Zichen Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zichen Zhu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Kai Yu
Shanghai Jiao Tong University, Shanghai, China
5 shared publications - Lu Chen
School of Computer Science X-LANCE Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China
5 shared publications - Da Ma
X-LANCE lab, Shanghai Jiao Tong University, Shanghai, China
3 shared publications - Danyang Zhang
X-LANCE lab, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Ruisheng Cao
X-LANCE Lab, Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
2 shared publications - Situo Zhang
X-LANCE lab, Shanghai Jiao Tong University, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14761-14770
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14761-14770
Open AccessCharTool: Tool-Integrated Visual Reasoning for Chart Understanding
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 864-872
Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 864-872
Open AccessHierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
- 15 February 2024
- Published by Springer Nature
- p. 302-315
CAM-GUI: A Conversational Assistant on Mobile GUI
- 15 February 2024
- Published by Springer Nature
- p. 302-315
CAM-GUI: A Conversational Assistant on Mobile GUI
- Open Access
- 9 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2262
DIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL
Semantic co-reference and ellipsis always lead to information deficiency when parsing natural language utterances with SQL in a multi-turn dialogue (i.e., conversational text-to-SQL task). The methodology of dividing a dialogue understanding task into dialogue utterance rewriting and language understanding is feasible to tackle this problem. To this end, we present a two-stage framework to complete conversational text-to-SQL tasks. To construct an efficient rewriting model in the first stage, we provide a large-scale dialogue rewrite dataset (DIR), which is extended from two cross-domain conversational text-to-SQL datasets, SParC and CoSQL. The dataset contains 5908 dialogues involving 160 domains. Therefore, it not only focuses on conversational text-to-SQL tasks, but is also a valuable corpus for dialogue rewrite study. In experiments, we validate the efficiency of our annotations with a popular text-to-SQL parser, RAT-SQL. The experiment results illustrate 11.81 and 27.17 QEM accuracy improvement on SParC and CoSQL, respectively, when we eliminate the semantic incomplete representations problem by directly parsing the golden rewrite utterances. The experiment results of evaluating the performance of the two-stage frameworks using different rewrite models show that the efficiency of rewrite models is important and still needs improvement. Additionally, as a new benchmark of the dialogue rewrite task, we also report the performance results of different baselines for related studies. Our dataset will be publicly available once this paper is accepted.
- 9 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2262
Open AccessDIR: A Large-Scale Dialogue Rewrite Dataset for Cross-Domain Conversational Text-to-SQL
Semantic co-reference and ellipsis always lead to information deficiency when parsing natural language utterances with SQL in a multi-turn dialogue (i.e., conversational text-to-SQL task). The methodology of dividing a dialogue understanding task into dialogue utterance rewriting and language understanding is feasible to tackle this problem. To this end, we present a two-stage framework to complete conversational text-to-SQL tasks. To construct an efficient rewriting model in the first stage, we provide a large-scale dialogue rewrite dataset (DIR), which is extended from two cross-domain conversational text-to-SQL datasets, SParC and CoSQL. The dataset contains 5908 dialogues involving 160 domains. Therefore, it not only focuses on conversational text-to-SQL tasks, but is also a valuable corpus for dialogue rewrite study. In experiments, we validate the efficiency of our annotations with a popular text-to-SQL parser, RAT-SQL. The experiment results illustrate 11.81 and 27.17 QEM accuracy improvement on SParC and CoSQL, respectively, when we eliminate the semantic incomplete representations problem by directly parsing the golden rewrite utterances. The experiment results of evaluating the performance of the two-stage frameworks using different rewrite models show that the efficiency of rewrite models is important and still needs improvement. Additionally, as a new benchmark of the dialogue rewrite task, we also report the performance results of different baselines for related studies. Our dataset will be publicly available once this paper is accepted.