Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

Zhong, Tianqi, Li, Zhaoyi, Wang, Quan, Song, Linqi, Wei, Ying, Lian, Defu, Mao, Zhendong

arXiv.org Artificial Intelligence 

Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods. Nonetheless, a comprehensive compositional generalization evaluation benchmark of MCTG is still lacking. We propose CompMCTG, a benchmark encompassing diverse multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol, to holistically evaluate the compositional generalization of MCTG approaches. We observe that existing MCTG works generally confront a noticeable performance drop in compositional testing. To mitigate this issue, we introduce Meta-MCTG, a training framework incorporating meta-learning, where we enable models to learn how to generalize by simulating compositional generalization scenarios in the training phase. We demonstrate the effectiveness of Meta-MCTG through achieving obvious improvement (by at most 3.64%) for compositional testing performance in 94.4% cases.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found