Papers by Shanbo Chu

2 papers
Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks (2020.emnlp-main)

Copied to clipboard

Challenge: Neural networks typically need large labeled data for training and are not easily interpretable.
Approach: They propose a type of recurrent neural networks that combine neural networks and regular expression rules.
Outcome: The proposed recurrent neural networks outperform previous neural approaches in low- and zero-shot scenarios and remain very competitive in rich-resource settings.
Learning Numeral Embedding (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing word embedding methods do not learn numeral embedds well because numerals are limited in number and their appearances in training corpora are highly scarce.
Approach: They propose two numeral embedding methods that can handle the out-of-vocabulary problem for numerals.
Outcome: The proposed methods can handle the out-of-vocabulary problem for numerals.

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