Transforming Dependency Structures to Logical Forms for Semantic Parsing

By Siva Reddy, Oscar Täckström, Michael Collins, Tom Kwiatkowski, Dipanjan Das, Mark Steedman, Mirella Lapata. 2016

172 citations recorded by the source corpus.

The strongly typed syntax of grammar formalisms such as CCG, TAG, LFG and HPSG offers a synchronous framework for deriving syntactic structures and semantic logical forms. In contrast—partly due to the lack of a strong type system—dependency structures are easy to annotate and have become a widely used form of syntactic analysis for many languages. However, the lack of a type system makes a formal mechanism for deriving logical forms from dependency structures challenging. We address this by introducing a robust system based on the lambda calculus for deriving neo-Davidsonian logical forms from dependency trees. These logical forms are then used for semantic parsing of natural language to Freebase. Experiments on the Free917 and Web-Questions datasets show that our representation is superior to the original dependency trees and that it outperforms a CCG-based representation on this task. Compared to prior work, we obtain the strongest result to date on Free917 and competitive results on WebQuestions.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

SPoC: Search-based Pseudocode to Code (2019, background): “While some semantic parsers operate by modifying the linguistic structure of the utterance [38, 40], most parsers construct the parse incrementally from scratch.”
Break It Down: A Question Understanding Benchmark (2020, background): “Domain-independent intermediate representations for semantic parsers were proposed by Kwiatkowski et al. (2013) and Reddy et al. (2016).”
FVQA: Fact-Based Visual Question Answering (2016, background): “KB-QA approaches can be divided into two categories: semantic parsing methods [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47] that try to translate questions into accurate logical expressions and then map to KB queries, and information retrieval methods [48], [49], [50], [51], [52],”
Statistical learning for semantic parsing: A survey (2019, methodology): “However, instead of using an external parser [74,75] or CCG grammars, CHENG17 induced intermediate representations in the form of predicate-argument structures from data with a transition-based approach.”
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem (2020, background): “The dependency parse tree not only represents various grammatical relationships be-tween pairs of text words, but also is shown to have an important role in transforming texts into logical forms (Reddy et al., 2016).”
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text (2021, methodology): “Semantic parsers (Reddy et al., 2016; Singh et al., 2020) are usually employed for converting texts to logical forms, and graph neural networks (Fang et al.”
Core techniques of question answering systems over knowledge bases: a survey (2017, unknown): “This is for example the case for Bor-des et al. 2015, Yang et al. 2014, Yavuz et al. 2016, STAGG (Yih et al. 2015) (Bast & Haussmann 2015) or Reddy et al. 2016.”
Learning to Paraphrase for Question Answering (2017, unknown): “We perform entity linking using the Freebasee/KG API on the original question (Reddy et al., 2016, 2017), and generate candidate Freebase subgraphs.”
Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering (2018, background): “There has been interest in the natural language processing community in answering questions based on knowledge bases (KBs) using either semantic parsing [37,38,39,40,41,42,43,44,45,46,47] or information retrieval [48,49,50,51,52,53,54] methods.”
Building a Neural Semantic Parser from a Domain Ontology (2018, unknown): “Following this direction, Dong and Lapata (2016) and Jia and Liang (2016) developed neural semantic parsers which treat semantic parsing as a sequence-to-sequence learning problem.”
Learning an Executable Neural Semantic Parser (2017, unknown): “The model—which can take, for example, the form of a support vector machine (Kate and Mooney 2006), a structured perceptron (Zettlemoyer and Collins 2007; Lu et al. 2008; Reddy, Lapata, and Steedman 2014; Reddy et al. 2016), or a log-linear model (Zettlemoyer and Collins 2005; Berant et al.”