Papers by Chenggang Mi

3 papers
Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings (C18-1)

Copied to clipboard

Challenge: Almost every natural language processing task suffers from data sparseness.
Approach: They propose a method which identify loanwords in monolingual corpora by using cross-lingual word embeddings as core feature and a log-linear model which combines several shallow features to predict the final results.
Outcome: The proposed method outperforms baseline models significantly on loanword identification and translation in four languages and eight translation directions.
Parallel sentences mining with transfer learning in an unsupervised setting (2021.naacl-srw)

Copied to clipboard

Challenge: Existing methods to mine parallel sentences in low-resource environments are not suitable for many low-level language pairs.
Approach: They propose an approach based on transfer learning to mine parallel sentences in an unsupervised setting using bilingual corpora of low-resource language pairs.
Outcome: The proposed model improves the performance of mined parallel sentences at two real-world low-resource language pairs compared with previous methods.
A Neural Network Based Model for Loanword Identification in Uyghur (L18-1)

Copied to clipboard

Challenge: Lexical borrowing happens in almost all languages, and we propose a new method to identify loanwords in Uyghur.
Approach: They propose a neural network based loanword identification model for Uyghur that captures past and future information and learns both word level and character level features automatically.
Outcome: The proposed model outperforms baseline models on Chinese, Arabic and Russian loanword detection in Uyghur.

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