Papers by Anh Tuan Phan

2 papers
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives (P19-1)

Copied to clipboard

Challenge: Using a pointer-generator framework for reading/sampling over large documents, we propose a framework for learning over long narratives where documents easily span over thousands of tokens.
Approach: They propose a curriculum learning (CL) based pointer-generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty.
Outcome: The proposed framework improves on the NarrativeQA reading comprehension benchmark and reaches state-of-the-art performance.
KC4MT: A High-Quality Corpus for Multilingual Machine Translation (2022.lrec-1)

Copied to clipboard

Challenge: In machine translation, Vietnamese is a low-resource language, and the quality of the training corpus is very low.
Approach: They propose a method for building high-quality multilingual parallel corpus in news domain . they also publicize a corpus that includes 500.000 Vietnamese-Chinese bilingual sentence pairs .
Outcome: The proposed method improves the quality of multilingual machine translation in Vietnamese, Laos, and Khmer . the public version includes 500.000 Vietnamese-Chinese bilingual sentence pairs .

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