University of Illinois at Chicago (UIC),
Chicago, IL, U.S.
Email: jzhan51@uic.edu
I am a research scientist at Salesforce AI Research. I received Ph.D. in the Department of Computer Science at the University of Illinois at Chicago. During my doctoral study, I was advised by Prof. Philip S. Yu in the BDSC Lab.
My previous research (before March 2019) focuses on adversarial training and its applications, and currently, I am mainly studying Conversational AI. My mission is to create accurate and smart dialog systems. My current research focuses on:
Natural language understanding, e.g., (few-shot) natural language understanding/classification/generation
Multi-domain dialog management, e.g., accurate (multimodal) dialog state tracking
Multi-modal dialog, e.g., multi-modal task-oriented dialog systems
News
Jan 2022: I will join Salesforce AI Research as a Research Scientist.
Sep 2021: Finished my internship at Facebook AI Research (FAIR). The project focuses on few-shot end-to-end task-oriented dialgue systems.
Aug 2021: Two paper are accepted by EMNLP 2021 main conference as short papers. One first-author work collaborates with Adobe Research and it focuses on natural language understanding.
June 2021: Check our new released paper and public resources for few-shot intent detection w/ and w/o out-of-scope queries.
May 2021: I finished my internship at Adobe Research and submitted one research paper, where I also discover PhotoShop user intents and improve intent detection performance using large-scale unlabeled PhotoShop user queries.
Dec 2020: Our toolkit NaturalCC has been released in GitHub, which can be accessed via the Homepage.
Nov 2020: We have released the paper, video for the EMNLP 2020 paper, and the corresponding code is available here!
Sep 2020: One first-author work collaborated with Salesforce Research is accepted by *SEM 2020 as a long paper. The work focuses on multi-domain dialog state tracking and it originally got borderline scores on ACL 2020. We have updated the paper!
Sep 2020: One first-author work collaborated with Salesforce Research is accepted by EMNLP 2020 main conference as a long paper. The work focuses on natural language understanding.
June 2020: One work collaborated with Google Research is accepted by ACL 2020 NLP4ConvAI, and the modified high-quality version of MultiWOZ 2.2 dataset with additional annotation
corrections and state tracking baselines is released here!
Publications
(Last Update: March 2022)
Are Pretrained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection
Jianguo Zhang, Kazuma Hashimoto, Yao Wan, Zhiwei Liu, Ye Liu, Caiming Xiong, Philip Yu
In Proceedings of ACL 2022 Workshop on NLP for Conversational AI
Program Committee/Reviewer: NLPCC 2019/2020; EMNLP 2020/2021; COLING 2020; NAACL-HLT 2021; ACL-IJCNLP 2021/2022; ACL Rolling Review; Transactions on Audio, Speech and Language Processing.
I am a photographer (Keep learning), guitar lover, pet lover (My cat name is Maomao), Chinese literature (Already read and forget many books) and basketball (Go Lakers, Metamind Lebron) fan.