Discriminative Reranking for Semantic Parsing

By Ruifang Ge, Raymond J. Mooney. 2006

59 citations recorded by the source corpus.

Semantic parsing is the task of mapping natural language sentences to complete formal meaning representations. The performance of semantic parsing can be potentially improved by using discriminative reranking, which explores arbitrary global features. In this paper, we investigate discriminative reranking upon a baseline semantic parser, SCISSOR, where the composition of meaning representations is guided by syntax. We examine if features used for syntactic parsing can be adapted for semantic parsing by creating similar semantic features based on the mapping between syntax and semantics. We report experimental results on two real applications, an interpreter for coaching instructions in robotic soccer and a natural-language database interface. The results show that reranking can improve the performance on the coaching interpreter, but not on the database interface.

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, 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 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.”
Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification (2010, methodology): “Examples include an early statistical method for learning to ﬁll slot-value representations (Miller et al., 1996) and a more recent approach for recovering semantic parse trees (Ge & Mooney, 2006).”
Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae (2014, background): “Genesereth and Kao [2013], and for an introduction targeted at linguists, see Gamut [1991].”
Learning a Compositional Semantic Parser using an Existing Syntactic Parser (2009, background): “Reranking could also potentially improve the results (Ge and Mooney, 2006; Lu et al., 2008).”
Solving Geometry Problems: Combining Text and Diagram Interpretation (2015, background): “Semantic parsing is an important area of NLP research (Zettlemoyer and Collins, 2005; Ge and Mooney, 2006; Flanigan et al., 2014; Eisenstein et al., 2009; Kate and Mooney, 2007; Goldwasser and Roth, 2011; Poon and Domingos, 2009; Berant and Liang, 2014; Kwiatkowski et al., 2013; Reddy et al., 2014).”
Global Reasoning over Database Structures for Text-to-SQL Parsing (2019, methodology): “To overcome this, we separately train a discriminative model (Collins and Koo, 2005; Ge and Mooney, 2006; Lu et al., 2008; Fried et al., 2017) to re-rank the top-K queries in the decoder’s output beam.”
Online Learning of Relaxed CCG Grammars for Parsing to Logical Form (2007, methodology): “, 1997; Ramaswamy and Kleindienst, 2000; Wong and Mooney, 2006), parsing techniques (Miller et al., 1996; Ge and Mooney, 2006), techniques that use inductive logic programming (Zelle and Mooney, 1996; Thompson and Mooney, 2002; Tang and Mooney, 2000; Kate et al.”
RefSum: Refactoring Neural Summarization (2021, methodology): “…used across different NLP tasks, such as constituency parsing (Collins and Koo, 2005; Huang, 2008), dependency parsing (Zhou et al., 2016; Do and Rehbein, 2020), semantic parsing (Ge and Mooney, 2006; Yin and Neubig, 2019), machine translation (Shen et al., 2004; Mizumoto and Matsumoto, 2016).”
Bootstrapping Semantic Parsers from Conversations (2011, background): “, 2010), parsing (Ruifang and Mooney, 2006; Lu et al., 2008), inductive logic programming (Zelle and Mooney, 1996; Thompson and Mooney, 2003; Tang and Mooney, 2000), probabilistic push-down automata (He and Young, 2005; 2006) and ideas from support vector machines and string kernels (Kate and Mooney”
Multi-Resolution Language Grounding with Weak Supervision (2014, background): “Early semantic parsing work made use of fully supervised training (Zettlemoyer and Collins, 2005; Ge and Mooney, 2006; Snyder and Barzilay, 2007), but more recent work has focused on reducing the amount of supervision required (Artzi and Zettlemoyer, 2013).”
Lexical Generalization in CCG Grammar Induction for Semantic Parsing (2011, methodology): “…translation techniques (Papineni et al., 1997; Ramaswamy and Kleindienst, 2000; Wong and Mooney, 2006), parsing models (Miller et al., 1996; Ge and Mooney, 2006; Lu et al., 2008), inductive logic programming algorithms (Zelle and Mooney, 1996; Thompson and Mooney, 2002; Tang and Mooney, 2000),…”
Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems (2016, methodology): “Our algo-rithm is also inﬂuenced by the discriminative re-ranking algorithms (Collins, 2000; Ge and Mooney, 2006; Charniak and Johnson, 2005) and models for learning from intractable supervision (Steinhardt and Liang, 2015).”
Semantic Understanding of Professional Soccer Commentaries (2012, background): “Some researchers use full supervision in general and controlled domains [Zettlemoyer and Collins, 2005; Ge and Mooney, 2006; Snyder and Barzilay, 2007] .”