Ruisheng Cao

Ruisheng Cao

Auto-generated profile, based on publicly available information

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

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2020 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
SZSu Zhu
Su Zhu
RCRuisheng Cao
Ruisheng Cao
Kai YuKai Yu
Kai Yu
Natural language understanding (NLU) converts sentences into structured semantic forms. The paucity of annotated training samples is still a fundamental challenge of NLU. To solve this data sparsity problem, previous work based on semi-supervised learning mainly focuses on exploiting unlabeled sentences. In this work, we introduce a dual task of NLU, semantic-to-sentence generation (SSG), and propose a new framework for semi-supervised NLU with the corresponding dual model. The framework is composed of dual pseudo-labeling and dual learning method, which enables an NLU model to make full use of data (labeled and unlabeled) through a closed-loop of the primal and dual tasks. By incorporating the dual task, the framework can exploit pure semantic forms as well as unlabeled sentences, and further improve the NLU and SSG models iteratively in the closed-loop. The proposed approaches are evaluated on two public datasets (ATIS and SNIPS). Experiments in the semi-supervised setting show that our methods can outperform various baselines significantly, and extensive ablation studies are conducted to verify the effectiveness of our framework. Finally, our method can also achieve the state-of-the-art performance on the two datasets in the supervised setting.

26 July 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
RCRuisheng Cao
Ruisheng Cao
LCLu Chen
Lu Chen
JLJieyu Li
Jieyu Li
HZHanchong Zhang
Hanchong Zhang
HXHongshen Xu
Hongshen Xu
Kai YuKai Yu
Kai Yu
Text-to-SQL is the task of converting a natural language utterance plus the corresponding database schema into a SQL program. The inputs naturally form a heterogeneous graph while the output SQL can be transduced into an abstract syntax tree (AST). Traditional encoder-decoder models ignore higher-order semantics in heterogeneous graph encoding and introduce permutation biases during AST construction, thus incapable of exploiting the refined structure knowledge precisely. In this work, we propose a generic heterogeneous graph to abstract syntax tree (HG2AST) framework to integrate dedicated structure knowledge into statistics-based models. On the encoder side, we leverage a line graph enhanced encoder (LGESQL) to iteratively update both node and edge features through dual graph message passing and aggregation. On the decoder side, a grammar-based decoder firstly constructs the equivalent SQL AST and then transforms it into the desired SQL via post-processing. To avoid over-fitting permutation biases, we propose a golden tree-oriented learning (GTL) algorithm to adaptively control the expanding order of AST nodes. The graph encoder and tree decoder are combined into a unified framework through two auxiliary modules. Extensive experiments on various text-to-SQL datasets, including single/multi-table, single/cross-domain, and multilingual settings, demonstrate the superiority and broad applicability.

9 February 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJieyu Li
Jieyu Li
ZCZhi Chen
Zhi Chen
LCLu Chen
Lu Chen
ZZZichen Zhu
Zichen Zhu
HLHanqi Li
Hanqi Li
Kai YuKai Yu
Kai Yu
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.

31 December 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DMDa Ma
Da Ma
XCXingyu Chen
Xingyu Chen
RCRuisheng Cao
Ruisheng Cao
ZCZhi Chen
Zhi Chen
LCLu Chen
Lu Chen
Kai YuKai Yu
Kai Yu
Generating natural language descriptions for structured representation (e.g., a graph) is an important yet challenging task. In this work, we focus on SQL-to-text, a task that maps a SQL query into the corresponding natural language question. Previous work represents SQL as a sparse graph and utilizes a graph-to-sequence model to generate questions, where each node can only communicate with k-hop nodes. Such a model will degenerate when adapted to more complex SQL queries due to the inability to capture long-term and the lack of SQL-specific relations. To tackle this problem, we propose a relation-aware graph transformer (RGT) to consider both the SQL structure and various relations simultaneously. Specifically, an abstract SQL syntax tree is constructed for each SQL to provide the underlying relations. We also customized self-attention and cross-attention strategies to encode the relations in the SQL tree. Experiments on benchmarks WikiSQL and Spider demonstrate that our approach yields improvements over strong baselines.

4 March 2024
Verified
Conference Paper
Open access
HXHongshen Xu
Hongshen Xu
LCLu Chen
Lu Chen
ZZZihan Zhao
Zihan Zhao
DMDa Ma
Da Ma
RCRuisheng Cao
Ruisheng Cao
Kai YuKai Yu
Kai Yu

1 January 2023
Verified
Conference Paper
Open access
PDF file
JLJieyu Li
Jieyu Li
LCLu Chen
Lu Chen
RCRuisheng Cao
Ruisheng Cao
SZSu Zhu
Su Zhu
HXHongshen Xu
Hongshen Xu
KYKai Yu
Kai Yu
Jieyu Li, Lu Chen, Ruisheng Cao, Su Zhu, Hongshen Xu, Zhi Chen, Hanchong Zhang, Kai Yu. Findings of the Association for Computational Linguistics: ACL 2023. 2023.