Papers by Tengfei Huo

2 papers
Graph Enhanced Cross-Domain Text-to-SQL Generation (D19-53)

Copied to clipboard

Challenge: Existing deep learning approaches for semantic parsing do not generalize to unseen data sets . existing benchmarks have shown text-to-SQL parsers do not generally perform well to unsen SQL queries.
Approach: They propose a new cross-domain learning scheme to perform text-to-SQL translation . they demonstrate its use on a large-scale cross- domain text- to-Sql data set Spider .
Outcome: The proposed learning scheme improves on a large-scale text-to-SQL data set.
One Comment from One Perspective: An Effective Strategy for Enhancing Automatic Music Comment (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for automatic comment generation generate common and meaningless comments for music.
Approach: They propose a multi-perspective strategy to enhance automatic music comment generation by combining different perspectives on a music comment dataset.
Outcome: The proposed model outperforms state-of-the-art models on two music comment datasets and outperformed existing models by a substantial margin.

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