Papers by Thanh-Le Ha

4 papers
Overcoming the Rare Word Problem for low-resource language pairs in Neural Machine Translation (D19-52)

Copied to clipboard

Challenge: Despite above approaches can improve the prediction of rare words, they still have challenges which have adverse effects on its effectiveness.
Approach: They propose three ways to address rare-word problem in neural machine translation systems . they propose an algorithm to learn morphology of unknown words for English in supervised way to minimize adverse effect of rare- word problem.
Outcome: The proposed approaches improve accuracy on two low-resource language pairs.
KIT Lecture Translator: Multilingual Speech Translation with One-Shot Learning (C18-2)

Copied to clipboard

Challenge: In today's globalized world, communication is difficult and often the language barrier still prevents communication.
Approach: They have developed a low-latency translation system that is adapted to lectures and covers several language pairs.
Outcome: The proposed system improves performance but also covers several European languages.
KIT-Multi: A Translation-Oriented Multilingual Embedding Corpus (L18-1)

Copied to clipboard

Challenge: Cross-lingual word embeddings are representations of words across languages in a shared continuous vector space.
Approach: They propose a multilingual word embedding corpus which is acquired by neural machine translation and is based on monolingual data.
Outcome: The proposed method is competitive with existing methods but on the cross-lingual document classification task, it obtains the best figures.
Gradient-based Gradual Pruning for Language-Specific Multilingual Neural Machine Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Multilingual neural machine translation suffers from performance degradation in high-resource languages compared to bilingual counterparts.
Approach: They propose a gradient-based gradual pruning technique for multilingual neural machine translation that allows for partial parameter sharing across language pairs to alleviate interference.
Outcome: The proposed approach yields a notable performance gain on IWSLT and WMT 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