Papers by Haitong Yang

2 papers
Document-level Multi-aspect Sentiment Classification by Jointly Modeling Users, Aspects, and Overall Ratings (C18-1)

Copied to clipboard

Challenge: Existing approaches focus on text information, but authors and overall ratings are ignored, both of which are proved to be significant on interpreting the sentiments of different aspects.
Approach: They propose a hierarchical user-aspect rating network model to consider user preference and overall ratings jointly.
Outcome: The proposed model can predict aspects of a product in two real-world datasets.
An Experimental Study on the Influence of Culture on Cross-Lingual Sentiment Transfer (2026.acl-long)

Copied to clipboard

Challenge: Identical linguistic expressions can convey different sentiments across cultural contexts . current multilingual models often reduce language to symbolic representation . cultural misalignment is a structural bottleneck, authors say .
Approach: They conduct an empirical study to quantify the influence of culture on cross-lingual sentiment transfer across 7 common SMLMs and 5 linguistically diverse languages.
Outcome: The proposed model disentangles cultural factors from confounding variables and shows cultural distance is a negative predictor of transfer performance.

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