paper-with-me

홈 › Papers

Learning Algebraic Recombination for Compositional Generalization

2021-07-14 · Findings (ACL) 2021 8 · Chenyao Liu, Shengnan An, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng, Dongmei Zhang

Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynamically recombining structured expressions in a recursive manner. However, most previous studies mainly concentrate on recombining lexical units, which is an important but not sufficient part of algebraic recombination. In this paper, we propose LeAR, an end-to-end neural model to learn algebraic recombination for compositional generalization. The key insight is to model the semantic parsing task as a homomorphism between a latent syntactic algebra and a semantic algebra, thus encouraging algebraic recombination. Specifically, we learn two modules jointly: a Composer for producing latent syntax, and an Interpreter for assigning semantic operations. Experiments on two realistic and comprehensive compositional generalization benchmarks demonstrate the effectiveness of our model. The source code is publicly available at https://github.com/microsoft/ContextualSP.

📄 PDF Abstract BibTeX arXiv:2107.06516

Code (2)

microsoft/ContextualSP 공식 구현 pytorch
thousfeet/lear pytorch

Tasks

Semantic Parsing

Similar Papers 제목 키워드 기반

Improving Compositional Generalization with Latent Structure and Data Augmentation

2021-12-14 · NAACL 2022 7 · Linlu Qiu, Peter Shaw, Panupong Pasupat, Paweł Krzysztof Nowak 외

Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has transferred some prior knowledge about c…

Data AugmentationDiagnosticSemantic Parsing

Toward Compositional Generalization in Object-Oriented World Modeling

2022-04-28 · Linfeng Zhao, Lingzhi Kong, Robin Walters, Lawson L. S. Wong

Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modelin…

Decision MakingObjectreinforcement-learningReinforcement Learning (RL)

Learning to Recombine and Resample Data for Compositional Generalization

2020-10-08 · ICLR 2021 1 · Ekin Akyürek, Afra Feyza Akyürek, Jacob Andreas

Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training dat…

Data AugmentationInstruction FollowingMorphological Analysis

Linguistic generalization and compositionality in modern artificial neural networks

2019-03-30 · Marco Baroni

In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalizat…

Systematic Generalization

Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks

2021-11-01 · EMNLP 2021 11 · Yichen Jiang, Mohit Bansal

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…