Papers by Myeong Cheol Shin

3 papers
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack (2021.findings-acl)

Copied to clipboard

Challenge: Out-of-domain (OOD) input detection is vital in task-oriented dialogue systems . accepted OOD inputs lead to incorrect response of the system .
Approach: They propose a method to generate out-of-domain samples from in-domain training datasets using OutFlip.
Outcome: The proposed method significantly improves an intent classification model's out-of-domain detection performance.
Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for text summarization are based on recall-oriented understudy for gisting evaluation (ROUGE) scores do not reflect semantic meaning correspondences between generated and reference summaries.
Approach: They propose to use Korean as a summarization language to generate a shorter form of text from the source document preserving salient information.
Outcome: The proposed evaluation metrics improve the correlation between the metrics and human judgment.
LittleBird: Efficient Faster & Longer Transformer for Question Answering (2022.emnlp-main)

Copied to clipboard

Challenge: Existing models for BERT have a limitation dealing with long inputs due to its attention mechanism.
Approach: They propose a model based on BigBird with improved speed and memory footprint . they propose 'pack and unpack attention' to replace global attention .
Outcome: The proposed model can work on long inputs even after being pre-trained on short inputs.

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