Hyesu Lim
2024
Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering
ChaeHun Park
|
Koanho Lee
|
Hyesu Lim
|
Jaeseok Kim
|
Junmo Park
|
Yu-Jung Heo
|
Du-Seong Chang
|
Jaegul Choo
Findings of the Association for Computational Linguistics ACL 2024
Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.
2023
PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
Minseok Choi
|
Hyesu Lim
|
Jaegul Choo
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)
2021
AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain
Jimin Hong
|
TaeHee Kim
|
Hyesu Lim
|
Jaegul Choo
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
During the fine-tuning phase of transfer learning, the pretrained vocabulary remains unchanged, while model parameters are updated. The vocabulary generated based on the pretrained data is suboptimal for downstream data when domain discrepancy exists. We propose to consider the vocabulary as an optimizable parameter, allowing us to update the vocabulary by expanding it with domain specific vocabulary based on a tokenization statistic. Furthermore, we preserve the embeddings of the added words from overfitting to downstream data by utilizing knowledge learned from a pretrained language model with a regularization term. Our method achieved consistent performance improvements on diverse domains (i.e., biomedical, computer science, news, and reviews).
Search
Co-authors
- Jaegul Choo 3
- Minseok Choi 1
- Chaehun Park 1
- Koanho Lee 1
- Jaeseok Kim 1
- show all...