The goal of Southern California Natural Language Processing Symposium is to gather researchers from the southern California region with broad expertise in natural language processing. The symposium will provide a participatory environment where attendees from a variety of fields working on natural language processing can share and discuss their latest findings.

This year, SoCal NLP Symposium will be hosted on April 6, 2018 at University of California, Irvine, and it will include invited talks from academia and industry, contributed work, poster presentations and open discussion. We welcome all students, postdocs, and faculty members from universities in the region, including UC Irvine, University of Southern California (USC), UC Los Angeles, UC Santa Barbara, UC Riverside, Caltech, UC San Diego, and other schools to join us this April.

Please stay tuned for more information!


Parking Information

For attendees who plan on driving, the Student Center can provide on-site parking lots. Attendees can stop at the Student Center Parking Structure Parking Kiosk, which is located on the corner of West Peltason Drive and Pereira Drive. Please [click here] to see the detailed directions. Attendees are to pay the attendant $10 for a general UCI parking permit.

After exiting the Student Center Parking Structure, attendees can walk across the street to the Student Center and enter through the Conference Center doors. The right sides are the Doheny Beach meeting rooms. Please check in at the registration desk to receive the name badge and packet folder.

Invited Speakers

Kai-Wei Chang
Assistant Professor
Department of Computer Science

Dhruv Batra
Assistant Professor
School of Interactive Computing
Georgia Tech

Marilyn Walker
Department of Computer Science

Christopher Ré
Associate Professor
Department of Computer Science

Sujith Ravi
Staff Research Scientist


8:30am - 9:00am  Breakfast & registration
9:00am - 9:15am  Opening Remarks
9:15am - 10:00am  Invited Talk by Kai-Wei Chang (UCLA): Men Also Like Shopping: Reducing Societal Bias in Natural Language Processing Models [Details]
10:00am - 10:45am      Invited Talk by Marilyn Walker (UCSC): Modelling Narrative Structure in Informal First-Person Narratives [Details]
10:45am - 11:00am  Contributed Talk by Cassidy Henry: The Bot Language Project: Moving Towards Natural Dialogue with Robots
11:00am - 11:15am  Contributed Talk by Robert Logan: Attribute-Value Extraction from Multimodal Data
11:15am - 12:00pm  Poster Session
12:00pm - 1:00pm  Lunch
1:00pm - 1:45pm  Invited Talk by Christopher Ré (Stanford): Snorkel: Beyond Hand-Labeled Data [Details]
1:45pm - 2:30pm  Invited Talk by Dhruv Batra (Georgia Tech): Visual Dialog: Towards AI Agents that Can See, Talk, and Act [Details]
2:30pm - 2:45pm  Contributed Talk by Wenhan Xiong: Scheduled Policy Optimization for Natural Language Communication with Intelligent Agent
2:45pm - 3:00pm  Contributed Talk by Max Schwarzer: Human Evaluation for Text Simplification: The Simplicity-Adequacy Tradeoff
3:00pm - 4:15pm  Coffee Break & Poster Session
4:15pm - 5:00pm  Invited Talk by Sujith Ravi (Google): Neural Structured Learning for Language and Vision [Details]
5:00pm - 5:30pm  Panel: Invited Speakers
5:30pm - 5:45pm  Closing Remarks & Awards

Accepted Extended Abstracts

The accepted extended abstracts are listed as follows:

[Note: We request authors to prepare a poster for the poster session. The poster should be 48 inches long and 36 inches wide. Please try to set your poster up on the poster boards in the conference room before the talks for the day begin (9:00 am). The best paper award, best undergraduate paper award and best poster award will be announced at the end of the symposium (5:30 pm).]

