paper-with-me

홈 › Papers

Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

2020-07-01 · Ben Bogin, Sanjay Subramanian, Matt Gardner, Jonathan Berant

Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples, compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization for grounded question answering. On this challenging dataset, our model reaches an accuracy of 96.1%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.

📄 PDF Abstract BibTeX arXiv:2007.00266

Code (1)

benbogin/glt-grounded-latent-trees-qa 공식 구현 pytorch

Tasks

Inductive BiasQuestion AnsweringSystematic Generalization

Similar Papers 제목 키워드 기반

Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings

2023-10-28 · NeurIPS 2023 11

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized…

Improving Compositional Generalization with Self-Training for Data-to-Text Generation

2021-10-16 · ACL 2022 5 · Sanket Vaibhav Mehta, Jinfeng Rao, Yi Tay, Mihir Kale 외

Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible…

Data-to-Text GenerationText Generation

Improving Compositional Generalization with Self-Training for Data-to-Text Generation

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Data-to-text generation focuses on generating fluent natural language responses from structured meaning representations (MRs). Such representations are compositional and it is costly to collect responses for all possible…

Data-to-Text GenerationText Generation

Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning

2025-10-15 · Awni Altabaa, Siyu Chen, John Lafferty, Zhuoran Yang arxiv

Systematic, compositional generalization beyond the training distribution remains a core challenge in machine learning -- and a critical bottleneck for the emergent reasoning abilities of modern language models. This wor…

Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language

2022-10-02 · Zhenlin Xu, Marc Niethammer, Colin Raffel

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various un…

DisentanglementRepresentation Learning