Multilingual corpus construction and domain adaptation for low-resource machine translation
低资源机器翻译的多语言语料库构建和领域适应
基本信息
- 批准号:22KJ1724
- 负责人:
- 金额:$ 1.41万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for JSPS Fellows
- 财政年份:2023
- 资助国家:日本
- 起止时间:2023-03-08 至 2024-03-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
During this year, I have published 5 papers and one journal paper is under review. For the 3 papers as the first author: 1) the first work published in an international conference AACL-IJCNLP2022 exploits BERT-based unsupervised subword segmentation for neural machine translation which is effective on low-resource to high-resource scenarios; 2) the second work published in a domestic conference NLP2023 utilizes machine translation of prompts for adjusting GPT-3 to Japanese tasks; 3) the third work submitting to the NLP journal leverages information from multiple subword segmenters in a proposed subword-relation-aware attention-mechanism and aligning loss objective. Other works include video-information for multimodal NMT which is published in the JIP journal, exploring contrastive word alignments for multilingual NMT which is published in a top international conference NAACL2022, and contrastive pre-training for relation extraction which is published in a top international conference EMNLP2022. Two co-authored papers are under review for international conference ACL2023 and one for EAMT2023. I have also participated in symposiums on campus and workshops in Japan, and communicate with many researchers there.Moreover, I took an internship at NICT in a national lab focusing on machine translation, and we have applied one patent for the BERT-based unsupervised subword segmentation.
在这一年里,我发表了5篇论文,一篇期刊论文正在审查中。对于作为第一作者的3篇论文:1)在国际会议AACL-IJCNLP 2022上发表的第一篇工作利用基于BERT的无监督子分词进行神经机器翻译,该方法在低资源到高资源场景下有效; 2)在国内会议NLP 2023上发表的第二篇工作利用机器翻译提示将GPT-3调整为日语任务; 3)提交给NLP期刊的第三个作品在所提出的子词关系感知注意力机制和对齐损失目标中利用来自多个子词分段器的信息。其他作品包括发表在JIP杂志上的多模态NMT的视频信息,在顶级国际会议NAACL 2022上发表的多语言NMT的对比词对齐探索,以及在顶级国际会议EMNLP 2022上发表的关系提取的对比预训练。两篇合著的论文正在为国际会议ACL 2023和EAMT 2023进行审查。我还参加了日本的校园研讨会和工作坊,并与那里的许多研究人员进行了交流。此外,我还在NICT的一个专注于机器翻译的国家实验室实习,我们已经申请了一项基于BERT的无监督子分词专利。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
对比词对齐何时可以改善多对多神经机器翻译?
- DOI:
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Zhuoyuan Mao;Chenhui Chu;Raj Dabre;Haiyue Song;Zhen Wan and Sadao Kurohashi
- 通讯作者:Zhen Wan and Sadao Kurohashi
BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine Translation
- DOI:
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Haiyue Song;Raj Dabre;Zhuoyuan Mao;Chenhui Chu;S. Kurohashi
- 通讯作者:Haiyue Song;Raj Dabre;Zhuoyuan Mao;Chenhui Chu;S. Kurohashi
Representative Data Selection for Sequence-to-Sequence Pre-training
序列到序列预训练的代表性数据选择
- DOI:
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Haiyue Song;Raj Dabre;Zhuoyuan Mao;Chenhui Chu;Sadao Kurohashi
- 通讯作者:Sadao Kurohashi
Video-guided Machine Translation with Spatial Hierarchical Attention Network
- DOI:10.18653/v1/2021.acl-srw.9
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Weiqi Gu;Haiyue Song;Chenhui Chu;S. Kurohashi
- 通讯作者:Weiqi Gu;Haiyue Song;Chenhui Chu;S. Kurohashi
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
宋 海越其他文献
宋 海越的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似国自然基金
基于ChatGPT的AI特异性戒烟辅导结合时空支持的动态戒烟管理模式构建及实证研究
- 批准号:
- 批准年份:2024
- 资助金额:15.0 万元
- 项目类别:省市级项目
相似海外基金
Learning about ChatGPT for educational purposes: Examining the role of online teacher communities for supporting teachers in Japan
了解用于教育目的的 ChatGPT:检查在线教师社区在支持日本教师方面的作用
- 批准号:
24K16767 - 财政年份:2024
- 资助金额:
$ 1.41万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
PestGPT: Integrating Visual Intelligence and ChatGPT into a Mobile Solution for Sustainable Pest Management
PestGPT:将视觉智能和 ChatGPT 集成到可持续害虫管理的移动解决方案中
- 批准号:
10076558 - 财政年份:2023
- 资助金额:
$ 1.41万 - 项目类别:
Collaborative R&D
SBIR Phase I: Using ChatGPT and Machine Learning to Power Positive Change among Justice Involved Youth
SBIR 第一阶段:利用 ChatGPT 和机器学习推动参与正义的青少年发生积极变化
- 批准号:
2333168 - 财政年份:2023
- 资助金额:
$ 1.41万 - 项目类别:
Standard Grant
Building a RT-ChatGPT on Radiotherapy for Cancer Treatment using a Medically Trained OpenAI ChatGPT
使用经过医学训练的 OpenAI ChatGPT 构建癌症放射治疗的 RT-ChatGPT
- 批准号:
487811 - 财政年份:2023
- 资助金额:
$ 1.41万 - 项目类别:
Miscellaneous Programs