Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.4
Hongjin Kim, Damrin Kim, Harksoo Kim
The objective of anaphora resolution in dialogue shared-task is to go above and beyond the simple cases of coreference resolution in written text on which NLP has mostly focused so far, which arguably overestimate the performance of current SOTA models. The anaphora resolution in dialogue shared-task consists of three subtasks; subtask1, resolution of anaphoric identity and non-referring expression identification, subtask2, resolution of bridging references, and subtask3, resolution of discourse deixis/abstract anaphora. In this paper, we propose the pipelined model (i.e., a resolution of anaphoric identity and a resolution of bridging references) for the subtask1 and the subtask2. In the subtask1, our model detects mention via the parentheses prediction. Then, we yield mention representation using the token representation constituting the mention. Mention representation is fed to the coreference resolution model for clustering. In the subtask2, our model resolves bridging references via the MRC framework. We construct query for each entity as “What is related of ENTITY?”. The input of our model is query and documents(i.e., all utterances of dialogue). Then, our model predicts entity span that is answer for query.
{"title":"The Pipeline Model for Resolution of Anaphoric Reference and Resolution of Entity Reference","authors":"Hongjin Kim, Damrin Kim, Harksoo Kim","doi":"10.18653/v1/2021.codi-sharedtask.4","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.4","url":null,"abstract":"The objective of anaphora resolution in dialogue shared-task is to go above and beyond the simple cases of coreference resolution in written text on which NLP has mostly focused so far, which arguably overestimate the performance of current SOTA models. The anaphora resolution in dialogue shared-task consists of three subtasks; subtask1, resolution of anaphoric identity and non-referring expression identification, subtask2, resolution of bridging references, and subtask3, resolution of discourse deixis/abstract anaphora. In this paper, we propose the pipelined model (i.e., a resolution of anaphoric identity and a resolution of bridging references) for the subtask1 and the subtask2. In the subtask1, our model detects mention via the parentheses prediction. Then, we yield mention representation using the token representation constituting the mention. Mention representation is fed to the coreference resolution model for clustering. In the subtask2, our model resolves bridging references via the MRC framework. We construct query for each entity as “What is related of ENTITY?”. The input of our model is query and documents(i.e., all utterances of dialogue). Then, our model predicts entity span that is answer for query.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124220717","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.8
Shengjie Li, Hideo Kobayashi, Vincent Ng
The CODI-CRAC 2021 shared task is the first shared task that focuses exclusively on anaphora resolution in dialogue and provides three tracks, namely entity coreference resolution, bridging resolution, and discourse deixis resolution. We perform a cross-task analysis of the systems that participated in the shared task in each of these tracks.
{"title":"The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis","authors":"Shengjie Li, Hideo Kobayashi, Vincent Ng","doi":"10.18653/v1/2021.codi-sharedtask.8","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.8","url":null,"abstract":"The CODI-CRAC 2021 shared task is the first shared task that focuses exclusively on anaphora resolution in dialogue and provides three tracks, namely entity coreference resolution, bridging resolution, and discourse deixis resolution. We perform a cross-task analysis of the systems that participated in the shared task in each of these tracks.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"40 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120855592","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.3
Tatiana Anikina, Cennet Oguz, N. Skachkova, Siyu Tao, S. Upadhyaya, Ivana Kruijff-Korbayová
We describe the system developed by the DFKI-TalkingRobots Team for the CODI-CRAC 2021 Shared-Task on anaphora resolution in dialogue. Our system consists of three subsystems: (1) the Workspace Coreference System (WCS) incrementally clusters mentions using semantic similarity based on embeddings combined with lexical feature heuristics; (2) the Mention-to-Mention (M2M) coreference resolution system pairs same entity mentions; (3) the Discourse Deixis Resolution (DDR) system employs a Siamese Network to detect discourse anaphor-antecedent pairs. WCS achieved F1-score of 55.6% averaged across the evaluation test sets, M2M achieved 57.2% and DDR achieved 21.5%.
