LIN 373N: Machine Learning Toolbox for Text Analysis
  • LIN 389C: Research in Computational Linguistics
• Fall 2020:
  • LIN 313: Language and Computers
  • LIN 393: Discourse Processing and Natural Language Generation
  • LIN 389C: Research in Computational Linguistics (instructor on record: Katrin Erk)
• Spring 2020:
  • LIN 373: Machine Learning Toolbox for Text Analysis
  • LIN 389C: Research in Computational Linguistics
• Fall 2019:
  • LIN 313: Language and Computers
  • LIN 393: Computational Linguistics with Minimal Supervision
  • LIN 389C: Research in Computational Linguistics (instructor on record: Katrin Erk)
• Spring 2019:
  • LIN 373: Machine Learning Toolbox for Text Analysis
  • LIN 389C: Research in Computational Linguistics
• Fall 2018:
  • LIN 313: Language and Computers
  • LIN 393S: Computational Discourse
  • LIN 389C: Research in Computational Linguistics (instructor on record: Katrin Erk)
• Spring 2018:
  • LIN 313: Language and Computers
  • LIN 389C: Research in Computational Linguistics
• Fall 2012, Fall 2013, Fall 2014:
  • CIS 430/530: Computational Linguistics (TA, University of Pennsylvania)
• Spring 2011:
  • CIS 120: Programming Languages and Techniques I (TA, University of Pennsylvania)
• Spring 2009:
  • VG 101: Introduction to Programming (TA, Shanghai Jiao Tong University)