Lune

EMNLP Findings2021

Weakly Supervised Semantic Parsing by Learning from Mistakes

Jiaqi Guo, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Abstract

Weakly supervised semantic parsing (WSP) aims at training a parser via utterancedenotation pairs. This task is challenging because it requires (1) searching consistent logical forms in a huge space; and (2) dealing with spurious logical forms. In this work, we propose Learning from Mistakes (LFM), a simple yet effective learning framework for WSP. LFM utilizes the mistakes made by a parser during searching, i.e., generating logical forms that do not execute to correct denotations, for tackling the two challenges. In a nutshell, LFM additionally trains a parser using utterance-logical form pairs created from mistakes, which can quickly bootstrap the parser to search consistent logical forms. Also, it can motivate the parser to learn the correct mapping between utterances and logical forms, thus dealing with the spuriousness of logical forms. We evaluate LFM on WikiTableQuestions, WikiSQL, and TabFact in the WSP setting. The parser trained with LFM outperforms the previous state-of-the-art semantic parsing approaches on the three datasets. Also, we find that LFM can substantially reduce the need for labeled data. Using only 10% of utterancedenotation pairs, the parser achieves 84.2 denotation accuracy on WikiSQL, which is competitive with the previous state-of-the-art approaches using 100% labeled data.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Understanding tables with intermediate pre-training cites TabFact: A Large-scale Dataset for Table-based Fact Verification
  • Binding Language Models in Symbolic Languages cites TabFact: A Large-scale Dataset for Table-based Fact Verification
  • Binding Language Models in Symbolic Languages cites Understanding tables with intermediate pre-training
  • Binding Language Models in Symbolic Languages cites TAPEX: Table Pre-training via Learning a Neural SQL Executor
  • Binding Language Models in Symbolic Languages cites TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
  • Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing cites TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
  • TAPEX: Table Pre-training via Learning a Neural SQL Executor cites TabFact: A Large-scale Dataset for Table-based Fact Verification
  • TAPEX: Table Pre-training via Learning a Neural SQL Executor cites Understanding tables with intermediate pre-training
  • TAPEX: Table Pre-training via Learning a Neural SQL Executor cites TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
  • TAPEX: Table Pre-training via Learning a Neural SQL Executor cites Grounded Adaptation for Zero-shot Executable Semantic Parsing
  • TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data cites TabFact: A Large-scale Dataset for Table-based Fact Verification
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. TAPEX: Table Pre-training via Learning a Neural SQL ExecutorQian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi et al.ICLR 2022 · 347 citations
  2. Binding Language Models in Symbolic LanguagesZhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li et al.ICLR 2023 · 38 citations

Builds on9

  1. TabFact: A Large-scale Dataset for Table-based Fact VerificationWenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang et al.ICLR 2020 · 674 citations
  2. TaBERT: Pretraining for Joint Understanding of Textual and Tabular DataPengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian RiedelACL 2020 · 417 citations
  3. Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic ParsingXi Victoria Lin, Richard Socher, Caiming XiongEMNLP Findings 2020 · 186 citations
  4. Understanding tables with intermediate pre-trainingJulian Martin Eisenschlos, Syrine Krichene, Thomas MüllerEMNLP Findings 2020 · 88 citations
  5. Grounded Adaptation for Zero-shot Executable Semantic ParsingVictor Zhong, Mike Lewis, Sida I. Wang, Luke ZettlemoyerEMNLP 2020 · 85 citations

Related papers

  1. Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-LearningYibo Sun, Duyu Tang, Nan Duan, Yeyun Gong et al.AAAI 2020 · 25 citations
  2. Merging Weak and Active Supervision for Semantic ParsingAnsong Ni, Pengcheng Yin, Graham NeubigAAAI 2020 · 17 citations
  3. Weakly Supervised Semantic Parsing with Execution-based Spurious Program FilteringKang-il Lee, Segwang Kim, Kyomin JungEMNLP 2023
  4. TaPas: Weakly Supervised Table Parsing via Pre-trainingJonathan Herzig, Pawel Krzysztof Nowak, Thomas Müller, Francesco Piccinno et al.ACL 2020 · 19 citations
  5. Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge GraphsPierre Marion, Pawel Krzysztof Nowak, Francesco PiccinnoEMNLP 2021 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines