Learning an Executable Neural Semantic Parser

Learning an Executable Neural Semantic Parser Jianpeng Cheng University of Edinburgh jianpeng.cheng@ed.ac.uk Siva Reddy Stanford University sivar@stanford.edu Vijay Saraswat IBM T.J. Watson Research vjsaraswat@stanford.edu Mirella Lapata University of Edinburgh mlap@inf.ed.ac.uk This article describes a neural semantic parser that maps natural language utterances onto logical forms that can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser generates tree-structured logical forms with a transition-based approach, combining a generic tree-generation algorithm with domain-general grammar defined by the logical language. The generation process is modeled by structured re- current neural networks, which provide a rich encoding of the sentential context and generation history for making predictions. To tackle mismatches between natural language and logical form tokens, various attention mechanisms are explored. Finally, we consider different training settings for the neural semantic parser, including fully supervised training where annotated logical forms are given, weakly supervised training where denotations are provided, and distant supervision where only unlabeled sentences and a knowledge base are available. Experiments across a wide range of data sets demonstrate the effectiveness of our parser. 1. Introduction An important task in artificial intelligence is to develop systems that understand natural language and enable interactions between computers and humans. Semantic parsing has emerged as a key technology toward achieving this goal. Semantic parsers specify a mapping between natural language utterances and machine-understandable meaning Submission received: 6 November 2017; revised version received: 17 July 2018; accepted for publication: 10 August 2018. doi:10.1162/COLI a 00342 © 2019 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 45, Number 1 Table 1 Examples of questions, corresponding logical forms, and their answers. Environment: A database of US geography Utterance: What is the longest river in Ohio? Logical form: longest(and(type.river, location(Ohio))) Denotation: Ohio River Environment: Freebase Utterance: How many daughters does Obama have? Logical form: count(daughterOf(Barack Obama)) Denotation: 2 representations, commonly known as logical forms. A logical form can be executed against a real-world environment, such as a knowledge base, to produce a response, often called a denotation. Table 1 shows examples of natural language queries, their cor- responding logical forms, and denotations. The query What is the longest river in Ohio? is represented by the logical form longest(and(type.river, location(Ohio))), which when executed against a database of US geography returns the answer Ohio River. In the second example, the logical form count(daughterOf(Barack Obama)) corresponds to the query How many daughters does Obama have? and is executed against the Freebase knowledge base to return the answer 2. In recent years, semantic parsing has attracted a great deal of attention because of its utility in a wide range of applications, such as question answering (Kwiatkowski et al. 2011; Liang, Jordan, and Klein 2011), relation extraction (Krishnamurthy and Mitchell 2012), goal-oriented dialog (Wen et al. 2015), natural language interfaces (Popescu et al. 2004), robot control (Matuszek et al. 2012), and interpreting instructions (Chen and Mooney 2011; Artzi and Zettlemoyer 2013). …

Content truncated to 500 words