  • Analysis of Scientific Language Variation by Research Fields. Pei Zhou, Muhao Chen, Kai-Wei Chang and Carlo Zaniolo.
  • Scheduled Policy Optimization for Natural Language Communication with Intelligent Agents. Wenhan Xiong and William Yang Wang.
  • A Deep Reinforcement Learning Method for Denoising Distant Supervision. Pengda Qin and William Yang Wang
  • Simple models for word formation in slang. Vivek Kulkarni and William Yang Wang.
  • Human Evaluation for Text Simplification: The Simplicity-Adequacy Tradeoff. Max Schwarzer and David Kauchak.
  • On The Effect of Hierarchical Reinforcement Learning in Summarization. Mahnaz Koupaee, Xin Wang and William Yang Wang.
  • Video Captioning via Hierarchical Reinforcement Learning. Xin Wang, Wenhu Chen, Jiawei Wu, Yuan-Fang Wang and William Yang Wang.
  • Coreference Resolution with Hierarchical Reinforcement Learning. Qingyu Yin and William Yang Wang.
  • Generating Natural Adversarial Examples. Zhengli Zhao, Dheeru Dua and Sameer Singh.
  • Neologism Based Domain Independent Models to Predict Year of Authorship of Documents. Vivek Kulkarni, Yingtao Tian, Parth Dandiwala and Steven Skiena.
  • Reinforced Co-Training. Jiawei Wu, Lei Li and William Yang Wang.
  • Identifying Social Roles in Online Discussions. Siddharth Jain.
  • Semi-Supervised Prediction-Constrained Topic Models. Michael Hughes, Gabriel Hope, Leah Weiner, Thomas McCoy, Roy Perlis, Erik Sudderth and Finale Doshi-Velez.
  • Quantifying Gendered Language at Mention Level. Ananya and Sameer Singh.
  • Embedding Multimodal Relational Data for Knowledge Base Completion. Pouya Pezeshkpour, Liyan Chen and Sameer Singh.
  • PRIMER – an emotionally reactive, mixed-initiative dialogue system. Carla Gordon, Anton Leuski and David Traum.
  • Using Meaning Specificity to Aid Negation Handling in Lexicon-Based Sentiment Analysis. Doreen Hii, Alan Yuen and Lisa Pearl.
  • Attribute-Value Extraction from Multimodal. Data Robert Logan and Sameer Singh.
  • Mixed Initiative in DS2A. Usman Sohail, Carla Gordon and David Traum.
  • Zero-Shot Relation Extraction from Word Embeddings. Orpaz Goldstein and Guy Van den Broeck.
  • Automatic Generation of Abstracts from Titles. Manuel Ciosici and Kevin Knight.
  • A Choctaw Morphology Generator. Jacqueline Brixey and Ron Artstein.
  • The Bot Language Project: Moving Towards Natural Dialogue with Robots. Cassidy Henry, Stephanie Lukin, Kimberly A. Pollard, Claire Bonial, Ashley Foots, Ron Artstein, Clare R. Voss, David Traum, Matthew Marge, Cory J. Hayes and Susan G. Hill.
  • Combining Intrinsic and Extrinsic Signals for Sentence Representations. Anthony Chen and Sameer Singh.
  • Mixtures of Contextual Experts for Language Modeling. Dimitrios Kotzias, Vishaal Prasad, Sameer Singh and Padhraic Smyth.
  • Multi-task Learning for Universal Sentence Representations. Wasi Ahmad, Xueying Bai, Zhechao Huang, Chao Jiang, Nanyun Peng and Kai-Wei Chang.
  • Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez Roman and Kai-Wei Chang.
  • Building Language Models for Text with Named Entities. Md Rizwan Parvez, Saikat Chakrabarti, Baishakhi Ray and Kai-Wei Chang.
  • Semi-supervised Content-based Fake News Detection using Tensor Embeddings and Label Propagation. Gisel Bastidas Guacho, Sara Abdali and Evangelos Papalexakis.
  • What It Takes to Achieve 100% Condition Accuracy on WikiSQL. Semih Yavuz, Izzeddin Gur, Yu Su and Xifeng Yan.



Sameer Singh
Assistant Professor
Department of Computer Science
UC Irvine

William Wang
Assistant Professor
Department of Computer Science
UC Santa Barbara

Student Co-Chairs

Dheeru Dua
Ph.D. Student
Department of Computer Science
UC Irvine

Jiawei Wu
Ph.D. Student
Department of Computer Science
UC Santa Barbara