Papers by Yi-Ting Li

2 papers
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent Chinese word segmentation models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context.
Approach: They propose a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework.
Outcome: The proposed approach achieves state-of-the-art (SoTA) performance on six of the nine CWS benchmark datasets and out-of vocabulary (OOV) recalls for eight of nine.
Improved Unsupervised Chinese Word Segmentation Using Pre-trained Knowledge and Pseudo-labeling Transfer (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to unsupervised Chinese word segmentation require multiple inferences to perform word segmenting.
Approach: They propose a method that integrates the segmentation signal from an unsupervised language model to a pre-trained BERT classifier under a pseudo-labeling framework.
Outcome: The proposed method achieves state-of-the-art performance on the eight UCWS tasks while significantly reducing training time compared to previous approaches.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations