Papers with unsupervised Chinese cross-domain segmenting

1 papers
Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks (2021.findings-emnlp)

Copied to clipboard

Challenge: Chinese has no word delimiter or inflection that can indicate segment boundaries or word semantics, increasing the difficulty of segmenting and labeling tasks.
Approach: They propose a paradigm based on attention augmentation to introduce crucial cross-domain knowledge via a translation system into Chinese model.
Outcome: The proposed model significantly advances the state-of-the-art results of Chinese cross-domain segmenting and labeling tasks.

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