Lexical Generalization in CCG Grammar Induction for Semantic Parsing

By Tom Kwiatkowski, Luke S. Zettlemoyer, Sharon Goldwater, Mark Steedman. 2011

239 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): “While limited-domain semantic parsers are able to learn the lexicon from per-example supervision (Kwiatkowski et al., 2011; Liang et al., 2011), at large scale they have inadequate coverage (Cai and Yates, 2013).”
SPoC: Search-based Pseudocode to Code (2019, background): “Partial parses can be constructed by combining smaller partial parses in a bottom-up fashion [58, 28, 27], adding the next token to the sequence [10, 22, 51, 11, 25], or creating a new node in a tree structure [10, 26, 54, 39].”
Learning with Latent Language (2017, neutral): “If these were not available it would be straightforward to employ an automatic template induction system (Kwiatkowski et al., 2011)”
Learning Dependency-Based Compositional Semantics (2011, methodology): “…(Miller et al. 1996; Zelle and Mooney 1996; Tang andMooney 2001; Ge andMooney 2005; Kate, Wong, and Mooney 2005; Zettlemoyer and Collins 2005; Kate andMooney 2006;Wong andMooney 2006; Kate and Mooney 2007; Wong and Mooney 2007; Zettlemoyer and Collins 2007; Kwiatkowski et al. 2010, 2011).”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, methodology): “Generalizing previous work (Kwiatkowski et al., 2011), we allow templates that abstract subsets of the constants in a lexical item.”
A Joint Model of Language and Perception for Grounded Attribute Learning (2012, methodology): “In this work, we initialize our parse model using the standard FUBL approach, followed by automatically inducing lexemes paired with new visual attributes not present in the initial training set, as we will see in the next section.”
Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, methodology): “Recently, algorithms have been developed to learn such parsers for many applications, including question answering (QA) (Kwiatkowski et al., 2011; Liang et al., 2011), relation extraction (Krishnamurthy and Mitchell, 2012), robot control (Matuszek et al.”
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”
Information Extraction over Structured Data: Question Answering with Freebase (2014, background): “…this via the bridge of various intermediate representations, including combinatory categorial grammar (Zettlemoyer and Collins, 2005, 2007, 2009; Kwiatkowski et al., 2010, 2011, 2013), synchronous context-free grammars (Wong and Mooney, 2007), dependency trees (Liang et al., 2011; Berant et…”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, background): “Meaning representations in these datasets are based on λ-calculus (Kwiatkowski et al., 2011).”
Bringing Machine Learning and Compositional Semantics Together (2015, background): “The long-term trends for this division of labor are hard to forecast, but we expect to increasingly see models that are able to learn these more abstract corners of the lexicon as well, since defining richer views of the lexicon has been a major focus of recent work (Wong & Mooney 2007; Kwiatkowski ”
Grounded Unsupervised Semantic Parsing (2013, background): “Despite these challenges, GUSP attains an accuracy of 84% in end-to-end question answering, effectively tying with the state-of-the-art supervised approaches (85% by Zettle-moyer & Collins (2007), 83% by Kwiatkowski et al. (2011)).”