Papers by Chia-Jung Lee

2 papers
Long Document Ranking with Query-Directed Sparse Transformer (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to document ranking require long documents to be broken to fit in pretrained models.
Approach: They propose a Query-Directed Sparse attention model that induces IR-axiomatic structures in transformer self-attention.
Outcome: The proposed model enforces the principle properties desired in ranking while also enjoying efficiency from sparsity.
Incorporating Behavioral Hypotheses for Query Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Prior work has focused on extending standard Seq2Seq models but literature often leaves out the influence of clickthrough actions.
Approach: They propose a generic encoder-decoder Transformer framework to generate query suggestions from user inputs.
Outcome: The proposed approach improves top-k word error rate and Bert F1 score compared to a recent BART model.

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