{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/107875"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/107875","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Synonymous question generation: Learning to ask in different ways using variational autoencoders","abstract":"Recently, there has been significant interest in advancing machine comprehension of text through question answering. Motivated by the idea that machine comprehension should be bidirectional, we explore synonymous question generation from knowledge graphs (KGs) to enable machines to learn how to ask semantically equivalent natural language questions with lexical and syntactical variety from KGs. To the best of our knowledge, this problem has not yet been explored in the literature. We propose explicitly modeling variations in natural language questions associated with KG triples through a conditional variational autoencoder-based model, the Template VAE (T-VAE). Evaluating the generated questions via the Fre'chet InferSent Distance (FID) and the Multiset-Jaccard-k-gram (MS-Jaccard-k) Measure, two joint diversity-quality metrics, demonstrates that the proposed model is able to produce fluent questions that accurately capture variations in questions associated with KG triples. Depending on test conditions, the T-VAE achieves a 15-21% improvement in MS-Jaccard-4 score and a 29-47% improvement in FID score relative to baseline methods.","abstract_html":"Recently, there has been significant interest in advancing machine comprehension of text through question answering. Motivated by the idea that machine comprehension should be bidirectional, we explore synonymous question generation from knowledge graphs (KGs) to enable machines to learn how to ask semantically equivalent natural language questions with lexical and syntactical variety from KGs. To the best of our knowledge, this problem has not yet been explored in the literature. We propose explicitly modeling variations in natural language questions associated with KG triples through a conditional variational autoencoder-based model, the Template VAE (T-VAE). Evaluating the generated questions via the Fre'chet InferSent Distance (FID) and the Multiset-Jaccard-k-gram (MS-Jaccard-k) Measure, two joint diversity-quality metrics, demonstrates that the proposed model is able to produce fluent questions that accurately capture variations in questions associated with KG triples. Depending on test conditions, the T-VAE achieves a 15-21% improvement in MS-Jaccard-4 score and a 29-47% improvement in FID score relative to baseline methods.","abstract_has_math":false,"creators":["Wei, Bingzhe"],"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":["Chang, Kevin C.-C."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:54:17Z","date_published":"2020-08-26T21:54:17Z","updated_at":"2026-07-22T22:24:47Z","subjects":["question generation","variational autoencoders","machine learning","natural language processing"],"languages":["en"],"rights":["Copyright 2020 Bingzhe Wei"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/107875","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chang, Kevin C.-C."]},{"key":"dc:creator","label":"Author","values":["Wei, Bingzhe"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:54:17Z","2020-04-13","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":["question generation","variational autoencoders","machine learning","natural language processing"]}]},{"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 Bingzhe Wei"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/107875"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Recently, there has been significant interest in advancing machine comprehension of text through question answering. Motivated by the idea that machine comprehension should be bidirectional, we explore synonymous question generation from knowledge graphs (KGs) to enable machines to learn how to ask semantically equivalent natural language questions with lexical and syntactical variety from KGs. To the best of our knowledge, this problem has not yet been explored in the literature. We propose explicitly modeling variations in natural language questions associated with KG triples through a conditional variational autoencoder-based model, the Template VAE (T-VAE). Evaluating the generated questions via the Fre'chet InferSent Distance (FID) and the Multiset-Jaccard-k-gram (MS-Jaccard-k) Measure, two joint diversity-quality metrics, demonstrates that the proposed model is able to produce fluent questions that accurately capture variations in questions associated with KG triples. Depending on test conditions, the T-VAE achieves a 15-21% improvement in MS-Jaccard-4 score and a 29-47% improvement in FID score relative to baseline methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Bingzhe Wei, accepted the attached license on 2020-04-09 at 19:17.","The student, Bingzhe Wei, submitted this Thesis for approval on 2020-04-10 at 17:23.","This Thesis was approved for publication on 2020-04-13 at 16:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14951 on 2020-08-25 at 17:06:42","Made available in DSpace on 2020-08-26T21:54:17Z (GMT). No. of bitstreams: 2 WEI-THESIS-2020.pdf: 18679108 bytes, checksum: 3e565c6cec35d43d1368319ffb7be86b (MD5) LICENSE.txt: 4208 bytes, checksum: 7f75bb514e88429786c655a25293722d (MD5) Previous issue date: 2020-04-13"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Synonymous question generation: Learning to ask in different ways using variational autoencoders"]}]}],"canonical_facts":{"dc:contributor":["Chang, Kevin C.-C."],"dc:creator":["Wei, Bingzhe"],"dc:date":["2020-08-26T21:54:17Z","2020-04-13","2020-05"],"dc:description":["Recently, there has been significant interest in advancing machine comprehension of text through question answering. Motivated by the idea that machine comprehension should be bidirectional, we explore synonymous question generation from knowledge graphs (KGs) to enable machines to learn how to ask semantically equivalent natural language questions with lexical and syntactical variety from KGs. To the best of our knowledge, this problem has not yet been explored in the literature. We propose explicitly modeling variations in natural language questions associated with KG triples through a conditional variational autoencoder-based model, the Template VAE (T-VAE). Evaluating the generated questions via the Fre'chet InferSent Distance (FID) and the Multiset-Jaccard-k-gram (MS-Jaccard-k) Measure, two joint diversity-quality metrics, demonstrates that the proposed model is able to produce fluent questions that accurately capture variations in questions associated with KG triples. Depending on test conditions, the T-VAE achieves a 15-21% improvement in MS-Jaccard-4 score and a 29-47% improvement in FID score relative to baseline methods.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Bingzhe Wei, accepted the attached license on 2020-04-09 at 19:17.","The student, Bingzhe Wei, submitted this Thesis for approval on 2020-04-10 at 17:23.","This Thesis was approved for publication on 2020-04-13 at 16:46.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14951 on 2020-08-25 at 17:06:42","Made available in DSpace on 2020-08-26T21:54:17Z (GMT). No. of bitstreams: 2 WEI-THESIS-2020.pdf: 18679108 bytes, checksum: 3e565c6cec35d43d1368319ffb7be86b (MD5) LICENSE.txt: 4208 bytes, checksum: 7f75bb514e88429786c655a25293722d (MD5) Previous issue date: 2020-04-13"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/107875"],"dc:language":["en"],"dc:rights":["Copyright 2020 Bingzhe Wei"],"dc:subject":["question generation","variational autoencoders","machine learning","natural language processing"],"dc:title":["Synonymous question generation: Learning to ask in different ways using variational autoencoders"],"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":"2026-07-22T22:24:47Z"}