International Conference on Language Resources and Evaluation最新文献

LIP-RTVE: An Audiovisual Database for Continuous Spanish in the Wild LIP-RTVE：野生连续西班牙语视听数据库

International Conference on Language Resources and Evaluation Pub Date : 2023-11-21 DOI: 10.48550/arXiv.2311.12457

David Gimeno-Gómez, C. Martínez-Hinarejos

引用次数: 0

Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning 领域不匹配并不总是阻碍跨语言迁移学习

International Conference on Language Resources and Evaluation Pub Date : 2022-11-30 DOI: 10.48550/arXiv.2211.16671

Daniel Edmiston, Phillip Keung, Noah A. Smith

{"title":"Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning","authors":"Daniel Edmiston, Phillip Keung, Noah A. Smith","doi":"10.48550/arXiv.2211.16671","DOIUrl":"https://doi.org/10.48550/arXiv.2211.16671","url":null,"abstract":"Cross-lingual transfer learning without labeled target language data or parallel text has been surprisingly effective in zero-shot cross-lingual classification, question answering, unsupervised machine translation, etc. However, some recent publications have claimed that domain mismatch prevents cross-lingual transfer, and their results show that unsupervised bilingual lexicon induction (UBLI) and unsupervised neural machine translation (UNMT) do not work well when the underlying monolingual corpora come from different domains (e.g., French text from Wikipedia but English text from UN proceedings). In this work, we show how a simple initialization regimen can overcome much of the effect of domain mismatch in cross-lingual transfer. We pre-train word and contextual embeddings on the concatenated domain-mismatched corpora, and use these as initializations for three tasks: MUSE UBLI, UN Parallel UNMT, and the SemEval 2017 cross-lingual word similarity task. In all cases, our results challenge the conclusions of prior work by showing that proper initialization can recover a large portion of the losses incurred by domain mismatch.","PeriodicalId":260442,"journal":{"name":"International Conference on Language Resources and Evaluation","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121168848","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

BERTifying Sinhala - A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification 对僧伽罗语文本分类的预训练语言模型的综合分析

International Conference on Language Resources and Evaluation Pub Date : 2022-08-16 DOI: 10.48550/arXiv.2208.07864

Vinura Dhananjaya, Piyumal Demotte, Surangika Ranathunga, Sanath Jayasena

引用次数: 4

Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient’s Perspective 从病人的角度跨语言检测药物不良反应的方法

International Conference on Language Resources and Evaluation Pub Date : 2022-08-03 DOI: 10.48550/arXiv.2208.02031

Lisa Raithel, Philippe E. Thomas, Roland Roller, Oliver Sapina, Sebastian Moller, Pierre Zweigenbaum

引用次数: 0

Cross-Lingual Knowledge Transfer for Clinical Phenotyping 临床表型的跨语言知识转移

International Conference on Language Resources and Evaluation Pub Date : 2022-08-03 DOI: 10.48550/arXiv.2208.01912

Jens-Michalis Papaioannou, Paul Grundmann, Betty van Aken, A. Samaras, Ilias Kyparissidis, G. Giannakoulas, Felix Alexander Gers, A. Loser

引用次数: 2

ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls ELF22:一个基于上下文的反网络喷子数据集来对抗网络喷子

International Conference on Language Resources and Evaluation Pub Date : 2022-07-30 DOI: 10.48550/arXiv.2208.00176

Huije Lee, Young Ju Na, Hoyun Song, Jisu Shin, Jong C. Park

{"title":"ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls","authors":"Huije Lee, Young Ju Na, Hoyun Song, Jisu Shin, Jong C. Park","doi":"10.48550/arXiv.2208.00176","DOIUrl":"https://doi.org/10.48550/arXiv.2208.00176","url":null,"abstract":"Online trolls increase social costs and cause psychological damage to individuals. With the proliferation of automated accounts making use of bots for trolling, it is difficult for targeted individual users to handle the situation both quantitatively and qualitatively. To address this issue, we focus on automating the method to counter trolls, as counter responses to combat trolls encourage community users to maintain ongoing discussion without compromising freedom of expression. For this purpose, we propose a novel dataset for automatic counter response generation. In particular, we constructed a pair-wise dataset that includes troll comments and counter responses with labeled response strategies, which enables models fine-tuned on our dataset to generate responses by varying counter responses according to the specified strategy. We conducted three tasks to assess the effectiveness of our dataset and evaluated the results through both automatic and human evaluation. In human evaluation, we demonstrate that the model fine-tuned with our dataset shows a significantly improved performance in strategy-controlled sentence generation.","PeriodicalId":260442,"journal":{"name":"International Conference on Language Resources and Evaluation","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127898799","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

DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit DialCrowd 2.0:一个以质量为中心的对话系统众包工具包

International Conference on Language Resources and Evaluation Pub Date : 2022-07-25 DOI: 10.48550/arXiv.2207.12551

Jessica Huynh, Ting-Rui Chiang, Jeffrey P. Bigham, M. Eskénazi

引用次数: 2

A Spoken Drug Prescription Dataset in French for Spoken Language Understanding 用于口语理解的法语口语药物处方数据集

International Conference on Language Resources and Evaluation Pub Date : 2022-07-17 DOI: 10.48550/arXiv.2207.08292

A. Kocabiyikoglu, Franccois Portet, P. Gibert, H. Blanchon, Jean-Marc Babouchkine, G. Gavazzi

引用次数: 1

Effectiveness of French Language Models on Abstractive Dialogue Summarization Task 法语语言模型在抽象对话摘要任务中的有效性

International Conference on Language Resources and Evaluation Pub Date : 2022-07-17 DOI: 10.48550/arXiv.2207.08305

Yongxin Zhou, Franccois Portet, F. Ringeval

{"title":"Effectiveness of French Language Models on Abstractive Dialogue Summarization Task","authors":"Yongxin Zhou, Franccois Portet, F. Ringeval","doi":"10.48550/arXiv.2207.08305","DOIUrl":"https://doi.org/10.48550/arXiv.2207.08305","url":null,"abstract":"Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings, interviews or phone calls. However, such dialogues are still difficult to handle with current models because the spontaneity of the language involves expressions that are rarely present in the corpora used for pre-training the language models. Moreover, the vast majority of the work accomplished in this field has been focused on English. In this work, we present a study on the summarization of spontaneous oral dialogues in French using several language specific pre-trained models: BARThez, and BelGPT-2, as well as multilingual pre-trained models: mBART, mBARThez, and mT5. Experiments were performed on the DECODA (Call Center) dialogue corpus whose task is to generate abstractive synopses from call center conversations between a caller and one or several agents depending on the situation. Results show that the BARThez models offer the best performance far above the previous state-of-the-art on DECODA. We further discuss the limits of such pre-trained models and the challenges that must be addressed for summarizing spontaneous dialogues.","PeriodicalId":260442,"journal":{"name":"International Conference on Language Resources and Evaluation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127500407","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

Open Terminology Management and Sharing Toolkit for Federation of Terminology Databases 术语数据库联盟开放术语管理和共享工具包

International Conference on Language Resources and Evaluation Pub Date : 2022-07-14 DOI: 10.48550/arXiv.2207.06729

Andis Lagzdicnvs, Uldis Silicnvs, Marcis Pinnis, Toms Bergmanis, Arturs Vasiclevskis, Andrejs Vasicljevs

引用次数: 1