Papers by Rui Gan

2 papers
Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Chinese speech recognition is becoming prevalent due to the similar semantic context of the entities and the overlap of Chinese pronunciation.
Approach: They propose three models to address common confusion issues in Chinese speech recognition . they implement a language model, a LSTM model with semantic features and a rule-based assisted Ngram model .
Outcome: The proposed models achieve highest recognition rate for “T” correction with improvements from 70% in the popular voice input methods up to 90%.
Synergetic Interaction Network with Cross-task Attention for Joint Relational Triple Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to joint entity-relation extraction are limited in their ability to capture the interdependence between the two sub-tasks.
Approach: They propose a synergistic approach to capture interdependence between named entity recognition and relation extraction sub-tasks in a Synergetic Interaction Network.
Outcome: The proposed model achieves significantly better performance on three benchmark datasets.

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