Junyi Jessy Li

I am an Assistant Professor in the Linguistics Department at The University of Texas at Austin. My research interests are in Natural Language Processing with a focus on computational discourse, in particular, techniques to characterize discourse structure and its impact on text understanding.

I obtained my Ph.D. from the Department of Computer and Information Science at the University of Pennsylvania in 2017, advised by Prof. Ani Nenkova. I got my BSE in Computer Science from the University of Michigan and BE in Electrical and Computer Engineering from the UM-SJTU Joint Institute at Shanghai Jiao Tong University. I was born in Shanghai, and here’s my name in Chinese: 李珺懿. Usually I go by Jessy.

Note to prospective students: I am looking to recruit graduate students who are passionate about computational discourse and/or interdisciplinary applications of NLP. You’re welcome to drop me a note, and to apply to the Linguistics Department’s PhD program.

Recent Service

• 2018: Area Chair (Discourse and Pragmatics) for NAACL, PC member for ACL, EMNLP, COLING, AAAI, IJCAI-ECAI, SIGDIAL, W-NUT, WiNLP, NLPCC, reviewer for the Computational Linguistics Journal
• 2017: PC member for EMNLP, ACL, ACL-SRW, EACL, EACL-SRW, W-NUT, NewSum, reviewer for the Dialogue and Discourse Journal

Publications

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

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

Resources

• [ACL’18] EBM-NLP: a corpus of richly annotated PICO elements of medical article abstracts.

• [ACL’17] Noisy sequence label aggregator and medical article abstracts with annotated participants (from crowd workers and professionals).

• [SIGDIAL’16] Code and data for near-extractive New York Times summaries.

• [LREC’16] Data for sentence specificity ratings and underspecified expressions within sentences.

• [AAAI’15] Speciteller, a fast and accurate predictor for sentence specificity.

Teaching

• Fall 2018:
  • LIN 313: Language and Computers
  • LIN 393S: Computational Discourse
• Previous:
  • 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)