Yoonjung Choi


2022

pdf bib
Data Augmentation for Inline Tag-Aware Neural Machine Translation
Yonghyun Ryu | Yoonjung Choi | Sangha Kim
Proceedings of the Seventh Conference on Machine Translation (WMT)

Despite the wide use of inline formatting, not much has been studied on translating sentences with inline formatted tags. The detag-and-project approach using word alignments is one solution to translating a tagged sentence. However, the method has a limitation: tag reinsertion is not considered in the translation process. Another solution is to use an end-to-end model which takes text with inline tags as inputs and translates them into a tagged sentence. This approach can alleviate the problems of the aforementioned method, but there is no sufficient parallel corpus dedicated to such a task. To solve this problem, an automatic data augmentation method by tag injection is suggested, but it is computationally expensive and augmentation is limited since the model is based on isolated translation for all fragments. In this paper, we propose an efficient and effective tag augmentation method based on word alignment. Our experiments show that our approach outperforms the detag-and-project methods. We also introduce a metric to evaluate the placement of tags and show that the suggested metric is reasonable for our task. We further analyze the effectiveness of each implementation detail.

pdf bib
SRT’s Neural Machine Translation System for WMT22 Biomedical Translation Task
Yoonjung Choi | Jiho Shin | Yonghyun Ryu | Sangha Kim
Proceedings of the Seventh Conference on Machine Translation (WMT)

This paper describes the Samsung Research’s Translation system (SRT) submitted to the WMT22 biomedical translation task in two language directions: English to Spanish and Spanish to English. To improve the overall quality, we adopt the deep transformer architecture and employ the back-translation strategy for monolingual corpus. One of the issues in the domain translation is to translate domain-specific terminologies well. To address this issue, we apply the soft-constrained terminology translation based on biomedical terminology dictionaries. In this paper, we provide the performance of our system with WMT20 and WMT21 biomedical testsets. Compared to the best model in WMT20 and WMT21, our system shows equal or better performance. According to the official evaluation results in terms of BLEU scores, our systems get the highest scores in both directions.

2021

pdf bib
Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
HyoJung Han | Seokchan Ahn | Yoonjung Choi | Insoo Chung | Sangha Kim | Kyunghyun Cho
Proceedings of the Sixth Conference on Machine Translation

Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.

2020

pdf bib
An Iterative Knowledge Transfer NMT System for WMT20 News Translation Task
Jiwan Kim | Soyoon Park | Sangha Kim | Yoonjung Choi
Proceedings of the Fifth Conference on Machine Translation

This paper describes our submission to the WMT20 news translation shared task in English to Japanese direction. Our main approach is based on transferring knowledge of domain and linguistic characteristics by pre-training the encoder-decoder model with large amount of in-domain monolingual data through unsupervised and supervised prediction task. We then fine-tune the model with parallel data and in-domain synthetic data, generated with iterative back-translation. For additional gain, we generate final results with an ensemble model and re-rank them with averaged models and language models. Through these methods, we achieve +5.42 BLEU score compare to the baseline model.

pdf bib
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation
Insoo Chung | Byeongwook Kim | Yoonjung Choi | Se Jung Kwon | Yongkweon Jeon | Baeseong Park | Sangha Kim | Dongsoo Lee
Findings of the Association for Computational Linguistics: EMNLP 2020

The deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is limited in computational resources such as mobile or edge devices. Quantization is an effective technique to address such challenges. Our analysis shows that for a given number of quantization bits, each block of Transformer contributes to translation quality and inference computations in different manners. Moreover, even inside an embedding block, each word presents vastly different contributions. Correspondingly, we propose a mixed precision quantization strategy to represent Transformer weights by an extremely low number of bits (e.g., under 3 bits). For example, for each word in an embedding block, we assign different quantization bits based on statistical property. Our quantized Transformer model achieves 11.8× smaller model size than the baseline model, with less than -0.5 BLEU. We achieve 8.3× reduction in run-time memory footprints and 3.5× speed up (Galaxy N10+) such that our proposed compression strategy enables efficient implementation for on-device NMT.

2014

pdf bib
Lexical Acquisition for Opinion Inference: A Sense-Level Lexicon of Benefactive and Malefactive Events
Yoonjung Choi | Lingjia Deng | Janyce Wiebe
Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

pdf bib
+/-EffectWordNet: Sense-level Lexicon Acquisition for Opinion Inference
Yoonjung Choi | Janyce Wiebe
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

pdf bib
Joint Inference and Disambiguation of Implicit Sentiments via Implicature Constraints
Lingjia Deng | Janyce Wiebe | Yoonjung Choi
Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers

2013

pdf bib
CPN-CORE: A Text Semantic Similarity System Infused with Opinion Knowledge
Carmen Banea | Yoonjung Choi | Lingjia Deng | Samer Hassan | Michael Mohler | Bishan Yang | Claire Cardie | Rada Mihalcea | Jan Wiebe
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity

pdf bib
Benefactive/Malefactive Event and Writer Attitude Annotation
Lingjia Deng | Yoonjung Choi | Janyce Wiebe
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)