Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques

被引:0
|
作者
Rai, Daking [1 ]
Wang, Bailin [2 ]
Zhou, Yilun [2 ]
Yao, Ziyu [1 ]
机构
[1] George Mason Univ, Fairfax, VA 22030 USA
[2] MIT, Cambridge, MA USA
基金
美国国家科学基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs). In this study, we empirically investigate improving an LM's generalization in semantic parsing with two simple techniques: at the token level, we introduce a token preprocessing method to preserve the semantic boundaries of tokens produced by LM tokenizers; at the sequence level, we propose to use special tokens to mark the boundaries of components aligned between input and output. Our experimental results on two text-to-SQL semantic parsing datasets show that our token preprocessing, although simple, can substantially improve the LM performance on both types of generalization, and our component boundary marking method is particularly helpful for compositional generalization.
引用
收藏
页码:150 / 160
页数:11
相关论文
共 20 条
  • [1] Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study
    Yao, Ziyu
    Su, Yu
    Sun, Huan
    Yih, Wen-tau
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 5447 - 5458
  • [2] UniSAr: a unified structure-aware autoregressive language model for text-to-SQL semantic parsing
    Dou, Longxu
    Gao, Yan
    Pan, Mingyang
    Wang, Dingzirui
    Che, Wanxiang
    Lou, Jian-Guang
    Zhan, Dechen
    [J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 14 (12) : 4361 - 4376
  • [3] UniSAr: a unified structure-aware autoregressive language model for text-to-SQL semantic parsing
    Longxu Dou
    Yan Gao
    Mingyang Pan
    Dingzirui Wang
    Wanxiang Che
    Jian-Guang Lou
    Dechen Zhan
    [J]. International Journal of Machine Learning and Cybernetics, 2023, 14 : 4361 - 4376
  • [4] On Modern Text-to-SQL Semantic Parsing Methodologies for Natural Language Interface to Databases: A Comparative Study
    Visperas, Moses
    Adoptante, Aunhel John
    Borjal, Christalline Joie
    Abia, Ma. Teresita
    Catapang, Jasper Kyle
    Peramo, Elmer
    [J]. 2023 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION, ICAIIC, 2023, : 390 - 396
  • [5] Approach of text search based on semantic parsing model
    Wei, XiangFeng
    Zhang, Quan
    [J]. FOURTH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, VOL 2, PROCEEDINGS, 2007, : 355 - +
  • [6] Model-based semantic dictionaries for medical language understanding
    Rassinoux, AM
    Baud, RH
    Ruch, P
    Trombert-Paviot, B
    Rodrigues, JM
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 1999, : 122 - 126
  • [7] MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain
    Marshan, Alaa
    Almutairi, Anwar Nais
    Ioannou, Athina
    Bell, David
    Monaghan, Asmat
    Arzoky, Mahir
    [J]. FRONTIERS IN BIG DATA, 2024, 7
  • [8] Improving the Accuracy of Text-to-SQL Tools Based on Large Language Models for Real-World Relational Databases
    Coelho, Gustavo M. C.
    Nascimento, Eduardo R. S.
    Izquierdo, Yenier T.
    Garcia, Grettel M.
    Feijo, Lucas
    Lemos, Melissa
    Garcia, Robinson L. S.
    de Oliveira, Aiko R.
    Pinheiro, Joao P.
    Casanova, Marco A.
    [J]. DATABASE AND EXPERT SYSTEMS APPLICATIONS, PT I, DEXA 2024, 2024, 14910 : 93 - 107
  • [9] Semantic Text Classification with Tensor Space Model-based Naive Bayes
    Kim, Han-joon
    Kim, Jiyun
    Kim, Jinseog
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2016, : 4206 - 4210
  • [10] STSG: A Short Text Semantic Graph Model for Similarity Computing Based on Dependency Parsing and Pre-trained Language Models
    Liao, Hai
    Liang, Yan
    Chen, Song
    Xiang, Lingyun
    Chang, Zhimin
    Xiao, Yun
    [J]. APPLIED ARTIFICIAL INTELLIGENCE, 2024, 38 (01)