A Statistical Semantic Parser that Integrates Syntax and Semantics

By Ruifang Ge, Raymond J. Mooney. 2005

203 citations recorded by the source corpus.

We introduce a learning semantic parser, Scissor, that maps natural-language sentences to a detailed, formal, meaning-representation language. It first uses an integrated statistical parser to produce a semantically augmented parse tree, in which each non-terminal node has both a syntactic and a semantic label. A compositional-semantics procedure is then used to map the augmented parse tree into a final meaning representation. We evaluate the system in two domains, a natural-language database interface and an interpreter for coaching instructions in robotic soccer. We present experimental results demonstrating that Scissor produces more accurate semantic representations than several previous approaches.

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

Parsing Algebraic Word Problems into Equations (2015, methodology): “Specifically, the recursive nature of our representation allows us to decompose the likelihood function p(t, w) into local scoring functions for each in- 3Inspired by Semantically Augmented Parse Trees (Ge and Mooney, 2005) adapted to equational logic. ternal node of t followed by scoring the root n”
Learning Dependency-Based Compositional Semantics (2011, background): “In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. law.”
Learning Semantic Correspondences with Less Supervision (2009, background): “Recent work in learning semantics has focused on mapping sentences to meaning representations (e.g., some logical form) given aligned sentence/meaning pairs as training data (Ge and Mooney, 2005; Zettlemoyer and Collins, 2005; Zettlemoyer and Collins, 2007; Lu et al., 2008).”
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 for Semantic Parsing with Statistical Machine Translation (2006, methodology): “Other learning methods involve the use of fully-annotated augmented parse trees (Ge and Mooney, 2005) or prior knowledge of the NL syntax (Zettle-moyer and Collins, 2005) in training, and hence require extensive human efforts when porting to a new domain or language.”
Reading to Learn: Constructing Features from Semantic Abstracts (2009, methodology): “This paper draws on recent literature on extracting logical forms from surface text (Zettlemoyer and Collins, 2005; Ge and Mooney, 2005; Downey et al., 2005; Liang et al., 2009), interpreting language in the context of a domain (Chen and Mooney, 2008), and using an actionable domain to guide text…”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, background): “Some semantic-parser learners additionally require either syntactic annotations (Ge & Mooney, 2005) or prior syntactic knowledge of the target language (Ge & Mooney, 2009; Zettlemoyer & Collins, 2005, 2007).”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, background): “Various models have been proposed over the years to learn semantic parsers from natural language expressions paired with their meaning representations (Tang and Mooney, 2000; Ge and Mooney, 2005; Zettlemoyer and Collins, 2007; Wong and Mooney, 2007; Lu et al., 2008; Kwiatkowski et al., 2011; Andreas”
Efficient grounding of abstract spatial concepts for natural language interaction with robot platforms (2018, background): “Ge and Mooney [32] integrate semantic roles and derivations within a syntactic parsing framework to determine a statical parse representation that integrates both syntax and compositional semantics.”
Translating Questions to SQL Queries with Generative Parsers Discriminatively Reranked (2012, background): “Early work on semantic parsing (Tang and Mooney, 2001) required either the definition of rules and constrains in an ILP framework or manually produced meaning representations (Ge and Mooney, 2005; Wong and Mooney, 2006), which are costly to produce.”
Learning Language Semantics from Ambiguous Supervision (2007, background): “Recent research in semantic parsing has developed methods that learn to map sentences into complete formal meaning representations (MRs) by training on a corpus of sentences each annotated with its corresponding MR (Ge & Mooney 2005; Zettlemoyer & Collins 2005; Kate, Wong, & Mooney 2005).”
Semantic Parsing with Bayesian Tree Transducers (2012, background): “SCISSOR (Ge and Mooney, 2005) takes syntactic parses rather than NL strings and attempts to translate them into MR expressions.”
Generative Alignment and Semantic Parsing for Learning from Ambiguous Supervision (2010, background): “The conventional approach to learning semantic parsers (Zelle and Mooney, 1996; Ge and Mooney, 2005; Kate and Mooney, 2006; Zettle-moyer and Collins, 2007; Zettlemoyer and Collins, 2005; Wong and Mooney, 2007b; Lu et al., 2008) requires detailed supervision unambiguously pairing each sentence with…”
NLyze: interactive programming by natural language for spreadsheet data analysis and manipulation (2014, background): “Several approaches have been presented, namely: syntax directed [14], those that use parse trees [4], SVM driven [15], combinatory categorial grammars [18, 42, 43], and dependency-based semantics [23, 32] among others.”
Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases (2019, unknown): “Early approaches depended on grammars that were manually-speciﬁed [4] or learned from database-speciﬁc training examples [14], [35], making it difﬁcult to scale them across different database schemas.”
DataTone: Managing Ambiguity in Natural Language Interfaces for Data Visualization (2015, background): “The grammars improve by adding new examples [9, 12, 31, 39], but these methods depend on large, labeled training corpora that are difficult to obtain.”
Learning a Compositional Semantic Parser using an Existing Syntactic Parser (2009, methodology): “available): SCISSOR (Ge and Mooney, 2005), an integrated syntactic-semantic parser; KRISP (Kate and Mooney, 2006), an SVM-based parser using string kernels; WASP (Wong and Mooney, 2006; Wong and Mooney, 2007), a system based on synchronous grammars; Z&C (Zettlemoyer and Collins, 2007)(3), a probabil”
Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus (2007, methodology): “WASP algorithm compared to: (1) the original WASP algorithm which uses a functional query language (FunQL); (2) SCISSOR (Ge and Mooney, 2005), a fully-supervised, combined syntacticsemantic parsing algorithm which also uses FunQL; and (3) Zettlemoyer and Collins (2005) (Z&C), a CCG-based algorithm w”