完全桥接分辨率的端到端方法

Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue Pub Date : 1900-01-01 DOI:10.18653/v1/2021.codi-sharedtask.5

Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, P. Denis

{"title":"完全桥接分辨率的端到端方法","authors":"Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, P. Denis","doi":"10.18653/v1/2021.codi-sharedtask.5","DOIUrl":null,"url":null,"abstract":"In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order coreference model finetuned for the task of full bridging. We find that while our approach is not effective at modeling the complexities of the task, it performs well on bridging resolution, suggesting a need for investigations into a robust anaphor identification model for future improvements.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"8 4","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"An End-to-End Approach for Full Bridging Resolution\",\"authors\":\"Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, P. Denis\",\"doi\":\"10.18653/v1/2021.codi-sharedtask.5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order coreference model finetuned for the task of full bridging. We find that while our approach is not effective at modeling the complexities of the task, it performs well on bridging resolution, suggesting a need for investigations into a robust anaphor identification model for future improvements.\",\"PeriodicalId\":270303,\"journal\":{\"name\":\"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue\",\"volume\":\"8 4\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/2021.codi-sharedtask.5\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2021.codi-sharedtask.5","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

在这篇文章中，我们描述了我们提交给CODI-CRAC 2021关于对话中回指消解的共享任务- Track BR(金)。我们展示了基于端到端变压器的高阶共参考模型的性能，该模型针对全桥接任务进行了微调。我们发现，虽然我们的方法在模拟任务的复杂性方面并不有效，但它在桥接分辨率方面表现良好，这表明需要研究一个强大的指代识别模型，以供未来改进。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An End-to-End Approach for Full Bridging Resolution

In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order coreference model finetuned for the task of full bridging. We find that while our approach is not effective at modeling the complexities of the task, it performs well on bridging resolution, suggesting a need for investigations into a robust anaphor identification model for future improvements.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue

自引率

0.00%

发文量