Papers by Haoran Lv

2 papers
Efficient Hybrid Generation Framework for Aspect-Based Sentiment Analysis (2023.eacl-main)

Copied to clipboard

Challenge: Aspect-based sentiment analysis (ABSA) has attracted broad commercial attention due to its commercial value.
Approach: They propose a framework that generates location and semantic information in parallel and a global hybrid loss function in combination with bipartite matching to achieve end-to-end model training.
Outcome: The proposed framework outperforms state-of-the-art methods in almost all cases and outperfies existing methods in terms of inference efficiency.
Language Constrained Multimodal Hyper Adapter For Many-to-Many Multimodal Summarization (2025.acl-long)

Copied to clipboard

Challenge: Existing models that share parameters neglect the language-specific knowledge learning.
Approach: They propose a language-constrained multimodal hyper adapter for multimodal summarization that integrates language-specific adapters into multilingual pre-trained backbones.
Outcome: The proposed model can generate summaries based on multimodal documents such as text and visuals, allowing people to quickly locate key information from the vast multimedia con.

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