发布求助
文献互助 智能选刊 最新文献

Journal of Natural Language Processing最新文献

筛选
英文 中文
Translation and Machine Translation 翻译与机器翻译
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.975
Atsushi Fujita, Masaru Yamada, K. Kageura
{"title":"Translation and Machine Translation","authors":"Atsushi Fujita, Masaru Yamada, K. Kageura","doi":"10.5715/JNLP.27.975","DOIUrl":"https://doi.org/10.5715/JNLP.27.975","url":null,"abstract":"","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"28 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126607857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Language Resources for Japanese Lexical Simplification 日语词汇简化的语言资源
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.801
Tomoyuki Kajiwara, Daiki Nishihara, Tomonori Kodaira, Mamoru Komachi
{"title":"Language Resources for Japanese Lexical Simplification","authors":"Tomoyuki Kajiwara, Daiki Nishihara, Tomonori Kodaira, Mamoru Komachi","doi":"10.5715/JNLP.27.801","DOIUrl":"https://doi.org/10.5715/JNLP.27.801","url":null,"abstract":"This study introduces three language resources for Japanese lexical simplification: 1) an evaluation dataset, 2) lexica, and 3) a toolkit that can be used to develop and benchmark Japanese lexical simplification systems. The word complexity lexicon adopted in this study was automatically expanded using a classifier trained on a small word complexity lexicon created by Japanese language teachers. Based on this word complexity estimator, simplified word pairs were extracted from a large-scale synonym lexicon, and a simplified synonym lexicon that is useful for lexical simplification was developed. In addition, a Python library, which implements automatic evaluation and key methods in each subtask to ease the construction process of a lexical simplification pipeline, was developed. The experimental results on the developed evaluation dataset revealed that the proposed method, which is based on the developed lexicon, achieves the highest performance of Japanese lexical simplification.","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115229118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Language Processing for Finance and Economics 财经语言处理
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.951
Hiroki Sakaji, K. Izumi, Hiroyuki Sakai
{"title":"Language Processing for Finance and Economics","authors":"Hiroki Sakaji, K. Izumi, Hiroyuki Sakai","doi":"10.5715/JNLP.27.951","DOIUrl":"https://doi.org/10.5715/JNLP.27.951","url":null,"abstract":"","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128792582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-dialect Neural Machine Translation for 48 Low-resource Japanese Dialects 48种低资源日语方言的多方言神经机器翻译
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.781
Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki, Kentaro Inui
{"title":"Multi-dialect Neural Machine Translation for 48 Low-resource Japanese Dialects","authors":"Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki, Kentaro Inui","doi":"10.5715/JNLP.27.781","DOIUrl":"https://doi.org/10.5715/JNLP.27.781","url":null,"abstract":"We present a multi-dialect neural machine translation (NMT) model tailored to Japanese. Although the surface forms of Japanese dialects differ from those of standard Japanese, most of the dialects have common fundamental properties, such as word order, and some also use numerous same phonetic correspondence rules. To take advantage of these properties, we integrate multilingual, syllable-level, and fixedorder translation techniques into a general NMT model. Our experimental results demonstrate that this model can outperform a baseline dialect translation model. In addition, we show that visualizing the dialect embeddings learned by the model can facilitate the geographical and typological analyses of the dialects.","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128037250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
SHINRA Project SHINRA项目
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/jnlp.27.945
S. Sekine
{"title":"SHINRA Project","authors":"S. Sekine","doi":"10.5715/jnlp.27.945","DOIUrl":"https://doi.org/10.5715/jnlp.27.945","url":null,"abstract":"","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127138014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Coordinate Structure Analysis using Local Models and CKY Algorithm 基于局部模型和CKY算法的坐标结构分析
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.719
Hiroki Teranishi, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto
