Large-scale Semantic Parsing without Question-Answer Pairs

By Siva Reddy, Mirella Lapata, Mark Steedman. 2014

247 citations recorded by the source corpus.

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

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 Natural Language Processing

In Information Extraction

Citations in the corpus

Large-scale Simple Question Answering with Memory Networks (2015, methodology): “Some of these approaches require little to no question-answer pairs (Fader et al., 2013; Reddy et al., 2014), relying on simple rules to tranform the semantic interpretation to a KB query.”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, neutral): “They have been studied extensively (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007; Das et al., 2010; Liang et al., 2011; Banarescu et al., 2013; Artzi and Zettlemoyer, 2013; Reddy et al., 2014; Berant and Liang, 2014; Dong and Lapata, 2016).”
Language to Logical Form with Neural Attention (2016, background): “…and Zettlemoyer, 2011), system demonstrations (Chen and Mooney, 2011; Goldwasser and Roth, 2011; Artzi and Zettle-moyer, 2013), question-answer pairs (Clarke et al., 2010; Liang et al., 2013), and distant supervision (Krishnamurthy and Mitchell, 2012; Cai and Yates, 2013; Reddy et al., 2014).”
Building a Semantic Parser Overnight (2015, background): “Recent work has made signiﬁcant strides in reducing supervision from logical forms (Zettle-moyer and Collins, 2005; Wong and Mooney, 2007) to denotations (Clarke et al., 2010; Liang et al., 2011) and to weaker forms (Artzi and Zettle-moyer, 2011; Reddy et al., 2014).”
Neural Module Networks for Reasoning over Text (2019, methodology): “Approaches have used labeled logical-forms (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005), or weak QA supervision (Clarke et al., 2010; Berant et al., 2013; Reddy et al., 2014) to learn parsers to answer questions against structured knowledge bases.”
Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base (2015, methodology): “Several semantic parsing methods use a domain-independent meaning representation derived from the combinatory categorial grammar (CCG) parses (e.g., (Cai and Yates, 2013; Kwiatkowski et al., 2013; Reddy et al., 2014)).”
Question Answering over Freebase with Multi-Column Convolutional Neural Networks (2015, background): “So recent works (Liang et al., 2011; Kwiatkowski et al., 2013; Berant et al., 2013; Berant and Liang, 2014; Bao et al., 2014; Reddy et al., 2014) mainly aimed at using weak supervision (question-answer pairs) to effectively train semantic parsers.”
Learning executable semantic parsers for natural language understanding (2016, background): “One can use a large corpus of text to exploit even weaker supervision [16, 27].”
The Value of Semantic Parse Labeling for Knowledge Base Question Answering (2016, methodology): “The design of our UI is inspired by recent work on semantic parsing that has been applied to the WEBQUESTIONS dataset (Bast and Haussmann, 2015; Reddy et al., 2014; Berant and Liang, 2014; Yih et al., 2015), as these approaches use a simpler and yet more restricted semantic representa-”
From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood (2017, background): “Our work is motivated by the classic problem of learning semantic parsers from indirect supervision (Clarke et al., 2010; Liang et al., 2011; Artzi and Zettlemoyer, 2011, 2013; Reddy et al., 2014; Pasupat and Liang, 2015).”
Alignment-Based Compositional Semantics for Instruction Following (2015, methodology): “Related models have previously been used for question answering (Reddy et al., 2014; Pasupat and Liang, 2015).”
Probabilistic Models for Learning a Semantic Parser Lexicon (2016, background): “Other work has avoided the lexicon learning problem altogether by searching over all possible meaning representations (Kate and Mooney, 2006; Clarke et al., 2010; Goldwasser et al., 2011; Berant and Liang, 2014; Pasupat and Liang, 2015; Reddy et al., 2014).”
SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning (2017, background): “…been many works considering parsing a natural language description into a logical form (Zelle & Mooney, 1996; Wong & Mooney, 2007; Zettlemoyer & Collins, 2007; 2012; Artzi & Zettlemoyer, 2011; 2013; Cai & Yates, 2013; Reddy et al., 2014; Liang et al., 2011; Quirk et al., 2015; Chen et al., 2016).”
Sequence-based Structured Prediction for Semantic Parsing (2016, methodology): “Reddy et al. (2014) exploits a weak supervision signal to learn a mapping between the logical form associated by a CCG based semantic parser with the input question and the appropriate logical form in Freebase (Bollacker et al., 2008).”
ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters (2018, background): “…interface for KBs, where questions are translated to structured queries via semantic parsing (Bao et al., 2016; Bast and Haussmann, 2015; Berant et al., 2013; Fader et al., 2013; Reddy et al., 2014; Mohammed et al., 2018; Xu et al., 2016; Yang et al., 2014; Yao and Durme, 2014; Yih et al., 2015).”
Learning to Learn Semantic Parsers from Natural Language Supervision (2019, background): “…Pasupat and Liang, 2015; Liang et al., 2016; Krishnamurthy et al., 2017); learning from indirect supervision from a large-scale knowledge base (Reddy et al., 2014; Krishnamurthy and Mitchell, 2012); learning from conversations of systems asking for and confirming information (Artzi and…”
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (2018, methodology): “Reddy et al. (2014, 2016) use Freebase-based semantic graph representation, and convert sentences to semantic graphs using CCG or dependency tree.”