{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101526"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101526","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Understanding stories via event sequence modeling","abstract":"Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of building a NLU system that can model what has happened in stories and predict what would happen in the future, we contribute on three fronts: First, we investigate the optimal way to model events in text; Second, we study how we can model a sequence of events with the balance of generality and specificity; Third, we improve event sequence modeling by joint modeling of semantic information and incorporating background knowledge. Each of the above three research problems poses both conceptual and computational challenges. For event extraction, we find that Semantic Role Labeling (SRL) signals can be served as good intermediate representations for events, thus giving us the ability to reliably identify events with minimal supervision. In addition, since it is important to resolve co-referred entities for extracted events, we make improvements to an existing co-reference resolution system. To model event sequences, we start from studying within document event co-reference (the simplest flow of events); and then extend to model two other more natural event sequences along with discourse phenomena while abstracting over the specific mentions of predicates and entities. We further identify problems for the basic event sequence models, where we fail to capture multiple semantic aspects and background knowledge. We then improve our system by jointly modeling frames, entities and sentiments, yielding joint representations of all these semantic aspects; while at the same time incorporate explicit background knowledge acquired from other corpus as well as human experience. For all tasks, we evaluate the developed algorithms and models on benchmark datasets and achieve better performance compared to other highly competitive methods.","abstract_html":"Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of building a NLU system that can model what has happened in stories and predict what would happen in the future, we contribute on three fronts: First, we investigate the optimal way to model events in text; Second, we study how we can model a sequence of events with the balance of generality and specificity; Third, we improve event sequence modeling by joint modeling of semantic information and incorporating background knowledge. Each of the above three research problems poses both conceptual and computational challenges. For event extraction, we find that Semantic Role Labeling (SRL) signals can be served as good intermediate representations for events, thus giving us the ability to reliably identify events with minimal supervision. In addition, since it is important to resolve co-referred entities for extracted events, we make improvements to an existing co-reference resolution system. To model event sequences, we start from studying within document event co-reference (the simplest flow of events); and then extend to model two other more natural event sequences along with discourse phenomena while abstracting over the specific mentions of predicates and entities. We further identify problems for the basic event sequence models, where we fail to capture multiple semantic aspects and background knowledge. We then improve our system by jointly modeling frames, entities and sentiments, yielding joint representations of all these semantic aspects; while at the same time incorporate explicit background knowledge acquired from other corpus as well as human experience. For all tasks, we evaluate the developed algorithms and models on benchmark datasets and achieve better performance compared to other highly competitive methods.","abstract_has_math":false,"creators":["Peng, Haoruo"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Roth, Dan","Hockenmaier, Julia","Peng, Jian","Gimpel, Kevin"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-27T16:17:37Z","date_published":"2018-09-27T16:17:37Z","updated_at":"2026-07-22T22:24:40Z","subjects":["event sequence modeling","event extraction","entity co-reference","event co-reference","semantic language model","discourse understanding"],"languages":["en"],"rights":["Copyright 2018 Haoruo Peng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101526","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Roth, Dan","Hockenmaier, Julia","Peng, Jian","Gimpel, Kevin"]},{"key":"dc:creator","label":"Author","values":["Peng, Haoruo"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-27T16:17:37Z","2018-07-03","2018-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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 sequence modeling","event extraction","entity co-reference","event co-reference","semantic language model","discourse understanding"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Haoruo Peng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101526"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of building a NLU system that can model what has happened in stories and predict what would happen in the future, we contribute on three fronts: First, we investigate the optimal way to model events in text; Second, we study how we can model a sequence of events with the balance of generality and specificity; Third, we improve event sequence modeling by joint modeling of semantic information and incorporating background knowledge. Each of the above three