{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108341"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108341","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Pairwise embedding for event coreference resolution","abstract":"Event coreference resolution is an important part in information extraction research and natural language understanding areas. Recently, the pre-trained language models emerging in modern Natural Language Processing (NLP) community provide a new perspective of solving classical NLP tasks. This thesis presents a novel, extensible, and error-tolerant model for within-document event coreference resolution. The model takes events from the same document pair wisely and extracts the features from both events. These features include but are not limited to sentence embeddings, trigger embeddings, and argument type representations. The extracted features are then used to fine-tune a pre-trained language model, BERT (Bidirectional Encoder Representations from Transformers), to perform event coreference resolution. The coreference results are evaluated by different metrics including B^3, MUC, and CEAF. Experimental results show that our pro-posed model outperforms baseline models with improvements of 0.009 on B^3 and 0.035 on MUC over the state-of-the-art models.","abstract_html":"Event coreference resolution is an important part in information extraction research and natural language understanding areas. Recently, the pre-trained language models emerging in modern Natural Language Processing (NLP) community provide a new perspective of solving classical NLP tasks. This thesis presents a novel, extensible, and error-tolerant model for within-document event coreference resolution. The model takes events from the same document pair wisely and extracts the features from both events. These features include but are not limited to sentence embeddings, trigger embeddings, and argument type representations. The extracted features are then used to fine-tune a pre-trained language model, BERT (Bidirectional Encoder Representations from Transformers), to perform event coreference resolution. The coreference results are evaluated by different metrics including B^3, MUC, and CEAF. Experimental results show that our pro-posed model outperforms baseline models with improvements of 0.009 on B^3 and 0.035 on MUC over the state-of-the-art models.","abstract_has_math":false,"creators":["Hu, Yanda"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Ji, Heng"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-27T00:51:32Z","date_published":"2020-08-27T00:51:32Z","updated_at":"2026-07-22T22:24:48Z","subjects":["event coreference","embedding"],"languages":["en"],"rights":["Copyright 2020 Yanda Hu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108341","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ji, Heng"]},{"key":"dc:creator","label":"Author","values":["Hu, Yanda"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-27T00:51:32Z","2022-08-27T00:51:40Z","2020-05-12","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["event coreference","embedding"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Yanda Hu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108341"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Event coreference resolution is an important part in information extraction research and natural language understanding areas. Recently, the pre-trained language models emerging in modern Natural Language Processing (NLP) community provide a new perspective of solving classical NLP tasks. This thesis presents a novel, extensible, and error-tolerant model for within-document event coreference resolution. The model takes events from the same document pair wisely and extracts the features from both events. These features include but are not limited to sentence embeddings, trigger embeddings, and argument type representations. The extracted features are then used to fine-tune a pre-trained language model, BERT (Bidirectional Encoder Representations from Transformers), to perform event coreference resolution. The coreference results are evaluated by different metrics including B^3, MUC, and CEAF. Experimental results show that our pro-posed model outperforms baseline models with improvements of 0.009 on B^3 and 0.035 on MUC over the state-of-the-art models.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-05-01","The student, Yanda Hu, accepted the attached license on 2020-05-08 at 18:16.","The student, Yanda Hu, submitted this Thesis for approval on 2020-05-08 at 18:18.","This Thesis was approved for publication on 2020-05-12 at 11:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15305 on 2020-08-25 at 17:44:18","Made available in DSpace on 2020-08-27T00:51:32Z (GMT). No. of bitstreams: 2 HU-THESIS-2020.pdf: 513097 bytes, checksum: 686a81a1f9bd5fc55e4609874ecc9f0e (MD5) LICENSE.txt: 4205 bytes, checksum: df443868acc5ec589e3d22b66eb16d2b (MD5) Previous issue date: 2020-05-12","Embargo set by: Seth Robbins for item 115956 Lift date: 2022-08-27T00:51:40Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Pairwise embedding for event coreference resolution"]}]}],"canonical_facts":{"dc:contributor":["Ji, Heng"],"dc:creator":["Hu, Yanda"],"dc:date":["2020-08-27T00:51:32Z","2022-08-27T00:51:40Z","2020-05-12","2020-05"],"dc:description":["Event coreference resolution is an important part in information extraction research and natural language understanding areas. Recently, the pre-trained language models emerging in modern Natural Language Processing (NLP) community provide a new perspective of solving classical NLP tasks. This thesis presents a novel, extensible, and error-tolerant model for within-document event coreference resolution. The model takes events from the same document pair wisely and extracts the features from both events. These features include but are not limited to sentence embeddings, trigger embeddings, and argument type representations. The extracted features are then used to fine-tune a pre-trained language model, BERT (Bidirectional Encoder Representations from Transformers), to perform event coreference resolution. The coreference results are evaluated by different metrics including B^3, MUC, and CEAF. Experimental results show that our pro-posed model outperforms baseline models with improvements of 0.009 on B^3 and 0.035 on MUC over the state-of-the-art models.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-05-01","The student, Yanda Hu, accepted the attached license on 2020-05-08 at 18:16.","The student, Yanda Hu, submitted this Thesis for approval on 2020-05-08 at 18:18.","This Thesis was approved for publication on 2020-05-12 at 11:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15305 on 2020-08-25 at 17:44:18","Made available in DSpace on 2020-08-27T00:51:32Z (GMT). No. of bitstreams: 2 HU-THESIS-2020.pdf: 513097 bytes, checksum: 686a81a1f9bd5fc55e4609874ecc9f0e (MD5) LICENSE.txt: 4205 bytes, checksum: df443868acc5ec589e3d22b66eb16d2b (MD5) Previous issue date: 2020-05-12","Embargo set by: Seth Robbins for item 115956 Lift date: 2022-08-27T00:51:40Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108341"],"dc:language":["en"],"dc:rights":["Copyright 2020 Yanda Hu"],"dc:subject":["event coreference","embedding"],"dc:title":["Pairwise embedding for event coreference resolution"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:48Z"}