{"title":"Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task","authors":"Tatiana Anikina, Cennet Oguz, N. Skachkova, Siyu Tao, S. Upadhyaya, Ivana Kruijff-Korbayová","doi":"10.18653/v1/2021.codi-sharedtask.3","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.3","url":null,"abstract":"We describe the system developed by the DFKI-TalkingRobots Team for the CODI-CRAC 2021 Shared-Task on anaphora resolution in dialogue. Our system consists of three subsystems: (1) the Workspace Coreference System (WCS) incrementally clusters mentions using semantic similarity based on embeddings combined with lexical feature heuristics; (2) the Mention-to-Mention (M2M) coreference resolution system pairs same entity mentions; (3) the Discourse Deixis Resolution (DDR) system employs a Siamese Network to detect discourse anaphor-antecedent pairs. WCS achieved F1-score of 55.6% averaged across the evaluation test sets, M2M achieved 57.2% and DDR achieved 21.5%.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122797620","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.7
N. Skachkova, Cennet Oguz, Tatiana Anikina, Siyu Tao, S. Upadhyaya, Ivana Kruijff-Korbayová
We compare our team’s systems to others submitted for the CODI-CRAC 2021 Shared-Task on anaphora resolution in dialogue. We analyse the architectures and performance, report some problematic cases in gold annotations, and suggest possible improvements of the systems, their evaluation, data annotation, and the organization of the shared task.
{"title":"Anaphora Resolution in Dialogue: Cross-Team Analysis of the DFKI-TalkingRobots Team Submissions for the CODI-CRAC 2021 Shared-Task","authors":"N. Skachkova, Cennet Oguz, Tatiana Anikina, Siyu Tao, S. Upadhyaya, Ivana Kruijff-Korbayová","doi":"10.18653/v1/2021.codi-sharedtask.7","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.7","url":null,"abstract":"We compare our team’s systems to others submitted for the CODI-CRAC 2021 Shared-Task on anaphora resolution in dialogue. We analyse the architectures and performance, report some problematic cases in gold annotations, and suggest possible improvements of the systems, their evaluation, data annotation, and the organization of the shared task.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124711971","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.2
Hideo Kobayashi, Shengjie Li, Vincent Ng
We describe the systems that we developed for the three tracks of the CODI-CRAC 2021 shared task, namely entity coreference resolution, bridging resolution, and discourse deixis resolution. Our team ranked second for entity coreference resolution, first for bridging resolution, and first for discourse deixis resolution.
{"title":"Neural Anaphora Resolution in Dialogue","authors":"Hideo Kobayashi, Shengjie Li, Vincent Ng","doi":"10.18653/v1/2021.codi-sharedtask.2","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.2","url":null,"abstract":"We describe the systems that we developed for the three tracks of the CODI-CRAC 2021 shared task, namely entity coreference resolution, bridging resolution, and discourse deixis resolution. Our team ranked second for entity coreference resolution, first for bridging resolution, and first for discourse deixis resolution.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126075242","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.1
Sopan Khosla, Juntao Yu, R. Manuvinakurike, Vincent Ng, Massimo Poesio, M. Strube, C. Rosé
In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue. The shared task focuses on detecting anaphoric relations in different genres of conversations. Using five conversational datasets, four of which have been newly annotated with a wide range of anaphoric relations: identity, bridging references and discourse deixis, we defined multiple subtasks focusing individually on these key relations. We discuss the evaluation scripts used to assess the system performance on these subtasks, and provide a brief summary of the participating systems and the results obtained across ?? runs from 5 teams, with most submissions achieving significantly better results than our baseline methods.
{"title":"The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","authors":"Sopan Khosla, Juntao Yu, R. Manuvinakurike, Vincent Ng, Massimo Poesio, M. Strube, C. Rosé","doi":"10.18653/v1/2021.codi-sharedtask.1","DOIUrl":"https://doi.org/10.18653/v1/2021.codi-sharedtask.1","url":null,"abstract":"In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue. The shared task focuses on detecting anaphoric relations in different genres of conversations. Using five conversational datasets, four of which have been newly annotated with a wide range of anaphoric relations: identity, bridging references and discourse deixis, we defined multiple subtasks focusing individually on these key relations. We discuss the evaluation scripts used to assess the system performance on these subtasks, and provide a brief summary of the participating systems and the results obtained across ?? runs from 5 teams, with most submissions achieving significantly better results than our baseline methods.","PeriodicalId":270303,"journal":{"name":"Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127638854","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}
Pub Date : 1900-01-01DOI: 10.18653/v1/2021.codi-sharedtask.5
Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron, P. Denis
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.
{"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":"https://doi.org/10.18653/v1/2021.codi-sharedtask.5","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":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120824610","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：