Hyoung-Gyu Lee


2023

pdf
Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints
Yujin Baek | Koanho Lee | Dayeon Ki | Cheonbok Park | Hyoung-Gyu Lee | Jaegul Choo
Findings of the Association for Computational Linguistics: ACL 2023

Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but understudied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are “homographs” or “unseen” during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT which integrates contextually rich information about unseen lexical constraints from pre-trained language models and strengthens a copy mechanism of the pointer network via direct supervision of a copying score. We also release HOLLY, an evaluation benchmark for assessing the ability of model to cope with “homographic” and “unseen” lexical constraints. Experiments on HOLLY and the previous test setup show the effectiveness of our method. The effects of PLUMCOT are shown to be remarkable in “unseen” constraints. Our dataset is available at https://github.com/papago-lab/HOLLY-benchmark.

2016

pdf
papago: A Machine Translation Service with Word Sense Disambiguation and Currency Conversion
Hyoung-Gyu Lee | Jun-Seok Kim | Joong-Hwi Shin | Jaesong Lee | Ying-Xiu Quan | Young-Seob Jeong
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations

In this paper, we introduce papago - a translator for mobile device which is equipped with new features that can provide convenience for users. The first feature is word sense disambiguation based on user feedback. By using the feature, users can select one among multiple meanings of a homograph and obtain the corrected translation with the user-selected sense. The second feature is the instant currency conversion of money expressions contained in a translation result with current exchange rate. Users can be quickly and precisely provided the amount of money converted as local currency when they travel abroad.

2015

pdf
NAVER Machine Translation System for WAT 2015
Hyoung-Gyu Lee | JaeSong Lee | Jun-Seok Kim | Chang-Ki Lee
Proceedings of the 2nd Workshop on Asian Translation (WAT2015)

2012

pdf
Decoder-based Discriminative Training of Phrase Segmentation for Statistical Machine Translation
Hyoung-Gyu Lee | Hae-Chang Rim
Proceedings of COLING 2012: Posters

pdf
Open Information Extraction for SOV Language Based on Entity-Predicate Pair Detection
Woong-Ki Lee | Yeon-Su Lee | Hyoung-Gyu Lee | Won-Ho Ryu | Hae-Chang Rim
Proceedings of COLING 2012: Demonstration Papers

2011

pdf
Phrase Segmentation Model using Collocation and Translational Entropy
Hyoung-Gyu Lee | Joo-Young Lee | Min-Jeong Kim | Hae-Chang Rim | Joong-Hwi Shin | Young-Sook Hwang
Proceedings of Machine Translation Summit XIII: Papers

2009

pdf
A Multi-Phase Approach to Biomedical Event Extraction
Hyoung-Gyu Lee | Han-Cheol Cho | Min-Jeong Kim | Joo-Young Lee | Gumwon Hong | Hae-Chang Rim
Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task