Shengyuan Hou — accepted AI-conference papers

2024

Leveraging Grammar Induction for Language Understanding and Generation

Jushi Kai, Shengyuan Hou, Yusheng Huang, Zhouhan Lin

EMNLP 2024finding

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar induction method for language understanding and generation. We…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Syntax-guided Localized Self-attention by Constituency Syntactic Distance

Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang +2

EMNLP 2022finding

Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data. However, learning syntactic information from data is not necessary if we can leverage an external sy…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