Coarse-to-Fine Decoding for Neural Semantic Parsing

By Li Dong, Mirella Lapata. 2018

407 citations recorded by the source corpus.

Semantic parsing aims at mapping natural language utterances into structured meaning representations. In this work, we propose a structure-aware neural architecture which decomposes the semantic parsing process into two stages. Given an input utterance, we first generate a rough sketch of its meaning, where low-level information (such as variable names and arguments) is glossed over. Then, we fill in missing details by taking into account the natural language input and the sketch itself. Experimental results on four datasets characteristic of different domains and meaning representations show that our approach consistently improves performance, achieving competitive results despite the use of relatively simple decoders.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “Semantic Parsing Similarly, recent approaches to the semantic parsing WikiSQL dataset have made use of structured approaches that move from coarse sketches of the input to fine-grained structured outputs (Dong and Lapata, 2018), direclty employing a type system (Yu et al.”
SPoC: Search-based Pseudocode to Code (2019, background): “Previous work on executable semantic parsing mainly focuses on translating short text descriptions to a one-line program [42, 35, 43, 44, 21, 8], and while recent work explored generating longer programs from text descriptions [22, 40, 29, 15, 16, 14], these programs are mostly evaluated on…”
A Discrete Hard EM Approach for Weakly Supervised Question Answering (2019, neutral): “…et al., 2019) 74.9 74.8 MML 70.6 70.5 Ours 84.4 83.9 Fully-supervised setting SQLNet (Xu et al., 2018) 69.8 68.0 TypeSQL (Yu et al., 2018b) 74.5 73.5 Coarse2Fine (Dong and Lapata, 2018) 79.0 78.5 SQLova (Hwang et al., 2019) 87.2 86.2 X-SQL (He et al., 2019) 89.5 88.7 Table 4: Results on W IKI SQL.”
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (2018, background): “These datasets have been studied for decades in both the NLP community (Warren and Pereira, 1982; Popescu et al., 2003b, 2004; Li et al., 2006; Giordani and Moschitti, 2012; Wang et al., 2017; Iyer et al., 2017; Zhong et al., 2017; Xu et al., 2017; Yu et al., 2018; Huang et al., 2018; Wang et al., 2”
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, methodology): “To evaluate the performance of continual semantic parsing, we report accuracy of exactly matched LFs as in (Dong and Lapata, 2018).”
Structural Language Models of Code (2019, background): “While this distinction between encoder and decoder types might be necessary for semantic parsing (Rabinovich et al., 2017; Dong & Lapata, 2018), NL → code (Yin & Neubig, 2017) and code → NL (Alon et al., 2019a; Fernandes et al., 2019) tasks because of the different modalities of the input and the…”
Robust Text-to-SQL Generation with Execution-Guided Decoding (2018, methodology): “A large number of subsequent neural semantic parsing works included an evaluation on WikiSQL (Xu, Liu, and Song 2017; Huang et al. 2018; Yu et al. 2018; Wang et al. 2018; Dong and Lapata 2018).”
Retrieval-Based Neural Code Generation (2018, background): “Another close work is Dong and Lapata (2018), which uses a two-staged structure-aware neural architecture.”
Synthesizing Environment-Aware Activities via Activity Sketches (2019, neutral): “A recent body of work has developed neural approaches to program generation using user-provided examples [8, 4], visual demonstrations [17], and descriptions [6].”
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer (2021, background): “3940 ments in syntactic parsing (Charniak and Johnson, 2005), semantic parsing (Dong and Lapata, 2018), and NER (Choi et al.”
Benchmarking Meaning Representations in Neural Semantic Parsing (2020, background): “…paper, we focus on grounded semantic parsing, where meaning representations are grounded to specific knowl- of neural networks techniques, significant improvements have been made in semantic parsing performance (Jia and Liang, 2016; Yin and Neubig, 2017; Dong and Lapata, 2018; Shaw et al., 2019).”
A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization (2019, methodology): “Instead of using pointer network for inferring the where condition values, we train for inferring the start and the end positions of the utterance, following (Dong and Lapata, 2018).”
Natural language to SQL: Where are we today? (2020, methodology): “For example, the studies in the natural language community [22, 44, 53, 46, 21, 24] exclude comparisons with [25, 35] from the database community.”
SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models (2022, background): “Generally, one way to improve compositional generalizability is to incorporate inductive biases directly to models through moduler models (Dong and Lapata, 2018), symbolic-neural machines (Chen et al.”
SParC: Cross-Domain Semantic Parsing in Context (2019, background): “Recently, an increasing number of neural approaches (Zhong et al., 2017; Xu et al., 2017; Yu et al., 2018a; Dong and Lapata, 2018; Yu et al., 2018b) have started to use large and cross-domain text-to-SQL datasets such as WikiSQL (Zhong et al., 2017) and Spider (Yu et al., 2018c).”
A Survey on Semantic Parsing (2018, methodology): “Similar methods to generate intermediate templates have been employed in [Dong and Lapata, 2018] where a sketch of the final output is used for easier decoding.”