{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108548"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108548","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Weakly supervised aspect extraction for domain-specific texts","abstract":"Aspect extraction, identifying aspects of text segments from a pre-defined set of aspects, is one of the keystones in text understanding. It benefits numerous applications, including sentiment analysis and product review summarization. Most existing aspect extraction methods heavily rely on human-curated aspect annotations of massive text segments, thus making them expensive to be applied in specific domains. Recent attempts leveraging clustering methods can alleviate such annotation effort, but they require domain-specific knowledge and effort to further filter, aggregate, and align the clustering results to desired aspects. Therefore, in this paper, we explore to extract aspects from the domain-specific raw texts with very limited supervision – only a few user-provided seed words per each aspect. Specifically, our proposed neural model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the aspect-related words in text segments are weighted higher than those unrelated ones. The self-training mechanism provides more pseudo labels in addition to limited supervision. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed framework, as well as the effectiveness of both the attention module and the self-training mechanism. Case studies on the attention weights further shed lights on the interpretability of our aspect extraction results.","abstract_html":"Aspect extraction, identifying aspects of text segments from a pre-defined set of aspects, is one of the keystones in text understanding. It benefits numerous applications, including sentiment analysis and product review summarization. Most existing aspect extraction methods heavily rely on human-curated aspect annotations of massive text segments, thus making them expensive to be applied in specific domains. Recent attempts leveraging clustering methods can alleviate such annotation effort, but they require domain-specific knowledge and effort to further filter, aggregate, and align the clustering results to desired aspects. Therefore, in this paper, we explore to extract aspects from the domain-specific raw texts with very limited supervision – only a few user-provided seed words per each aspect. Specifically, our proposed neural model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the aspect-related words in text segments are weighted higher than those unrelated ones. The self-training mechanism provides more pseudo labels in addition to limited supervision. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed framework, as well as the effectiveness of both the attention module and the self-training mechanism. Case studies on the attention weights further shed lights on the interpretability of our aspect extraction results.","abstract_has_math":false,"creators":["Guo, Fang"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Han, Jiawei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-10-07T21:00:12Z","date_published":"2020-10-07T21:00:12Z","updated_at":"2026-07-22T22:24:48Z","subjects":["Aspect Extraction","Weakly-supervised"],"languages":["en"],"rights":["Copyright 2020 Fang Guo"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108548","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Han, Jiawei"]},{"key":"dc:creator","label":"Author","values":["Guo, Fang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-10-07T21:00:12Z","2020-07-24","2020-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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":["Aspect Extraction","Weakly-supervised"]}]},{"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 Fang Guo"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108548"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Aspect extraction, identifying aspects of text segments from a pre-defined set of aspects, is one of the keystones in text understanding. It benefits numerous applications, including sentiment analysis and product review summarization. Most existing aspect extraction methods heavily rely on human-curated aspect annotations of massive text segments, thus making them expensive to be applied in specific domains. Recent attempts leveraging clustering methods can alleviate such annotation effort, but they require domain-specific knowledge and effort to further filter, aggregate, and align the clustering results to desired aspects. Therefore, in this paper, we explore to extract aspects from the domain-specific raw texts with very limited supervision – only a few user-provided seed words per each aspect. Specifically, our proposed neural model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the aspect-related words in text segments are weighted higher than those unrelated ones. The self-training mechanism provides more pseudo labels in addition to limited supervision. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed framework, as well as the effectiveness of both the attention module and the self-training mechanism. Case studies on the attention weights further shed lights on the interpretability of our aspect extraction results.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-10-02 without embargo terms","The student, Fang Guo, accepted the attached license on 2020-07-24 at 10:25.","The student, Fang Guo, submitted this Thesis for approval on 2020-07-24 at 10:30.","This Thesis was approved for publication on 2020-07-24 at 11:15.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15747 on 2020-10-02 at 15:15:31","Made available in DSpace on 2020-10-07T21:00:12Z (GMT). No. of bitstreams: 2 GUO-THESIS-2020.pdf: 489575 bytes, checksum: 495a38126a32eaf8167bc75284ebbd02 (MD5) LICENSE.txt: 4205 bytes, checksum: 477df7f60ae99ca4602b0ecce1be4b57 (MD5) Previous issue date: 2020-07-24"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Weakly supervised aspect extraction for domain-specific texts"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei"],"dc:creator":["Guo, Fang"],"dc:date":["2020-10-07T21:00:12Z","2020-07-24","2020-08"],"dc:description":["Aspect extraction, identifying aspects of text segments from a pre-defined set of aspects, is one of the keystones in text understanding. It benefits numerous applications, including sentiment analysis and product review summarization. Most existing aspect extraction methods heavily rely on human-curated aspect annotations of massive text segments, thus making them expensive to be applied in specific domains. Recent attempts leveraging clustering methods can alleviate such annotation effort, but they require domain-specific knowledge and effort to further filter, aggregate, and align the clustering results to desired aspects. Therefore, in this paper, we explore to extract aspects from the domain-specific raw texts with very limited supervision – only a few user-provided seed words per each aspect. Specifically, our proposed neural model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the aspect-related words in text segments are weighted higher than those unrelated ones. The self-training mechanism provides more pseudo labels in addition to limited supervision. Extensive experiments on real-world datasets demonstrate the superior performance of our proposed framework, as well as the effectiveness of both the attention module and the self-training mechanism. Case studies on the attention weights further shed lights on the interpretability of our aspect extraction results.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-10-02 without embargo terms","The student, Fang Guo, accepted the attached license on 2020-07-24 at 10:25.","The student, Fang Guo, submitted this Thesis for approval on 2020-07-24 at 10:30.","This Thesis was approved for publication on 2020-07-24 at 11:15.","DSpace SAF Submission Ingestion Package generated from Vireo submission #15747 on 2020-10-02 at 15:15:31","Made available in DSpace on 2020-10-07T21:00:12Z (GMT). No. of bitstreams: 2 GUO-THESIS-2020.pdf: 489575 bytes, checksum: 495a38126a32eaf8167bc75284ebbd02 (MD5) LICENSE.txt: 4205 bytes, checksum: 477df7f60ae99ca4602b0ecce1be4b57 (MD5) Previous issue date: 2020-07-24"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108548"],"dc:language":["en"],"dc:rights":["Copyright 2020 Fang Guo"],"dc:subject":["Aspect Extraction","Weakly-supervised"],"dc:title":["Weakly supervised aspect extraction for domain-specific texts"],"dc:type":["text","Thesis"],"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":"2026-07-22T22:24:48Z"}