Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

By Luke S. Zettlemoyer, Michael Collins. 2005

1,003 citations recorded by the source corpus.

This paper addresses the problem of mapping natural language sentences to lambda–calculus encodings of their meaning. We describe a learning algorithm that takes as input a training set of sentences labeled with expressions in the lambda calculus. The algorithm induces a grammar for the problem, along with a log-linear model that represents a distribution over syntactic and semantic analyses conditioned on the input sentence. We apply the method to the task of learning natural language interfaces to databases and show that the learned parsers outperform previous methods in two benchmark database domains.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, background): “A related ﬁeld that tackles compositionality from a very different angle is that of trying to map sentences to logical form (Zettlemoyer and Collins, 2005).”
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs (2019, background): “…(e.g., SQL) that can perform discrete operations against a structured knowledge representation, such as knowledge graphs or tabular databases (Zettlemoyer and Collins, 2005 Logical form language Our logical form language identiﬁes ﬁve basic elements in the table representation:…”
Semantic Parsing on Freebase from Question-Answer Pairs (2013, background): “Traditional semantic parsers (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007; Kwiatkowski et al., 2010) have two limitations: (i) they require annotated logical forms as supervision, and (ii) they operate in limited domains with a small number of logical predicates.”
A Convolutional Neural Network for Modelling Sentences (2014, background): “Another approach represents the meaning of sentences by way of automatically extracted logical forms (Zettlemoyer and Collins, 2005).”
Show Your Work: Scratchpads for Intermediate Computation with Language Models (2021, neutral): “Finally, supervised approaches to semantic parsing (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005; Kwiatkowksi et al., 2010; Wong & Mooney, 2006) predict the text of a database query, which can then be executed to answer a natural language question.”
Break It Down: A Question Understanding Benchmark (2020, methodology): “Our formalism, Question Decomposition Meaning Representation (QDMR), is inspired by database query languages (SQL; SPARQL), and by semantic parsing (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Clarke et al., 2010), in which questions are given full meaning representations.”
A Discrete Hard EM Approach for Weakly Supervised Question Answering (2019, background): “Latent-variable learning has been extensively studied in the literature of semantic parsing (Zettlemoyer and Collins, 2005; Clarke et al., 2010; Liang et al., 2013; Berant et al., 2013; Artzi and Zettlemoyer, 2013).”
ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “Furthermore, it obviates the need to translate claims and evidence into meaning representations such as lambda calculus (Zettlemoyer and Collins, 2005).”
Training Classifiers with Natural Language Explanations (2018, methodology): “We lean on the formalism of semantic parsing (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang, 2016).”
Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “While semantic parsers have traditionally relied on labeled datasets of statements paired with labeled logical forms (Zettlemoyer and Collins, 2005), recent approaches have focused on training semantic parsers from denotations of logical forms, rather than logical forms themselves (Krishnamurthy…”
Grounded Language Learning in a Simulated 3D World (2017, background): “Semantic parsing, as pursued the field of natural language processing, has predominantly focussed on building a compositional mapping from natural language to formal semantic representations that are then grounded in a database or knowledge graph (Zettlemoyer and Collins, 2005; Berant et al., 2013).”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, methodology): “A few methods (Zettlemoyer and Collins, 2005; Ge and Mooney, 2006) use an expensive supervision in the form of manually annotated formal representations for every sentence in the training data.”
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, background): “• Semantic parsing converts questions to logical forms (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005).”
Modifying Memories in Transformer Models (2020, background): “KBs are widely utilized to store and access the relational knowledge in NLP domain (Ji et al., 2020; Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005, inter alia).”
Learning to Automatically Solve Algebra Word Problems (2014, background): “Other approaches have relied on access to more costly annotated logical forms (Zelle and Mooney, 1996; Thompson and Mooney, 2003; Wong and Mooney, 2006; Zettlemoyer and Collins, 2005; Kwiatkowski et al., 2010).”
The Web as a Knowledge-Base for Answering Complex Questions (2018, background): “Conversely, work on QA through semantic parsing has focused primarily on compositionality: questions are translated to compositional programs that encode a sequence of actions for finding the answer in a knowledge-base (KB) (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Artzi and Zettlemoye”