paper-with-me

Papers

SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset

2022-08-26 · Saihao Huang, Lijie Wang, Zhenghua Li, Zeyang Liu, Chenhui Dou, Fukang Yan, Xinyan Xiao, Hua Wu, Min Zhang

As the first session-level Chinese dataset, CHASE contains two separate parts, i.e., 2,003 sessions manually constructed from scratch (CHASE-C), and 3,456 sessions translated from English SParC (CHASE-T). We find the two parts are highly discrepant and incompatible as training and evaluation data. In this work, we present SeSQL, yet another large-scale session-level text-to-SQL dataset in Chinese, consisting of 5,028 sessions all manually constructed from scratch. In order to guarantee data quality, we adopt an iterative annotation workflow to facilitate intense and in-time review of previous-round natural language (NL) questions and SQL queries. Moreover, by completing all context-dependent NL questions, we obtain 27,012 context-independent question/SQL pairs, allowing SeSQL to be used as the largest dataset for single-round multi-DB text-to-SQL parsing. We conduct benchmark session-level text-to-SQL parsing experiments on SeSQL by employing three competitive session-level parsers, and present detailed analysis.

📄 PDF Abstract BibTeX arXiv:2208.12711

Code (0)

등록된 구현이 없습니다.

Tasks

SQL ParsingText to SQLText-To-SQL

Similar Papers 제목 키워드 기반

Domain Adaptation for Robust Workload Level Alignment Between Sessions and Subjects using fNIRS

2020-07-02 · Boyang Lyu, Thao Pham, Giles Blaney, Zachary Haga 외

Significance: We demonstrated the potential of using domain adaptation on functional Near-Infrared Spectroscopy (fNIRS) data to classify different levels of n-back tasks that involve working memory. Aim: Domain shift in …

Domain Adaptation

S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks

2022-01-04 · Minjin Choi, jinhong Kim, Joonsek Lee, Hyunjung Shim 외

Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user. Most existing SR models focus only on modeling intra-session characteristics but pay less attenti…

Computational EfficiencyRecommendation SystemsSession-Based Recommendations

Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions

2020-05-15 · Zhuohao Chen, Nikolaos Flemotomos, Victor Ardulov, Torrey A. Creed 외

Cognitive Behavioral Therapy (CBT) is a goal-oriented psychotherapy for mental health concerns implemented in a conversational setting with broad empirical support for its effectiveness across a range of presenting probl…

SentenceSentence segmentation

Understanding Inter-Session Intentions via Complex Logical Reasoning

2023-12-21 · Jiaxin Bai, Chen Luo, Zheng Li, Qingyu Yin 외

Understanding user intentions is essential for improving product recommendations, navigation suggestions, and query reformulations. However, user intentions can be intricate, involving multiple sessions and attribute req…

AttributeComplex Query AnsweringLogical Reasoning

Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems

2019-04-08 · Jiaxuan You, Yichen Wang, Aditya Pal, Pong Eksombatchai 외

Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models w…

GPURecommendation SystemsSession-Based Recommendations