# Cooperative Learning of Disjoint Syntax and Semantics

arXiv: https://arxiv.org/abs/1902.09393 · HTML: https://mlsanity.com/paper/1902.09393/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 27 of 27)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization](https://mlsanity.com/paper/2110.07732/) (2021)
- [Learning Algebraic Recombination for Compositional Generalization](https://mlsanity.com/paper/2107.06516/) (2021)
- [Substructure Substitution: Structured Data Augmentation for NLP](https://mlsanity.com/paper/2101.00411/) (2021)
- [D-Separation for Causal Self-Explanation](https://mlsanity.com/paper/2309.13391/) (2023)
- [Structured Reordering for Modeling Latent Alignments in Sequence Transduction](https://mlsanity.com/paper/2106.03257/) (2021)
- [Modeling Hierarchical Structures with Continuous Recursive Neural Networks](https://mlsanity.com/paper/2106.06038/) (2021)
- [Enhancing the Rationale-Input Alignment for Self-explaining Rationalization](https://mlsanity.com/paper/2312.04103/) (2023)
- [Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint](https://mlsanity.com/paper/2305.13599/) (2023)
- [Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces](https://mlsanity.com/paper/2110.15072/) (2021)
- [Beam Tree Recursive Cells](https://mlsanity.com/paper/2305.19999/) (2023)
- [Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization](https://mlsanity.com/paper/2503.06202/) (2025)
- [Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability](https://mlsanity.com/paper/2311.04449/) (2023)
- [Investigating Recurrent Transformers with Dynamic Halt](https://mlsanity.com/paper/2402.00976/) (2024)
- [Learning Syntax from Naturally-Occurring Bracketings](https://mlsanity.com/paper/2104.13933/) (2021)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Learning compositional structures for semantic graph parsing](https://mlsanity.com/paper/2106.04398/) (2021)
- [Banyan: Improved Representation Learning with Explicit Structure](https://mlsanity.com/paper/2407.17771/) (2024)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [SynJax: Structured Probability Distributions for JAX](https://mlsanity.com/paper/2308.03291/) (2023)
- [Unsupervised Learning of Explainable Parse Trees for Improved Generalisation](https://mlsanity.com/paper/2104.04998/) (2021)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)
- [FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding](https://mlsanity.com/paper/2111.14031/) (2021)
- [Spontaneous Emerging Preference in Two-tower Language Model](https://mlsanity.com/paper/2210.07041/) (2022)
- [Ordered Memory Baselines](https://mlsanity.com/paper/2302.06451/) (2023)
- [Interpreting Sentiment Composition with Latent Semantic Tree](https://mlsanity.com/paper/2308.16588/) (2023)

## Abstract (arXiv)

There has been considerable attention devoted to models that learn to jointly infer an expression's syntactic structure and its semantics. Yet, citetNangiaB18 has recently shown that the current best systems fail to learn the correct parsing strategy on mathematical expressions generated from a simple context-free grammar. In this work, we present a recursive model inspired by newciteChoiYL18 that reaches near perfect accuracy on this task. Our model is composed of two separated modules for syntax and semantics. They are cooperatively trained with standard continuous and discrete optimization schemes. Our model does not require any linguistic structure for supervision and its recursive nature allows for out-of-domain generalization with little loss in performance. Additionally, our approach performs competitively on several natural language tasks, such as Natural Language Inference or Sentiment Analysis.