Papers by William Shiyuan Wang

2 papers
Context and POS in Action: A Comparative Study of Chinese Homonym Disambiguation in Human and Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Ambiguity is pervasive in language, yet we resolve it effortlessly and unconsciously . ambiguity is common because languages allow words to take on multiple meanings .
Approach: They build a sentence-pair dataset to examine how context and POS influence homonym resolution in humans and large language models.
Outcome: The proposed dataset compared humans and large language models to determine how POS and context influence homonym resolution in humans.
Exploring Layer-wise Representations of English and Chinese Homonymy in Pre-trained Language Models (2025.findings-acl)

Copied to clipboard

Challenge: lexical ambiguity can arise due to the misunderstanding of its multiple senses.
Approach: They propose to use part of speech to examine homonyms in Chinese and English . they find no universal layer depth excels in differentiating homnomial representations .
Outcome: The proposed model improves contextualization of homonym representations in Chinese . the results challenge the simplistic understanding of their inner workings, the authors say .

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