Hantae Kim


2022

pdf bib
DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation
Cheonbok Park | Hantae Kim | Ioan Calapodescu | Hyun Chang Cho | Vassilina Nikoulina
Findings of the Association for Computational Linguistics: ACL 2022

Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel samples it would require. It is however a desirable functionality that could help MT practitioners to make an informed decision before investing resources in dataset creation. We propose a Domain adaptation Learning Curve prediction (DaLC) model that predicts prospective DA performance based on in-domain monolingual samples in the source language. Our model relies on the NMT encoder representations combined with various instance and corpus-level features. We demonstrate that instance-level is better able to distinguish between different domains compared to corpus-level frameworks proposed in previous studies Finally, we perform in-depth analyses of the results highlighting the limitations of our approach, and provide directions for future research.

2021

pdf bib
Papago’s Submission for the WMT21 Quality Estimation Shared Task
Seunghyun Lim | Hantae Kim | Hyunjoong Kim
Proceedings of the Sixth Conference on Machine Translation

This paper describes Papago submission to the WMT 2021 Quality Estimation Task 1: Sentence-level Direct Assessment. Our multilingual Quality Estimation system explores the combination of Pretrained Language Models and Multi-task Learning architectures. We propose an iterative training pipeline based on pretraining with large amounts of in-domain synthetic data and finetuning with gold (labeled) data. We then compress our system via knowledge distillation in order to reduce parameters yet maintain strong performance. Our submitted multilingual systems perform competitively in multilingual and all 11 individual language pair settings including zero-shot.