← Search

Chengang Hu

2 accepted papers

2023

DiNeR: A Large Realistic Dataset for Evaluating Compositional Generalization

EMNLP 2023long main

Most of the existing compositional generalization datasets are synthetically-generated, resulting in a lack of natural language variation. While there have been recent attempts to introduce non-synthetic datasets for compositional generalization, they suffer from either limited data scale or a lack…

Cited by 0SourcecodeScholar
2022

Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario

EMNLP 2022main

People can acquire knowledge in an unsupervised manner by reading, and compose the knowledge to make novel combinations. In this paper, we investigate whether pretrained language models can perform compositional generalization in a realistic setting: recipe generation. We design the counterfactual r…