Naihao(Neo) Deng

I am a reseach assistant at Westlake University, where I work with Yue Zhang on natural language processing (NLP). I am also a visiting scholar at University of Michigan.

I did my Master's at University of Michigan. I did my undergrad at Shanghai Jiao Tong University and University of Michigan.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

I am interested in the three aspects of NLP.

First, using NLP tools to understand the way human beings perceive the world, and build NLP models that can perceive the world better by studying how human beings perceive the world.

Second, building NLP applications that can help research and real-life applications.

Third, using NLP tools to study social problems systematically.

(* indicates equal contribution)

WildQA: In-the-Wild Video Question Answering
Santiago Castro*, Naihao Deng*, Pingxuan Huang*, Mihai G. Burzo, Rada Mihalcea
COLING, 2022 (Oral Presentation)
project page / arXiv / code+data

We propose WildQA, a video understanding dataset of videos recorded in outside settings. In addition to video question answering (Video QA), we also introduce the new task of identifying visual support for a given question and answer (Video Evidence Selection).

Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect
Naihao Deng, Yulong Chen, Yue Zhang
COLING, 2022 (Oral Presentation)
project page / arXiv

We review recent progress on text-to-SQL for datasets, methods, and evaluation and provide this systematic survey, addressing the aforementioned challenges and discussing potential future directions.

The Cross-lingual Conversation Summarization Challenge
Yulong Chen*, Ming Zhong*, Xuefeng Bai*, Naihao Deng, Jing Li, Xiaochao Zhu, Yue Zhang
INLG, 2022 Shared Task
arXiv

We propose the shared task of crosslingual conversation summarization, ConvSumX Challenge.

DialogSum Challenge: Results of the Dialogue Summarization Shared Task
Yulong Chen*, Naihao Deng*, Yang Liu, Yue Zhang
INLG, 2022 Shared Task report
arXiv

We report the results of DialogSum Challenge. We find that there is a salient gap between model generated outputs and human annotated summaries by human evaluation from multiple aspects.

Analyzing the Effects of Annotator Gender Across NLP Tasks
Laura Biester, Vanita Sharma, Ashkan Kazemi, Naihao Deng, Steven Wilson, Rada Mihalcea
Perspectivist Approaches to NLP @LREC, 2022
paper

We study annotator gender bias in NLP tasks of word similarity, sentiment analysis and NLI in 4 NLP datasets. We develop a robust framework to test for differences in annotation across genders for four benchmark datasets.

Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
Naihao Deng, Shuaichen Chang, Peng Shi, Tao Yu, Rui Zhang
(draft version accepted in NLP for Programming @ ACL-IJCNLP, 2021)
arxiv / code

We propose to generate SQL queries before users type in the complete text query. We build datasets to study this problem.

Service and Leadership
Program Committee, SUKI 2022 @NAACL 2022
Reviewer for LREC2022
Session Chair, 2021 Engineering Research Symposium @University of Michigan
Graduate Study Mentor, University of Michigan
Computer Consultant, University of Michigan Library
UM Concession Volunteer
Volunteer Teacher in Junior School, Yunnan, China
Graduate Student Instructor, EECS 486: Information Retrieval, University of Michigan
Student Instructor, VE230: Magnetics, Shanghai Jiao Tong University
Design and source code from Jon Barron's website