{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86629"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86629","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Towards Effective and Controllable Neural Text Generation","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Fang, Le; 0000-0002-8923-537X"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Chen, Changyou","Computer Science and Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-21T21:35:48Z","date_published":"2025-02-21T21:35:48Z","updated_at":"2026-07-27T19:05:32Z","subjects":["computer science"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86629","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chen, Changyou","Computer Science and Engineering"]},{"key":"dc:creator","label":"Author","values":["Fang, Le; 0000-0002-8923-537X"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-21T21:35:48Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86629"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","Deep neural networks have recently achieved remarkable empirical success in text generation tasks. Users demand both effective and controllable generation, which mean respectively to generate high-quality human-level sequences of words, and to control text output in certain aspects to accommodate different practical needs. Researchers have therefore adopted various neural architectures and techniques. Deep latent variable models, especially variational auto-encoders, have played important roles in representation learning of languages, owing to which promising performances have been shown in several tasks. In recent years, self-attention architectures become the main-stream workhorses and have promoted state-of-the-art generation performances by large margins. Given such context, this thesis presents several studies towards effective and controllable neural text generation. The first part studies the main challenge in using traditional RNN or LSTM based deep latent variable models for text generation, which is the notorious \"posterior collapse\" issue that leads to ineffective usage of input representations. Sample-based representation for natural language is proposed to mitigate the issue and learn better latent features for downstream generation applications. More effective deep latent variable models are trained with mutual information taking into account. The second part deals with controllable generation of open-domain long text in the era of self-attention architectures. When large scale pre-trained language models have shown surprising generation capabilities and the dominant paradigm of \"pre-training + fine-tuning\" emerges to shine in natural language understanding, the thesis presents long text generation based on pre-trained model with fine-grained control. A new task named \"outline to story\" is introduced as a test bed and a simple yet powerful baseline model named \"fine-tune with special tokens\" is proposed. The third part explores deep latent variable models, specifically variational auto-encoders with self-attention architectures. By integrating latent representation vectors with self-attention based pre-trained components, the conditional variational auto-encoder shows effective representation learning performance as expected, and provides a principled way for controlled and conditional generation. This part takes conditional story generation as main test bed and presents satisfying empirical results. Overall, this manuscript advocates to revive the power of representation learning in the era of large-scale pre-trained Transformer-based modeling, in order to achieve both effective and controllable text generation in a principled way.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards Effective and Controllable Neural Text Generation"]}]}],"canonical_facts":{"dc:contributor":["Chen, Changyou","Computer Science and Engineering"],"dc:creator":["Fang, Le; 0000-0002-8923-537X"],"dc:date":["2025-02-21T21:35:48Z","2020"],"dc:description":["Ph.D.","Deep neural networks have recently achieved remarkable empirical success in text generation tasks. Users demand both effective and controllable generation, which mean respectively to generate high-quality human-level sequences of words, and to control text output in certain aspects to accommodate different practical needs. Researchers have therefore adopted various neural architectures and techniques. Deep latent variable models, especially variational auto-encoders, have played important roles in representation learning of languages, owing to which promising performances have been shown in several tasks. In recent years, self-attention architectures become the main-stream workhorses and have promoted state-of-the-art generation performances by large margins. Given such context, this thesis presents several studies towards effective and controllable neural text generation. The first part studies the main challenge in using traditional RNN or LSTM based deep latent variable models for text generation, which is the notorious \"posterior collapse\" issue that leads to ineffective usage of input representations. Sample-based representation for natural language is proposed to mitigate the issue and learn better latent features for downstream generation applications. More effective deep latent variable models are trained with mutual information taking into account. The second part deals with controllable generation of open-domain long text in the era of self-attention architectures. When large scale pre-trained language models have shown surprising generation capabilities and the dominant paradigm of \"pre-training + fine-tuning\" emerges to shine in natural language understanding, the thesis presents long text generation based on pre-trained model with fine-grained control. A new task named \"outline to story\" is introduced as a test bed and a simple yet powerful baseline model named \"fine-tune with special tokens\" is proposed. The third part explores deep latent variable models, specifically variational auto-encoders with self-attention architectures. By integrating latent representation vectors with self-attention based pre-trained components, the conditional variational auto-encoder shows effective representation learning performance as expected, and provides a principled way for controlled and conditional generation. This part takes conditional story generation as main test bed and presents satisfying empirical results. Overall, this manuscript advocates to revive the power of representation learning in the era of large-scale pre-trained Transformer-based modeling, in order to achieve both effective and controllable text generation in a principled way.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86629"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["computer science"],"dc:title":["Towards Effective and Controllable Neural Text Generation"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:32Z"}