Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification

By Tom Kwiatkowski, Luke S. Zettlemoyer, Sharon Goldwater, Mark Steedman. 2010

327 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Semantic Parsing on Freebase from Question-Answer Pairs (2013, methodology): “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.”
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.”
A simple neural network module for relational reasoning (2017, background): “Answering text-based questions has long been an active research area in the NLP community [3, 22, 27, 48].”
Parsing Algebraic Word Problems into Equations (2015, background): “Our work is related to situated semantic interpretation, which aims to map natural language sentences to formal meaning representations (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Ge and Mooney, 2006; Kwiatkowski et al., 2010).”
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).”
Learning Dependency-Based Compositional Semantics (2011, methodology): “16 The 88.2% corresponds to 87.9% in Kwiatkowski et al. (2010).”
A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input (2014, positive): “Although the architecture learns the mapping from weak supervision, it achieves comparable results to the semantic parsers that rely on manual annotations of logical forms ([2], [3]).”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, methodology): “Supervised approaches for learning semantic parsers have received significant attention, e.g. Kate and Mooney (2006), Wong and Mooney (2007), Muresan (2011) and Kwiatkowski et al. (2010, 2012).”
Latent Predictor Networks for Code Generation (2016, background): “Unfortunately, these approaches define strong assumptions regarding the grammar and structure of the output, which makes it difficult to generalize for other domains (Kwiatkowski et al., 2010).”
Semantic Parsing via Paraphrasing (2014, background): “We consider the semantic parsing problem of mapping natural language utterances into logical forms to be executed on a knowledge base (KB) (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007; Kwiatkowski et al., 2010).”
Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World (2013, background): “…can be trained using sentences annotated with their formal representation (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Kate and Mooney, 2006; Kwiatkowski et al., 2010) or various less restrictive annotations (Clarke et al., 2010; Liang et al., 2011; Krishnamurthy and Mitchell, 2012).”
Language to Logical Form with Neural Attention (2016, background): “Tables 2–4 present comparisons against a variety of systems previously described Method Accuracy SCISSOR (Ge and Mooney, 2005) 72.3 KRISP (Kate and Mooney, 2006) 71.7 WASP (Wong and Mooney, 2006) 74.8 λ -WASP (Wong and Mooney, 2007) 86.6 LNLZ08 (Lu et al., 2008) 81.8 ZC05 (Zettlemoyer and Collins, 2”
Learning Language Games through Interaction (2016, neutral): “For example, if x = ‘enlever tout’ and z = remove(all()), then features include: (‘enlever’,all) (‘tout’,all) (‘enlever’,remove) (‘tout’,remove) (‘enlever’, (remove, 1,all)) (‘tout’, (remove, 1,all)) Note that we do not model an explicit alignment or derivation compositionally connecting the utteran”
Towards a Visual Turing Challenge (2014, background): “Recently we witness a tremendous progress in the machine perception [1, 2, 3, 4, 5, 6, 7, 8] and in the language understanding [9, 10, 11, 12, 13] tasks.”