Jinyi Zhang

Prof. Dr. Jinyi Zhang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024 in IEEE Access
Verified
Journal Article
Open access
YWYanshu Wang
Yanshu Wang
Jinyi ZhangJinyi Zhang
Jinyi Zhang
TSTianrong Shi
Tianrong Shi
DDDashuai Deng
Dashuai Deng
TYTian Ye
Tian Ye
TMTadahiro Matsumoto
Tadahiro Matsumoto
This paper explores the role of Large Language Models (LLMs) in revolutionizing interactive Machine Translation (MT), providing a comprehensive analysis across nine innovative research directions. LLMs demonstrate exceptional capabilities in handling complex tasks through advanced text generation and interactive human-machine collaboration, significantly enhancing translation accuracy and efficiency, especially in low-resource language scenarios. This study also outlines potential advancements in LLM applications, emphasizing the integration of domain-specific knowledge and the exploration of model combinations to optimize performance. Future research is suggested to focus on enhancing model adaptability to diverse linguistic environments and refining human-machine interaction frameworks to better serve practical translation needs. The findings contribute to the ongoing discourse on the strategic deployment of MT with LLMs, aiming to direct future developments towards more robust and nuanced language processing solutions.

17 May 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Jinyi ZhangJinyi Zhang
Jinyi Zhang
TMTadahiro Matsumoto
Tadahiro Matsumoto
The translation quality of Neural Machine Translation (NMT) systems depends strongly on the training data size. Sufficient amounts of parallel data are, however, not available for many language pairs. This paper presents a corpus augmentation method, which has two variations: one is for all language pairs, and the other is for the Chinese-Japanese language pair. The method uses both source and target sentences of the existing parallel corpus and generates multiple pseudo-parallel sentence pairs from a long parallel sentence pair containing punctuation marks as follows: (1) split the sentence pair into parallel partial sentences; (2) back-translate the target partial sentences; and (3) replace each partial sentence in the source sentence with the back-translated target partial sentence to generate pseudo-source sentences. The word alignment information, which is used to determine the split points, is modified with “shared Chinese character rates” in segments of the sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with ASPEC-JC (Asian Scientific Paper Excerpt Corpus, Japanese-Chinese) show that the method substantially improves translation performance. We also supply the code (see Supplementary Materials) that can reproduce our proposed method.

21 June 2024 in ACM Transactions on Asian and Low-Resource Language Information Processing
Verified
Journal Article
Open access
Jinyi ZhangJinyi Zhang
Jinyi Zhang
SKSu Ke
Su Ke
HLHaowei Li
Haowei Li
JMJiannan Mao
Jiannan Mao
TYTian Ye
Tian Ye
TMTadahiro Matsumoto
Tadahiro Matsumoto
Machine translation–the automatic transformation of one natural language (source language) into another (target language) through computational means–occupies a central role in computational linguistics and stands as a cornerstone of research within the field of Natural Language Processing (NLP). In recent years, the prominence of Neural Machine Translation (NMT) has grown exponentially, offering an advanced framework for machine translation research. It is noted for its superior translation performance, especially when tackling the challenges posed by low-resource language pairs that suffer from a limited corpus of data resources. This article offers an exhaustive exploration of the historical trajectory and advancements in NMT, accompanied by an analysis of the underlying foundational concepts. It subsequently provides a concise demarcation of the unique characteristics associated with low-resource languages and presents a succinct review of pertinent translation models and their applications, specifically within the context of languages with low-resources. Moreover, this article delves deeply into machine translation techniques, highlighting approaches tailored for Chinese-centric low-resource languages. Ultimately, it anticipates upcoming research directions in the realm of low-resource language translation.

13 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Jinyi ZhangJinyi Zhang
Jinyi Zhang
TYTian Ye
Tian Ye
JMJiannan Mao
Jiannan Mao
MHMei Han
Mei Han
TMTadahiro Matsumoto
Tadahiro Matsumoto
Currently, there are only a limited number of Japanese-Chinese bilingual corpora of a sufficient amount that can be used as training data for neural machine translation (NMT). In particular, there are few corpora that include spoken language such as daily conversation. In this research, we attempt to construct a Japanese-Chinese bilingual corpus of a certain scale by crawling the subtitle data of movies and TV series from the websites. We calculated the BLEU scores of the constructed WCC-JC (Web Crawled Corpus—Japanese and Chinese) and the other compared corpora. We also manually evaluated the translation results using the translation model trained on the WCC-JC to confirm the quality and effectiveness.

11 October 2023 in IEEE Access
Verified
Journal Article
Open access
Jinyi ZhangJinyi Zhang
Jinyi Zhang
CGCong Guo
Cong Guo
JMJiannan Mao
Jiannan Mao
CGChong Guo
Chong Guo
TMTadahiro Matsumoto
Tadahiro Matsumoto
In an era of increasing globalization, the imperative for understanding multilingual texts elevated the role of translation to an everyday necessity. The efficacy of contemporary Neural Machine Translation (NMT) systems was heavily dependent on the availability of substantial training data. As such, the creation of an expansive parallel corpus became a strategic focal point, providing a bedrock for the evolution of high-caliber NMT systems. However, building a parallel corpus often posed challenges due to its complexity and cost, especially for language pairs that lacked sufficient parallel data. To tackle this challenge, this study proposed a novel data augmentation method for the corpus. Bilingual news texts sourced from the KEKE English website were utilized, and SentenceBERT was employed to ensure accurate sentence alignment. Subsequently, the parallel partial sentences within the corpus were filtered and used to augment the dataset. Finally, the effectiveness of the method was assessed by calculating BLEU, chrF and METEOR scores based on both the original corpus and the data-augmented corpus using the base translation model. The experimental results indicated that compared to the baseline method, the optimal method showed an improvement of 0.4-2.1 points in BLEU scores, an improvement of 0.5-2.7 points in chrF scores, and an increase of 0.5-1.6 points in METEOR scores.

26 February 2023 in Electronics
Verified
Journal Article
Open access
PDF file
Jinyi ZhangJinyi Zhang
Jinyi Zhang
TYTian Ye
Tian Ye
JMJiannan Mao
Jiannan Mao
MHMei Han
Mei Han
FWFeng Wen
Feng Wen
TMTadahiro Matsumoto
Tadahiro Matsumoto
Movie and TV subtitles are frequently employed in natural language processing (NLP) applications, but there are limited Japanese-Chinese bilingual corpora accessible as a dataset to train neural machine translation (NMT) models. In our previous study, we effectively constructed a corpus of a considerable size containing bilingual text data in both Japanese and Chinese by collecting subtitle text data from websites that host movies and television series. The unsatisfactory translation performance of the initial corpus, Web-Crawled Corpus of Japanese and Chinese (WCC-JC 1.0), was predominantly caused by the limited number of sentence pairs. To address this shortcoming, we thoroughly analyzed the issues associated with the construction of WCC-JC 1.0 and constructed the WCC-JC 2.0 corpus by first collecting subtitle data from movie and TV series websites. Then, we manually aligned a large number of high-quality sentence pairs. Our efforts resulted in a new corpus that includes about 1.4 million sentence pairs, an 87% increase compared with WCC-JC 1.0. As a result, WCC-JC 2.0 is now among the largest publicly available Japanese-Chinese bilingual corpora in the world. To assess the performance of WCC-JC 2.0, we calculated the BLEU scores relative to other comparative corpora and performed manual evaluations of the translation results generated by translation models trained on WCC-JC 2.0. We provide WCC-JC 2.0 as a free download for research purposes only.