A Pilot Study for Chinese SQL Semantic Parsing

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 3652–3658, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 3652 A Pilot Study for Chinese SQL Semantic Parsing Qingkai Min , Yuefeng Shi and Yue Zhang School of Engineering, Westlake University, China Institute of Advanced Technology, Westlake Institute for Advanced Study {minqingkai, shiyuefeng, zhangyue}@westlake.edu.cn Abstract The task of semantic parsing is highly use- ful for dialogue and question answering sys- tems. Many datasets have been proposed to map natural language text into SQL, among which the recent Spider dataset provides cross- domain samples with multiple tables and com- plex queries. We build a Spider dataset for Chinese, which is currently a low-resource language in this task area. Interesting research questions arise from the uniqueness of the lan- guage, which requires word segmentation, and also from the fact that SQL keywords and columns of DB tables are typically written in English. We compare character- and word- based encoders for a semantic parser, and dif- ferent embedding schemes. Results show that word-based semantic parser is subject to seg- mentation errors and cross-lingual word em- beddings are useful for text-to-SQL. 1 Introduction The task of semantic parsing is highly useful for tasks such as dialogue (Chen et al., 2013; Gupta et al., 2018; Einolghozati et al., 2019) and question answering (Gildea and Jurafsky, 2002; Yih et al., 2015; Reddy et al., 2016). Among a wide range of possible semantic representations, SQL offers a standardized interface to knowledge bases across tasks (Astrova, 2009; Xu et al., 2017; Dong and Lapata, 2018; Lee et al., 2011). Recently, Yu et al. (2018b) released a manually labelled dataset for parsing natural language questions into complex SQL, which facilitates related research. Yu et al. (2018b)’s dataset is exclusive for En- glish questions. Intuitively, the same semantic parsing task can be applied cross-lingual, since SQL is a universal semantic representation and database interface. However, for languages other than English, there can be added difficulties pars- ing into SQL. Take Chinese for example, the addi- tional challenges can be at least two-fold. First, structures of relational databases, in particular names and column names of DB tables, are typi- cally represented in English. This adds to the chal- lenges to question-to-DB mapping. Second, the basic semantic unit for denoting columns or cells can be words, but word segmentation can be erro- neous. It is also interesting to study the influence of other linguistic characteristics of Chinese, such as zero-pronoun, on its SQL parsing. We investigate parsing Chinese questions to SQL by creating a first dataset, and empirically evaluating a strong baseline model on the dataset. In particular, we translate the Spider (Yu et al., 2018b) dataset into Chinese. Using the model of Yu et al. (2018a), we compare several key model configurations. Results show that our human-translated dataset is significantly more reliable compared to a dataset composed of machine-translated questions. In addition, the overall accuracy …

Content truncated to 500 words