{"title":"Coordinate Structure Analysis using Local Models and CKY Algorithm","authors":"Hiroki Teranishi, Hiroyuki Shindo, Taro Watanabe, Yuji Matsumoto","doi":"10.5715/JNLP.27.719","DOIUrl":"https://doi.org/10.5715/JNLP.27.719","url":null,"abstract":"The task of coordinate structure analysis is to identify coordinated phrases linked by a coordinator. Coordination is a major source of ambiguities in natural language and confuses even state-of-the-art syntactic parsers. In this paper, we generalize a scoring function that takes a pair of spans with a coordinator and returns a higher score for the two spans to be coordinated. During inference, our system employs this function with the CKY parsing algorithm and produces coordinate structures for a given sentence. To obtain such a function, we decompose the task into three independent subtasks and build the function based on three different neural networks for the tasks. The experimental results on English corpora demonstrate that our model achieves stateof-the-art results, ensuring that the global structure of coordination is consistent.","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127393948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Semi-Supervised Extractive Question Summarizer Using Question-Answer Pairs and its Learning Methods 基于问答对的半监督抽取问题摘要器及其学习方法
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.825
Tatsuya Ishigaki, Kazuya Machida, Hayato Kobayashi, Hiroya Takamura, M. Okumura
{"title":"Semi-Supervised Extractive Question Summarizer Using Question-Answer Pairs and its Learning Methods","authors":"Tatsuya Ishigaki, Kazuya Machida, Hayato Kobayashi, Hiroya Takamura, M. Okumura","doi":"10.5715/JNLP.27.825","DOIUrl":"https://doi.org/10.5715/JNLP.27.825","url":null,"abstract":"We treat extractive summarization for questions. Neural extractive summarizers often require much labeled training data. Obtaining such labels is difficult, especially for user-generated content, such as questions posted on community question answering services. In this paper, we propose semi-supervised extractive summarizers for such questions that exploit question-answer pairs to alleviate the problem of insufficient labeled data. To this end, we propose several learning methods, namely pretraining, multi-task learning, distant supervision, and sampling methods, to examine how to effectively use such unlabeled paired data. Experimental results show that multi-task training performs well with an appropriate sampling method or distant supervision, especially when the labeled data is small.","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133058708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Japanese Discourse Relation Analysis: Task Definition, Connective Detection, and Corpus Annotation 日语语篇关系分析:任务定义、连接检测与语料库标注
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.889
Yudai Kishimoto, Yugo Murawaki, Daisuke Kawahara, S. Kurohashi
{"title":"Japanese Discourse Relation Analysis: Task Definition, Connective Detection, and Corpus Annotation","authors":"Yudai Kishimoto, Yugo Murawaki, Daisuke Kawahara, S. Kurohashi","doi":"10.5715/JNLP.27.889","DOIUrl":"https://doi.org/10.5715/JNLP.27.889","url":null,"abstract":"uments, (2) automatically annotating discourse units and connectives, (3) designing a discourse relation tagset consisting of seven classes organized into a two-level hierar-chy, and (4) annotating discourse relations through two types of annotators, namely experts and crowd workers. We report that there is significant room for improvement in data annotation performed by crowd workers. Based on this corpus, we develop a Japanese discourse parser. Experimental results show that the proposed parser outperforms previously developed models. We also demonstrate that the automatic recognizer of discourse connectives can be used as a high-quality parser for explicit discourse relations. We implement a recognizer of discourse units and discourse connectives in KNP. We also make the corpus publicly available.","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127233998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Developing a Site for Worldwide COVID-19 Information Aggregation through Open Collaboration 通过开放协作开发全球COVID-19信息聚合网站
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.939
Daisuke Kawahara
{"title":"Developing a Site for Worldwide COVID-19 Information Aggregation through Open Collaboration","authors":"Daisuke Kawahara","doi":"10.5715/JNLP.27.939","DOIUrl":"https://doi.org/10.5715/JNLP.27.939","url":null,"abstract":"","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132281929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Natural Language Processing Application to the Chemical Domain 自然语言处理在化学领域的应用
Journal of Natural Language Processing Pub Date : 2020-12-15 DOI: 10.5715/JNLP.27.969
Tomoya Iwakura, Hiyori Yoshikawa
{"title":"Natural Language Processing Application to the Chemical Domain","authors":"Tomoya Iwakura, Hiyori Yoshikawa","doi":"10.5715/JNLP.27.969","DOIUrl":"https://doi.org/10.5715/JNLP.27.969","url":null,"abstract":"","PeriodicalId":218014,"journal":{"name":"Journal of Natural Language Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123583490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书