{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/78684"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/78684","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Constraint-based metric-aware approach for relation co-extraction","abstract":"This thesis focuses on relation extraction within unstructured text data. We are interested in the bootstrapping approach, in which only a small portion of examples are given to train the extractor. The training of the extractor is actually a process of finding good textual representation patterns for that relationship and the duality relationship between tuples and patterns are explored as a mutual enhancement in an iterative way. However, due to the lack of decent amount of labelled data at the beginning, the bootstrapping performance is often unsatisfactory. Recent literatures explore additional meta level information such as constraints and find a way to add it along with bootstrapping seeds to further reinforce supervision. Our approach takes a step further by exploring how to better incorporate such domain specific constraints into the ranking process of selecting textual patterns for better extraction precision and recall. Thus, we call it a constriant-based metric-aware approach. We explore three types of general constraints and develop models for each of them. We finally conduct experiment on the Wikipedia article dataset, and the results show that with our model, we can achieve significant performance boost in terms of f1 score.","abstract_html":"This thesis focuses on relation extraction within unstructured text data. We are interested in the bootstrapping approach, in which only a small portion of examples are given to train the extractor. The training of the extractor is actually a process of finding good textual representation patterns for that relationship and the duality relationship between tuples and patterns are explored as a mutual enhancement in an iterative way. However, due to the lack of decent amount of labelled data at the beginning, the bootstrapping performance is often unsatisfactory. Recent literatures explore additional meta level information such as constraints and find a way to add it along with bootstrapping seeds to further reinforce supervision. Our approach takes a step further by exploring how to better incorporate such domain specific constraints into the ranking process of selecting textual patterns for better extraction precision and recall. Thus, we call it a constriant-based metric-aware approach. We explore three types of general constraints and develop models for each of them. We finally conduct experiment on the Wikipedia article dataset, and the results show that with our model, we can achieve significant performance boost in terms of f1 score.","abstract_has_math":false,"creators":["Chen, Xiaoyu"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-07-22T22:34:00Z","date_published":"2015-07-22T22:34:00Z","updated_at":"2026-07-22T22:26:12Z","subjects":["relation extraction","constraints","random walk"],"languages":["en"],"rights":["Copyright 2015 Xiaoyu Chen"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/78684","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Chen, Xiaoyu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-07-22T22:34:00Z","2017-07-23T09:15:23Z","2015-05","2015-04-28","2015-5"]},{"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":["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":["relation extraction","constraints","random walk"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Xiaoyu Chen"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/78684"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis focuses on relation extraction within unstructured text data. We are interested in the bootstrapping approach, in which only a small portion of examples are given to train the extractor. The training of the extractor is actually a process of finding good textual representation patterns for that relationship and the duality relationship between tuples and patterns are explored as a mutual enhancement in an iterative way. However, due to the lack of decent amount of labelled data at the beginning, the bootstrapping performance is often unsatisfactory. Recent literatures explore additional meta level information such as constraints and find a way to add it along with bootstrapping seeds to further reinforce supervision. Our approach takes a step further by exploring how to better incorporate such domain specific constraints into the ranking process of selecting textual patterns for better extraction precision and recall. Thus, we call it a constriant-based metric-aware approach. We explore three types of general constraints and develop models for each of them. We finally conduct experiment on the Wikipedia article dataset, and the results show that with our model, we can achieve significant performance boost in terms of f1 score.","Submission published under a 24 month embargo labeled 'U of I only', the embargo will last until 2017-05-01","The student, Xiaoyu Chen, accepted the attached license on 2015-04-28 at 12:13.","The student, Xiaoyu Chen, submitted this Thesis for approval on 2015-04-28 at 13:01.","This Thesis was approved for publication on 2015-04-28 at 14:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8155 on 2015-07-22 at 14:18:57","Made available in DSpace on 2015-07-22T22:34:00Z (GMT). No. of bitstreams: 2 CHEN-THESIS-2015.pdf: 983954 bytes, checksum: 328c1af0aa96f23626c0aca7bccfc909 (MD5) LICENSE.txt: 4208 bytes, checksum: afee2a85a63920bfda33778d360692d6 (MD5) Previous issue date: 2015-04-28","Embargo set by: Seth Robbins for item 79925 Lift date: 2017-07-22T22:34:16Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 79925 on 2017-07-23T09:15:23Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Constraint-based metric-aware approach for relation co-extraction"]}]}],"canonical_facts":{"dc:creator":["Chen, Xiaoyu"],"dc:date":["2015-07-22T22:34:00Z","2017-07-23T09:15:23Z","2015-05","2015-04-28","2015-5"],"dc:description":["This thesis focuses on relation extraction within unstructured text data. We are interested in the bootstrapping approach, in which only a small portion of examples are given to train the extractor. The training of the extractor is actually a process of finding good textual representation patterns for that relationship and the duality relationship between tuples and patterns are explored as a mutual enhancement in an iterative way. However, due to the lack of decent amount of labelled data at the beginning, the bootstrapping performance is often unsatisfactory. Recent literatures explore additional meta level information such as constraints and find a way to add it along with bootstrapping seeds to further reinforce supervision. Our approach takes a step further by exploring how to better incorporate such domain specific constraints into the ranking process of selecting textual patterns for better extraction precision and recall. Thus, we call it a constriant-based metric-aware approach. We explore three types of general constraints and develop models for each of them. We finally conduct experiment on the Wikipedia article dataset, and the results show that with our model, we can achieve significant performance boost in terms of f1 score.","Submission published under a 24 month embargo labeled 'U of I only', the embargo will last until 2017-05-01","The student, Xiaoyu Chen, accepted the attached license on 2015-04-28 at 12:13.","The student, Xiaoyu Chen, submitted this Thesis for approval on 2015-04-28 at 13:01.","This Thesis was approved for publication on 2015-04-28 at 14:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8155 on 2015-07-22 at 14:18:57","Made available in DSpace on 2015-07-22T22:34:00Z (GMT). No. of bitstreams: 2 CHEN-THESIS-2015.pdf: 983954 bytes, checksum: 328c1af0aa96f23626c0aca7bccfc909 (MD5) LICENSE.txt: 4208 bytes, checksum: afee2a85a63920bfda33778d360692d6 (MD5) Previous issue date: 2015-04-28","Embargo set by: Seth Robbins for item 79925 Lift date: 2017-07-22T22:34:16Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 79925 on 2017-07-23T09:15:23Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/78684"],"dc:language":["en"],"dc:rights":["Copyright 2015 Xiaoyu Chen"],"dc:subject":["relation extraction","constraints","random walk"],"dc:title":["Constraint-based metric-aware approach for relation co-extraction"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:12Z"}