百度语义解析 ( Text-to-SQL ) 技术研究及应用( 六 )

外界知识的利用：有一些常识信息不包含在表格中，如排序操作的方向判断（列为“出生日期” ，问题为“年龄最大的员工”）、表格值进制转换（列为“人口(亿)” ，问题为“人口超5千万的城市”）等，这些信息需要引入外界知识来协助SQL生成。

融进渐进式对话：对于用户的歧义表达和模糊表达，需要有“提问-反馈-再提问”的过程，这类问题往往需要通过多轮对话解决，而用户的问题通常是上下文相关的，因此需要模型具备基于上下文的理解和分析能力。

今天的分享就到这里，谢谢大家。
参考文献
[1] Seq2sql: Generating structured queries from natural language using reinforcement learning (Victor Zhong, Caiming Xiong, Richard Socher. CoRR2017)
[2] Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, etc. EMNLP2018)
[3] A Pilot Study for Chinese SQL Semantic Parsing (Qingkai Min, Yuefeng Shi, Yue Zhang. EMNLP2019)
[4] SParC: Cross-Domain Semantic Parsing in Context (Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, etc. ACL2019)
[5] CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (Tao Yu, Rui Zhang, He Yang Er, Suyi Li, Eric Xue, etc. EMNLP2019)
[6] https://tianchi.aliyun.com/markets/tianchi/zhuiyi_cn
[7] Pointer Networks （OriolVinyals, Meire Fortunato, Navdeep Jaitly. NIPS2015）
[8] Semantic Parsing with Syntax- and Table-Aware SQL Generation (Yibo Sun, Duyu Tang, Nan Duan, etc. ACL2018)
[9] Coarse-to-Fine Decoding for Neural Semantic Parsing (Li Dong, Mirella Lapata. ACL2018)
[10] SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning (Xiaojun Xu, Chang Liu, DawnSong. CoRR 2018)
[11] TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation (Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir Radev. NAACL2018)
[12] Achieving 90% accuracy in WikiSQL (Wonseok Hwang, Jinyeong Yim, SeungHyun Park, Mnjoon Seo. CoRR2019)
[13] X-SQL: Reinforce Context Into Schema Representation (Pengcheng He, Yi Mao, Kaushik Chakrabarti, Weizhu Chen. CoRR2019)
[14] TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation (Pengcheng Yin, Graham Neubig, EMNLP 2018 )
[15] Abstract syntax networks for code generation and semantic parsing (Maxim Rabinovich, Mitchell Stern, Dan Klein. ACL2017)
[16] Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (Jiaqi Guo, Zecheng Zhan, Yan Gao, Yan Xiao, Jian-Guang Lou, Ting Liu, Dongmei Zhang. ACL2019)
[17] Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing (Ben Bogin, Matt Gardner, Jonathan Berant. ACL2019)
[18] RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (Bailin Wang, Richard Shin, Xiaodong Liu, Oleksandr Polozov, Matthew Richardson. Submitted to ACL2020)
[19] Robust Text-to-SQL Generation with Execution-Guided Decoding (Chenglong Wang, Kedar Tatwawadi, Marc Brockschmidt, Po-Sen Huang, Yi Mao, Oleksandr Polozov, Rishabh Singh. CoRR2018)