Xiang Deng
Ohio State University
24 Papers
152 Citations
Xiang Deng is an academic researcher from Ohio State University. The author has contributed to research in topics: Computer science & Relationship extraction. The author has an hindex of 5, co-authored 9 publications.
Chat about Author
Papers
Mind2Web: Towards a Generalist Agent for the Web
TL;DR: Mind2Web as mentioned in this paper is a dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website, but it is not suitable for generalist web agents.
165
AgentBench: Evaluating LLMs as Agents
Xiao Liu,Hao Yu,Hanchen Zhang,Yifan Xu,Xuanyu Lei,Hanyu Lai,Yu Gu,Yuxian Gu,Hangliang Ding,Kai Men,Kejuan Yang,Shudan Zhang,Xiang Deng,Aohan Zeng,Zhengxiao Du,Chenhui Zhang,Shengqi Shen,Tianjun Zhang,Yu Su,Huan Sun,Minlie Huang,Yuxiao Dong,Jie Tang +22 more
TL;DR: An extensive test over 27 API-based and open-sourced LLMs shows that, while top commercial LLMs present a strong ability of acting as agents in complex environments, there is a significant disparity in performance between them and OSS competitors.
•Posted Content
TURL: Table Understanding through Representation Learning
TL;DR: This paper proposes a structure-aware Transformer encoder to model the row-column structure of relational tables, and presents a new Masked Entity Recovery objective for pre-training to capture the semantics and knowledge in large-scale unlabeled data.
137
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng,Ahmed Hassan Awadallah,Christopher A. Meek,Oleksandr Polozov,Huan Sun,Matthew Richardson +5 more
TL;DR: A novel weakly supervised Structure-Grounded pretraining framework for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text- table corpus and brings significant improvement over BERTLARGE in all settings.
Structure-Grounded Pretraining for Text-to-SQL
Xiang Deng,Ahmed Hassan Awadallah,Christopher A. Meek,Oleksandr Polozov,Huan Sun,Matthew Richardson +5 more
- 01 Jun 2021
TL;DR: STRUG as mentioned in this paper is a weakly supervised structure-grounded pretraining framework for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text table corpus.