Large-scale Semantic Parsing without Question-Answer Pairs

Large-scale Semantic Parsing without Question-Answer Pairs Siva Reddy, Mirella Lapata, Mark Steedman School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB siva.reddy@ed.ac.uk, mlap@inf.ed.ac.uk, steedman@inf.ed.ac.uk Abstract In this paper we introduce a novel semantic parsing approach to query Freebase in natu- ral language without requiring manual anno- tations or question-answer pairs. Our key in- sight is to represent natural language via se- mantic graphs whose topology shares many commonalities with Freebase. Given this rep- resentation, we conceptualize semantic pars- ing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Free- base guided by denotations as a form of weak supervision. Evaluation experiments on a sub- set of the FREE917 and WEBQUESTIONS benchmark datasets show our semantic parser improves over the state of the art. 1 Introduction Querying a database to retrieve an answer, telling a robot to perform an action, or teaching a com- puter to play a game are tasks requiring communi- cation with machines in a language interpretable by them. Semantic parsing addresses the specific task of learning to map natural language (NL) to machine interpretable formal meaning representations. Tra- ditionally, sentences are converted into logical form grounded in the symbols of some fixed ontology or relational database. Approaches for learning semantic parsers have been for the most part supervised, using annotated training data consisting of sentences and their cor- responding logical forms (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007; Kwiatkowski et al., 2010). More recently, al- ternative forms of supervision have been proposed to alleviate the annotation burden, e.g., by learn- ing from conversational logs (Artzi and Zettlemoyer, 2011), from sentences paired with system behav- ior (Chen and Mooney, 2011; Goldwasser and Roth, Question What is the capital of Texas? Logical Form λx. city(x)∧capital(x,Texas) Answer {Austin} Figure 1: An example question with annotated logi- cal query, and its answer. 2011; Artzi and Zettlemoyer, 2013), via distant su- pervision (Krishnamurthy and Mitchell, 2012; Cai and Yates, 2013), from questions (Goldwasser et al., 2011; Poon, 2013; Fader et al., 2013), and question- answer pairs (Clarke et al., 2010; Liang et al., 2011). Indeed, methods which learn from question-answer pairs have been gaining momentum as a means of scaling semantic parsers to large, open-domain problems (Kwiatkowski et al., 2013; Berant et al., 2013; Berant and Liang, 2014; Yao and Van Durme, 2014). Figure 1 shows an example of a question, its annotated logical form, and answer (or denotation). In this paper, we build a semantic parser that does not require example annotations or question-answer pairs but instead learns from a large knowledge base (KB) and web-scale cor- pora. Specifically, we exploit Freebase, a large community-authored knowledge base that spans many sub-domains and stores real world facts in graphical format, and parsed sentences from a large corpus. We formulate semantic parsing as a graph matching problem. We convert the output of an open-domain combinatory categorial gram- mar (CCG) parser (Clark and Curran, 2007) into …

Content truncated to 500 words