Papers by Chia-Fang Ho

2 papers
Learning to Respond to Mixed-code Queries using Bilingual Word Embeddings (N19-4)

Copied to clipboard

Challenge: Many queries are submitted to search engines on the Web every day to retrieve linguistic information for learning a second language (L2) due to limited L2 vocabulary knowledge, users often submit mix-coded queries without converting them into target language queries.
Approach: They propose a method for learning bilingual word embeddings to support second language learners . mixed-code queries are transformed into target language queries . preliminary evaluation shows method performs reasonablly well .
Outcome: The proposed method performs reasonablly well on a list of common word-translation queries.
Learning to Link Grammar and Encyclopedic Information of Assist ESL Learners (P19-3)

Copied to clipboard

Challenge: Linggle Booster provides rich lexical information such as collocations and grammar patterns for target words.
Approach: They propose a system that takes an article, identifies target vocabulary, provides lexical information, and generates a quiz on target words.
Outcome: The proposed system has been evaluated on a set of target words and has a good performance.

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