mlsanityData to 7 Oct 2026

SUBS: Subtree Substitution for Compositional Semantic Parsing

arXiv 2205.01538 ↗First posted 3 May 2022cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Although sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate this problem. However, prior work only leveraged superficial grammar or rules for data augmentation, which resulted in limited improvement. We propose to use subtree substitution for compositional data augmentation, where we consider subtrees with similar semantic functions as exchangeable. Our experiments showed that such augmented data led to significantly better performance on SCAN and GeoQuery, and reached new SOTA on compositional split of GeoQuery.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 3 May 2022.

Builds on

18 of 24 references.

References · 18

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  3. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  4. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  5. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  6. 2019Good-Enough Compositional Data Augmentationcited by 158
  7. 2018Improving Text-to-SQL Evaluation Methodologycited by 133
  8. 2016Data Recombination for Neural Semantic Parsingcited by 111
  9. 2019Compositional generalization through meta sequence-to-sequence learningcited by 98
  10. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
  11. 2020Compositional Generalization via Neural-Symbolic Stack Machinescited by 80
  12. 2020Span-based Semantic Parsing for Compositional Generalizationcited by 77
6 more
  1. 2020Understanding tables with intermediate pre-trainingcited by 68
  2. 2020Learning to Recombine and Resample Data for Compositional Generalizationcited by 65
  3. 2018Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networkscited by 51
  4. 2019Data Augmentation via Dependency Tree Morphing for Low-Resource Languagescited by 45
  5. 2020Compositional Generalization via Semantic Taggingcited by 32
  6. 2021Substructure Substitution: Structured Data Augmentation for NLPcited by 25

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 7; 2024: 1; 2025: 2.

16 papers.

Sort:

  1. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  2. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  3. 2023Learning to Substitute Spans towards Improving Compositional Generalizationcited by 8
  4. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  5. 2023Structural generalization in COGS: Supertagging is (almost) all you needcited by 4
  6. 2024Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformationscited by 4
  7. 2022Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsingcited by 3
  8. 2023Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalizationcited by 3
  9. 2022On the Security Vulnerabilities of Text-to-SQL Modelscited by 2
  10. 2023On graph-based reentrancy-free semantic parsingcited by 2
  11. 2023Layer-wise Representation Fusion for Compositional Generalizationcited by 2
  12. 2023Efficient Model-Agnostic Multi-Group Equivariant Networkscited by 1
4 more
  1. 2025Learning to Substitute Components for Compositional Generalizationcited by 1
  2. 2022A Short Survey of Systematic Generalizationcited by 0
  3. 2023Semantic Parsing in Limited Resource Conditionscited by 0
  4. 2025Data Distributional Properties As Inductive Bias for Systematic Generalizationcited by 0