Sequence-based Structured Prediction for Semantic Parsing

By Chunyang Xiao, Marc Dymetman, Claire Gardent. 2016

122 citations recorded by the source corpus.

We propose an approach for semantic parsing that uses a recurrent neural network to map a natural language question into a logical form representation of a KB query. Building on recent work by (Wang et al., 2015), the interpretable logical forms, which are structured objects obeying certain constraints, are enumerated by an underlying grammar and are paired with their canonical realizations. In order to use sequence prediction, we need to sequentialize these logical forms. We compare three sequentializations: a direct linearization of the logical form, a linearization of the associated canonical realization, and a sequence consisting of derivation steps relative to the underlying grammar. We also show how grammatical constraints on the derivation sequence can easily be integrated inside the RNN-based sequential predictor. Our experiments show important improvements over previous results for the same dataset, and also demonstrate the advantage of incorporating the grammatical constraints.

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

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].”
FVQA: Fact-Based Visual Question Answering (2016, background): “increasing interest in the problem of natural language question answering over structured KBs (referred to as KB-QA). KBQA approaches can be divided into two categories: semantic parsing methods [37]–[47] that try to translate questions into accurate logical expressions and then map to KB queries, a”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, background): “Examples include tree decoders (Dong and Lapata, 2016; Alvarez-Melis and Jaakkola, 2017), decoders constrained by a grammar model (Xiao et al., 2016; Yin and Neu-big, 2017; Krishnamurthy et al., 2017), or modular decoders which use syntax to dynamically compose various submodels (Rabinovich et al.,…”
Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing (2019, methodology): “One direction is to employ sequence-to-sequence model by modeling semantic parsing as a sentence to logical form translation problem (Dong and Lapata, 2016; Jia and Liang, 2016; Ling et al., 2016; Xiao et al., 2016).”
A Survey on Semantic Parsing (2018, methodology): “Xiao et al. [2016] similarly employ the grammar model as prior information so that the generation of derivation trees is constrained by the grammar.”
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing (2018, background): “While these models have a long history (Zelle and Mooney, 1996; Tang and Mooney, 2001), recent advances are largely attributed to the success of neural network models (Xiao et al., 2016; Ling et al., 2016; Dong and Lapata, 2016; Iyer et al., 2017; Zhong et al., 2017).”
Natural Language to Code Translation with Execution (2022, background): “…and conditioned text generation, there has been much work exploring natural language to code generation with end-to-end neural model architectures (Xiao et al., 2016; Ling et al., 2016; Rabinovich et al., 2017; Dong and Lapata, 2018; Suhr et al., 2018; Xu et al., 2020; Lachaux et al., 2021,…”
Structural Language Models of Code (2019, background): “One way to represent a partial tree is to linearize it according to the traversal order (Xiao et al., 2016); however, this creates artificially long distances between the current node at and ancestor nodes (e.”
Energy-Based Models for Code Generation under Compilability Constraints (2021, background): “This problem has inspired a large body of work on different fronts on injecting sequence-level priors by either directly optimizing sequence-level features (Ranzato et al., 2016) or through fusion with grammars and automata (Xiao et al., 2016).”
LEVER: Learning to Verify Language-to-Code Generation with Execution (2023, unknown): “…including rule-based systems (Woods, 1973; Templeton & Burger, 1983), structured prediction (Zelle & Mooney, 1996; Zettlemoyer & Collins, 2005; Gulwani & Marron, 2014) and deep learning (Xiao et al., 2016; Dong & Lapata, 2016; Rabinovich et al., 2017; Zhong et al., 2017; Lin et al., 2017).”
Structural Language Models for Any-Code Generation (2019, background): “One way to represent a partial tree is to linearize it according to the traversal order (Xiao et al., 2016); however, this could create artiﬁcially long distances between the current node a t and ancestor nodes (e.g., the root a 0 ).”
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (2018, methodology): “A lot of Seq2Seq models have also been employed for semantic parsing (Xiao et al., 2016; Dong and Lapata, 2016; Jia and Liang, 2016), where a sentence is parsed by translating it to linearized logical form using RNN models.”
Discourse Representation Structure Parsing (2018, background): “Dong and Lapata (2016) and Alvarez-Melis and Jaakkola (2017) generate trees in a top-down fashion, while in other work (Xiao et al., 2016; Krishnamurthy et al., 2017) the decoder generates from a grammar that guarantees that predicted logical forms are well-typed.”
TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation (2018, background): “To alleviate this issue, there have been recent efforts in neural semantic parsing with general-purpose grammar models (Xiao et al., 2016; Dong and Lapata, 2018).”
Learning to Recombine and Resample Data for Compositional Generalization (2020, background): “Previous attempts to address this and related shortcomings in neural models have focused on explicitly encouraging rule-like behavior by e.g. modeling data with symbolic grammars (Jia & Liang, 2016; Xiao et al., 2016; Cai et al., 2017) or applying rule-based data augmentation (Andreas, 2020).”
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries (2020, background): “…pairing natu-ral utterances with logical forms (Dahl et al., 1994; Wang et al., 2015; Zhong et al., 2017; Yu et al., 2018, inter alia ) has enabled signiﬁcant progress on supervised approaches to semantic parsing (Jia and Liang, 2016; Xiao et al., 2016; Dong and Lapata, 2016, 2018, inter alia ).”
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.”