Probabilistic Models for Learning a Semantic Parser Lexicon

By Jayant Krishnamurthy. 2016

10 citations recorded by the source corpus.

We introduce several probabilistic models for learning the lexicon of a semantic parser. Lexicon learning is the first step of training a semantic parser for a new application domain and the quality of the learned lexicon significantly affects both the accuracy and efficiency of the final semantic parser. Existing work on lexicon learning has focused on heuristic methods that lack convergence guarantees and require significant human input in the form of lexicon templates or annotated logical forms. In contrast, our probabilistic models are trained directly from question/answer pairs using EM and our simplest model has a concave objective that guarantees convergence to a global optimum. An experimental evaluation on a set of 4th grade science questions demonstrates that our models improve semantic parser accuracy (35-70% error reduction) and efficiency (4-25x more sentences per second) relative to prior work despite using less human input. Our models also obtain competitive results on GEO880 without any datasetspecific engineering.

Subfields: Artificial Intelligence, Molecular Biology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Natural Language Processing

Citations in the corpus

Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “We then use the PAL lexicon induction algorithm (Krishnamurthy, 2016) to expand the lexicon by adding automatically generated entries.”
Learning Out-of-Vocabulary Words in Intelligent Personal Agents (2018, unknown): “…and Mooney, 1996 ] , machine translation [ Wong and Mooney, 2007 ] , probabilistic CCG/CFG grammar based parsers [ Zettlemoyer and Collins, 2005; 2007; Kwiatkowski et al. , 2011; Artzi and Zettlemoyer, 2013; Krishnamurthy, 2016 ] , neural networks [ Jia and Liang, 2016; Dong and Lapata, 2016 ] .”
Building a Neural Semantic Parser from a Domain Ontology (2018, unknown): “…Goldwater, & Steedman, 2010b; Kwiatkowski et al., 2011; Krishnamurthy & Mitchell, 2012; Artzi, Das, & Petrov, 2014; Krishnamurthy & Mitchell, 2015; Krishnamurthy, 2016; Gardner & Kr-ishnamurthy, 2017) or using less supervision (Artzi & Zettlemoyer, 2013a; Reddy, Lapata, & Steedman, 2014).”