research problems poses both conceptual and computational challenges. For event extraction, we find that Semantic Role Labeling (SRL) signals can be served as good intermediate representations for events, thus giving us the ability to reliably identify events with minimal supervision. In addition, since it is important to resolve co-referred entities for extracted events, we make improvements to an existing co-reference resolution system. To model event sequences, we start from studying within document event co-reference (the simplest flow of events); and then extend to model two other more natural event sequences along with discourse phenomena while abstracting over the specific mentions of predicates and entities. We further identify problems for the basic event sequence models, where we fail to capture multiple semantic aspects and background knowledge. We then improve our system by jointly modeling frames, entities and sentiments, yielding joint representations of all these semantic aspects; while at the same time incorporate explicit background knowledge acquired from other corpus as well as human experience. For all tasks, we evaluate the developed algorithms and models on benchmark datasets and achieve better performance compared to other highly competitive methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-09-27 without embargo terms","The student, Haoruo Peng, accepted the attached license on 2018-07-03 at 02:09.","The student, Haoruo Peng, submitted this Dissertation for approval on 2018-07-03 at 02:23.","This Dissertation was approved for publication on 2018-07-03 at 11:43.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12715 on 2018-09-27 at 10:46:32","Made available in DSpace on 2018-09-27T16:17:37Z (GMT). No. of bitstreams: 3 PENG-DISSERTATION-2018.pdf: 1063590 bytes, checksum: 0cf29c743eeaf919d4faf4d4443f13d7 (MD5) LICENSE.txt: 4208 bytes, checksum: fc5f9c86c1f4ba9722aa2afff1490582 (MD5) PROQUEST_LICENSE.txt: 4554 bytes, checksum: ed4e4ef41c3737d72043d1996e3fb088 (MD5) Previous issue date: 2018-07-03"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Understanding stories via event sequence modeling"]}]}],"canonical_facts":{"dc:contributor":["Roth, Dan","Hockenmaier, Julia","Peng, Jian","Gimpel, Kevin"],"dc:creator":["Peng, Haoruo"],"dc:date":["2018-09-27T16:17:37Z","2018-07-03","2018-08"],"dc:description":["Understanding stories, i.e. sequences of events, is a crucial yet challenging natural language understanding (NLU) problem, which requires dealing with multiple aspects of semantics, including actions, entities and emotions, as well as background knowledge. In this thesis, towards the goal of building a NLU system that can model what has happened in stories and predict what would happen in the future, we contribute on three fronts: First, we investigate the optimal way to model events in text; Second, we study how we can model a sequence of events with the balance of generality and specificity; Third, we improve event sequence modeling by joint modeling of semantic information and incorporating background knowledge. Each of the above three research problems poses both conceptual and computational challenges. For event extraction, we find that Semantic Role Labeling (SRL) signals can be served as good intermediate representations for events, thus giving us the ability to reliably identify events with minimal supervision. In addition, since it is important to resolve co-referred entities for extracted events, we make improvements to an existing co-reference resolution system. To model event sequences, we start from studying within document event co-reference (the simplest flow of events); and then extend to model two other more natural event sequences along with discourse phenomena while abstracting over the specific mentions of predicates and entities. We further identify problems for the basic event sequence models, where we fail to capture multiple semantic aspects and background knowledge. We then improve our system by jointly modeling frames, entities and sentiments, yielding joint representations of all these semantic aspects; while at the same time incorporate explicit background knowledge acquired from other corpus as well as human experience. For all tasks, we evaluate the developed algorithms and models on benchmark datasets and achieve better performance compared to other highly competitive methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-09-27 without embargo terms","The student, Haoruo Peng, accepted the attached license on 2018-07-03 at 02:09.","The student, Haoruo Peng, submitted this Dissertation for approval on 2018-07-03 at 02:23.","This Dissertation was approved for publication on 2018-07-03 at 11:43.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12715 on 2018-09-27 at 10:46:32","Made available in DSpace on 2018-09-27T16:17:37Z (GMT). No. of bitstreams: 3 PENG-DISSERTATION-2018.pdf: 1063590 bytes, checksum: 0cf29c743eeaf919d4faf4d4443f13d7 (MD5) LICENSE.txt: 4208 bytes, checksum: fc5f9c86c1f4ba9722aa2afff1490582 (MD5) PROQUEST_LICENSE.txt: 4554 bytes, checksum: ed4e4ef41c3737d72043d1996e3fb088 (MD5) Previous issue date: 2018-07-03"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101526"],"dc:language":["en"],"dc:rights":["Copyright 2018 Haoruo Peng"],"dc:subject":["event sequence modeling","event extraction","entity co-reference","event co-reference","semantic language model","discourse understanding"],"dc:title":["Understanding stories via event sequence modeling"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:40Z"}