# Compositional Generalization Requires Compositional Parsers

arXiv: https://arxiv.org/abs/2202.11937 · HTML: https://mlsanity.com/paper/2202.11937/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers](https://mlsanity.com/paper/2108.12284/) (2021)
- [Span-based Semantic Parsing for Compositional Generalization](https://mlsanity.com/paper/2009.06040/) (2020)
- [Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks](https://mlsanity.com/paper/2001.03632/) (2020)
- [Meta-Learning to Compositionally Generalize](https://mlsanity.com/paper/2106.04252/) (2021)
- [Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations](https://mlsanity.com/paper/1603.04351/) (2016)
- [Deep RNNs Encode Soft Hierarchical Syntax](https://mlsanity.com/paper/1805.04218/) (2018)
- [Learning Algebraic Recombination for Compositional Generalization](https://mlsanity.com/paper/2107.06516/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Lexicon Learning for Few-Shot Neural Sequence Modeling](https://mlsanity.com/paper/2106.03993/) (2021)
- [Are Pre-trained Convolutions Better than Pre-trained Transformers?](https://mlsanity.com/paper/2105.03322/) (2021)
- [AMR Dependency Parsing with a Typed Semantic Algebra](https://mlsanity.com/paper/1805.11465/) (2018)
- [Compositional Semantic Parsing Across Graphbanks](https://mlsanity.com/paper/1906.11746/) (2019)
- [Modeling Source Syntax for Neural Machine Translation](https://mlsanity.com/paper/1705.01020/) (2017)
- [Improving Compositional Generalization in Classification Tasks via Structure Annotations](https://mlsanity.com/paper/2106.10434/) (2021)
- [Fast semantic parsing with well-typedness guarantees](https://mlsanity.com/paper/2009.07365/) (2020)
- [Compositional generalization in semantic parsing with pretrained transformers](https://mlsanity.com/paper/2109.15101/) (2021)
- [Learning compositional structures for semantic graph parsing](https://mlsanity.com/paper/2106.04398/) (2021)

## Built on by (most cited first, 2 of 2)

- [Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models](https://mlsanity.com/paper/2212.10769/) (2022)
- [Hierarchical Phrase-based Sequence-to-Sequence Learning](https://mlsanity.com/paper/2211.07906/) (2022)

## Abstract (arXiv)

A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences. We present a systematic comparison of sequence-to-sequence models and models guided by compositional principles on the recent COGS corpus (Kim and Linzen, 2020). Though seq2seq models can perform well on lexical tasks, they perform with near-zero accuracy on structural generalization tasks that require novel syntactic structures; this holds true even when they are trained to predict syntax instead of semantics. In contrast, compositional models achieve near-perfect accuracy on structural generalization; we present new results confirming this from the AM parser (Groschwitz et al., 2021). Our findings show structural generalization is a key measure of compositional generalization and requires models that are aware of complex structure.