Papers by Tuan-Anh Nguyen

2 papers
HeterGraphLongSum: Heterogeneous Graph Neural Network with Passage Aggregation for Extractive Long Document Summarization (2022.coling-1)

Copied to clipboard

Challenge: Existing models for extractive document summarization are based on sequence-to-sequence (Seq2Sequency) but long-form document summaries using graph-based methods are still an open research issue.
Approach: They propose a heterogeneous graph neural network model to improve the performance of extractive document summarization using graph-based methods.
Outcome: The proposed model can achieve state-of-the-art performance without pre-trained language models.
Towards Safer Operations: An Expert-involved Dataset of High-Pressure Gas Incidents for Preventing Future Failures (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing datasets for incident management tasks are labor-intensive and time-consuming.
Approach: They propose a new IncidentAI dataset for safety prevention that includes three tasks . they argue that NLP techniques are beneficial for analyzing incident reports .
Outcome: The proposed dataset shows that NLP techniques are beneficial for analyzing incident reports to prevent future failures.

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