Papers by Yuanchao Liu

3 papers
A Dual Contrastive Learning Framework for Enhanced Multimodal Conversational Emotion Recognition (2025.coling-main)

Copied to clipboard

Challenge: Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion.
Approach: They propose a Dual Contrastive Learning Framework that enhances existing MERC models without additional data.
Outcome: The proposed framework outperforms existing models on two MERC benchmark datasets and shows that it reduces label dependence and enhances emotion-sensitive independent modality features.
Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks (2020.coling-main)

Copied to clipboard

Challenge: Existing extractive summarization models hardly capture inter-sentence relationships, especially in long documents.
Approach: They propose to use a graph neural network to capture inter-sentence relationships efficiently via graph-structured document representation.
Outcome: The proposed model outperforms existing models on CNN/DM and NYT datasets and significantly outperfies them on longer documents.
Neural-based Chinese Idiom Recommendation for Enhancing Elegance in Essay Writing (P19-1)

Copied to clipboard

Challenge: idiom recommendation is difficult because remembering idiomatic expressions is difficult, authors say . idiomas are often written in ancient classical Chinese for conciseness, meaning is difficult to remember .
Approach: They propose to use a neural machine translation framework to recommend idioms . they assume that idiomatic expressions are written with one pseudo target language .
Outcome: The proposed approach achieves promising performance compared with baseline methods.

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