On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries
复制标题
DOI：
10.18653/v1/2020.findings-emnlp.167
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Tianze Shi;Chen Zhao;Jordan L. Boyd-Graber;Hal Daum'e;Lillian Lee
中科院分区：
文献类型：
--
作者：
Tianze Shi;Chen Zhao;Jordan L. Boyd-Graber;Hal Daum'e;Lillian Lee
用逻辑形式注释的大规模语义解析数据集使监督方法取得了重大进展。但更丰富的监管能起到更大的作用吗？为了探索细粒度的词汇级监督的实用性，我们引入了SQUALL，这是一个数据集，它通过手动创建的SQL等价物以及SQL和问题片段之间的对齐来丰富11，276个WIKITABLEQUESTIONS英语问题。我们的注释为编码器解码器模型提供了新的训练可能性，包括以前因缺乏对齐而无法使用的机器翻译方法。我们提出并测试了两种方法：（1）监督注意;（2）采用一个辅助目标，消除歧义的输入查询表列中的引用。在5折交叉验证中，这些策略在强基线上提高了4.4%的执行准确性。Oracle实验表明，注释比对可以支持高达23.9%的进一步准确性增益。
Large-scale semantic parsing datasets annotated with logical forms have enabled major advances in supervised approaches. But can richer supervision help even more? To explore the utility of fine-grained, lexical-level supervision, we introduce SQUALL, a dataset that enriches 11,276 WIKITABLEQUESTIONS English-language questions with manually created SQL equivalents plus alignments between SQL and question fragments. Our annotation enables new training possibilities for encoderdecoder models, including approaches from machine translation previously precluded by the absence of alignments. We propose and test two methods: (1) supervised attention; (2) adopting an auxiliary objective of disambiguating references in the input queries to table columns. In 5-fold cross validation, these strategies improve over strong baselines by 4.4% execution accuracy. Oracle experiments suggest that annotated alignments can support further accuracy gains of up to 23.9%.