Universal Semantic Parsing

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 89–101 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Universal Semantic Parsing Siva Reddy†∗ Oscar T¨ackstr¨om‡ Slav Petrov‡ Mark Steedman†† Mirella Lapata†† †Stanford University ‡ Google Inc. ††University of Edinburgh sivar@stanford.edu, {oscart, slav}@google.com, {steedman, mlap}@inf.ed.ac.uk Abstract Universal Dependencies (UD) offer a uni- form cross-lingual syntactic representation, with the aim of advancing multilingual ap- plications. Recent work shows that se- mantic parsing can be accomplished by transforming syntactic dependencies to log- ical forms. However, this work is lim- ited to English, and cannot process de- pendency graphs, which allow handling complex phenomena such as control. In this work, we introduce UDEPLAMBDA, a semantic interface for UD, which maps natural language to logical forms in an almost language-independent fashion and can process dependency graphs. We per- form experiments on question answering against Freebase and provide German and Spanish translations of the WebQuestions and GraphQuestions datasets to facilitate multilingual evaluation. Results show that UDEPLAMBDA outperforms strong base- lines across languages and datasets. For English, it achieves a 4.9 F1 point improve- ment over the state-of-the-art on Graph- Questions. 1 Introduction The Universal Dependencies (UD) initiative seeks to develop cross-linguistically consistent annota- tion guidelines as well as a large number of uni- formly annotated treebanks for many languages (Nivre et al., 2016). Such resources could advance multilingual applications of parsing, improve com- parability of evaluation results, enable cross-lingual learning, and more generally support natural lan- guage understanding. ∗Work done at the University of Edinburgh Seeking to exploit the benefits of UD for natu- ral language understanding, we introduce UDEP- LAMBDA, a semantic interface for UD that maps natural language to logical forms, representing un- derlying predicate-argument structures, in an al- most language-independent manner. Our frame- work is based on DEPLAMBDA (Reddy et al., 2016) a recently developed method that converts English Stanford Dependencies (SD) to logical forms. The conversion process is illustrated in Figure 1 and discussed in more detail in Section 2. Whereas DEPLAMBDA works only for English, U- DEPLAMBDA applies to any language for which UD annotations are available.1 Moreover, DEP- LAMBDA can only process tree-structured inputs whereas UDEPLAMBDA can also process depen- dency graphs, which allow to handle complex con- structions such as control. The different treatments of various linguistic constructions in UD compared to SD also require different handling in UDEP- LAMBDA (Section 3.3). Our experiments focus on Freebase semantic parsing as a testbed for evaluating the framework’s multilingual appeal. We convert natural language to logical forms which in turn are converted to ma- chine interpretable formal meaning representations for retrieving answers to questions from Freebase. To facilitate multilingual evaluation, we provide translations of the English WebQuestions (Berant et al., 2013) and GraphQuestions (Su et al., 2016) datasets to German and Spanish. We demonstrate that UDEPLAMBDA can be used to derive logical forms for these languages using a minimal amount of language-specific knowledge. Aside from devel- oping the first multilingual semantic parsing tool for Freebase, …

Content truncated to 500 words