On graph-based reentrancy-free semantic parsing
Not on the map. Why?
Abstract (arXiv)
We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on Geoquery, Scan and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 34 of its 90 references that are in the map. First posted on arXiv 15 Feb 2023.
Builds on
34 of 90 references.
References · 34
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2021Convex optimizationcited by 2,515
- 2018Deep contextualized word representationscited by 2,290
- 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 284
- 2016Language to Logical Form with Neural Attentioncited by 158
- 2019Good-Enough Compositional Data Augmentationcited by 158
- 2018Improving Text-to-SQL Evaluation Methodologycited by 135
22 more
- 2019Learning with Fenchel-Young Lossescited by 119
- 2016Data Recombination for Neural Semantic Parsingcited by 111
- 2015On the Global Linear Convergence of Frank-Wolfe Optimization Variantscited by 77
- 2020Span-based Semantic Parsing for Compositional Generalizationcited by 77
- 2014Grammar as a Foreign Languagecited by 70
- 2020Learning to Recombine and Resample Data for Compositional Generalizationcited by 65
- 2019CLOSURE: Assessing Systematic Generalization of CLEVR Modelscited by 63
- 2017A Minimal Span-Based Neural Constituency Parsercited by 59
- 2018Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networkscited by 51
- 2018Simpler but More Accurate Semantic Dependency Parsingcited by 46
- 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
- 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
- 2020Compositional Generalization via Semantic Taggingcited by 32
- 2019Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsingcited by 24
- 2021Structured Reordering for Modeling Latent Alignments in Sequence Transductioncited by 17
- 2022SUBS: Subtree Substitution for Compositional Semantic Parsingcited by 16
- 2018A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programmingcited by 14
- 2016Dependency Parsing as Head Selectioncited by 13
- 2020Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n^6) down to O(n^3)cited by 11
- 2021LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsingcited by 7
- 2015Parsing as Reductioncited by 6
- 2023On the inconsistency of separable losses for structured predictioncited by 2
Built on by
Citing papers per year: 2023: 2.
2 papers.