Publications

Tracking Must Go On: Dialogue State Tracking with Verified Self-Training
Jihyun Lee, Chaebin Lee, Yunsu Kim, Gary Geunbae Lee
Interspeech 2023

Score-Balanced Loss for Multi-Aspect Pronunciation Assessment
Heejin Do, Yunsu Kim, Gary Geunbae Lee
Interspeech 2023

Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations
Baikjin Jung, Myungji Lee, Jong-Hyeok Lee, Yunsu Kim
ACL 2023 (Main Conference)
paper

Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring
Heejin Do, Yunsu Kim, Gary Geunbae Lee
ACL 2023 (Findings)

DORIC: Domain Robust Fine-Tuning for Open Intent Clustering through Dependency Parsing
Jihyun Lee, Seungyeon Seo, Yunsu Kim, Gary Geunbae Lee
DSTC11
paper

Hierarchical Pronunciation Assessment with Multi-Aspect Attention
Heejin Do, Yunsu Kim, Gary Geunbae Lee
ICASSP 2023
paper

Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking
Jihyun Lee, Chaebin Lee, Yunsu Kim, Gary Geunbae Lee
arXiv preprint
paper

Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions
Seonjeong Hwang, Yunsu Kim, Gary Geunbae Lee
AACL-IJCNLP 2022 (Main Conference)
paper

Neural Machine Translation for Low-Resource Scenarios
Yunsu Kim
Ph.D. Thesis, Fakultät für Mathematik, Informatik und Naturwissenschaften, RWTH Aachen University
thesis  slides

When and Why is Unsupervised Neural Machine Translation Useless?
Yunsu Kim, Miguel Graça, Hermann Ney
EAMT 2020
paper  slides  video

Pivot-based Transfer Learning for Neural Machine Translation between non-English Languages
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
EMNLP-IJCNLP 2019
paper  poster

When and Why is Document-level Context Useful in Neural Machine Translation?
Yunsu Kim, Duc Thanh Tran, Hermann Ney
DiscoMT 2019
paper  code  poster  slides

Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
Yunsu Kim, Yingbo Gao, Hermann Ney
ACL 2019
paper  code  poster

Learning Bilingual Sentence Embeddings via Autoencoding and Computing Similarities with a Multilayer Perceptron
Yunsu Kim, Hendrik Rosendahl, Nick Rossenbach, Jan Rosendahl, Shahram Khadivi, Hermann Ney
Repl4NLP 2019
paper  poster

Generalizing Back-Translation in Neural Machine Translation
Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, Hermann Ney
WMT 2019
paper  slides

The RWTH Aachen University Machine Translation Systems for WMT 2019
Jan Rosendahl, Christian Herold, Yunsu Kim, Miguel Graça, Weiyue Wang, Parnia Bahar, Yingbo Gao, Hermann Ney
WMT 2019
paper

Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder
Yunsu Kim, Jiahui Geng, Hermann Ney
EMNLP 2018
paper  code  slides  video

The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018
Julian Schamper, Jan Rosendahl, Parnia Bahar, Yunsu Kim, Arne Nix, Hermann Ney
WMT 2018
paper
1st Place in German-English

The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task
Nick Rossenbach, Jan Rosendahl, Yunsu Kim, Miguel Graça, Aman Gokrani, Hermann Ney
WMT 2018
paper
1st Place in SMT 10M Track / 2nd Place in NMT 10M Track

The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018
Miguel Graça, Yunsu Kim, Julian Schamper, Jiahui Geng, Hermann Ney
WMT 2018
paper  poster
1st Place in German-English and English-German

Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes
Yunsu Kim, Julian Schamper, Hermann Ney
EACL 2017
paper  poster

A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing
Yunsu Kim, Andreas Guta, Joern Wuebker, Hermann Ney
WMT 2016
paper  slides

Extended Translation Models in Phrase-based Decoding
Andreas Guta, Joern Wuebker, Miguel Graça, Yunsu Kim, Hermann Ney
WMT 2015
paper

Phrase Table Smoothing with Word Classes
Yunsu Kim
Master's Thesis, Fakultät für Mathematik, Informatik und Naturwissenschaften, RWTH Aachen University
thesis  slides

Subspace Clustering of Data Streams: New Algorithms and Effective Evaluation Measures
Marwan Hassani, Yunsu Kim, Seungjin Choi, Thomas Seidl
Journal of Intelligent Information Systems (JIIS), Volume 42, Number 3
paper

Effective Evaluation Measures for Subspace Clustering of Data Streams
Marwan Hassani, Yunsu Kim, Seungjin Choi, Thomas Seidl
QIMIE 2013
paper

Subspace MOA: Subspace Stream Clustering Evaluation Using the MOA Framework
Marwan Hassani, Yunsu Kim, Thomas Seidl
DASFAA 2013
paper  code
Best Demo Award Runner-up