{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/144901"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/144901","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Open Intent Generation Through Unsupervised Semantic Clustering of Task-Oriented Dialog","abstract":"The natural language processing field has seen task-oriented dialog systems emerge as a strong area of interest in research and industry over the past years. However, the limited existence of complex and sufficiently annotated training data still places a bottleneck on the development of more advanced, domain-agnostic chatbots. Novel domains require extensive time and manual effort from experts when creating intents for new datasets to support dialog systems. This thesis analyzes a two-staged unsupervised semantic clustering and intent generation approach with multiple dataset adaptive interchangeable methods. We examine various pre-trained embeddings, scoring objectives for the number of clusters, unsupervised clustering algorithms, intent generation techniques, and utterance tokenization schemes. We then run experiments with these combinations on three datasets: SNIPS, MultiWOZ, and real-world chat data. This is followed by quantitative metric and in-depth qualitative cluster-based evaluation. We show the benefits of bigram frequency intent generation as datasets increase irregularity and confirm the success of the universal sentence encoder embeddings with K-Means clustering. Additionally, our examination of real-world data underlines the importance of fine-grained utterance tokenization and gives promise to the feasibility of research methods on unpublished data. Altogether, this thesis provides a comprehensive analysis covering the abilities of the the two-stage pipeline components to support open intent discovery for a variety of dataset characteristics, offering alternative solutions where beneficial for real-world applications. This gives insight to the optimal configuration to automatically generate a novel dialog training dataset from unstructured, unlabeled chat utterances. The code for this thesis can be found at https://github.com/jnwagner53/dialog-intent-generation.","abstract_html":"The natural language processing field has seen task-oriented dialog systems emerge as a strong area of interest in research and industry over the past years. However, the limited existence of complex and sufficiently annotated training data still places a bottleneck on the development of more advanced, domain-agnostic chatbots. Novel domains require extensive time and manual effort from experts when creating intents for new datasets to support dialog systems. This thesis analyzes a two-staged unsupervised semantic clustering and intent generation approach with multiple dataset adaptive interchangeable methods. We examine various pre-trained embeddings, scoring objectives for the number of clusters, unsupervised clustering algorithms, intent generation techniques, and utterance tokenization schemes. We then run experiments with these combinations on three datasets: SNIPS, MultiWOZ, and real-world chat data. This is followed by quantitative metric and in-depth qualitative cluster-based evaluation. We show the benefits of bigram frequency intent generation as datasets increase irregularity and confirm the success of the universal sentence encoder embeddings with K-Means clustering. Additionally, our examination of real-world data underlines the importance of fine-grained utterance tokenization and gives promise to the feasibility of research methods on unpublished data. Altogether, this thesis provides a comprehensive analysis covering the abilities of the the two-stage pipeline components to support open intent discovery for a variety of dataset characteristics, offering alternative solutions where beneficial for real-world applications. This gives insight to the optimal configuration to automatically generate a novel dialog training dataset from unstructured, unlabeled chat utterances. The code for this thesis can be found at https://github.com/jnwagner53/dialog-intent-generation.","abstract_has_math":false,"creators":["Wagner, Julia N."],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Glass, James"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:22:24Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/144901","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Glass, James"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Wagner, Julia N."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T16:19:44Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T16:19:44Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/144901"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The natural language processing field has seen task-oriented dialog systems emerge as a strong area of interest in research and industry over the past years. However, the limited existence of complex and sufficiently annotated training data still places a bottleneck on the development of more advanced, domain-agnostic chatbots. Novel domains require extensive time and manual effort from experts when creating intents for new datasets to support dialog systems. This thesis analyzes a two-staged unsupervised semantic clustering and intent generation approach with multiple dataset adaptive interchangeable methods. We examine various pre-trained embeddings, scoring objectives for the number of clusters, unsupervised clustering algorithms, intent generation techniques, and utterance tokenization schemes. We then run experiments with these combinations on three datasets: SNIPS, MultiWOZ, and real-world chat data. This is followed by quantitative metric and in-depth qualitative cluster-based evaluation. We show the benefits of bigram frequency intent generation as datasets increase irregularity and confirm the success of the universal sentence encoder embeddings with K-Means clustering. Additionally, our examination of real-world data underlines the importance of fine-grained utterance tokenization and gives promise to the feasibility of research methods on unpublished data. Altogether, this thesis provides a comprehensive analysis covering the abilities of the the two-stage pipeline components to support open intent discovery for a variety of dataset characteristics, offering alternative solutions where beneficial for real-world applications. This gives insight to the optimal configuration to automatically generate a novel dialog training dataset from unstructured, unlabeled chat utterances. The code for this thesis can be found at https://github.com/jnwagner53/dialog-intent-generation."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Open Intent Generation Through Unsupervised Semantic Clustering of Task-Oriented Dialog"]}]}],"canonical_facts":{"dc:contributor.advisor":["Glass, James"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Wagner, Julia N."],"dc:date.accessioned":["2022-08-29T16:19:44Z"],"dc:date.available":["2022-08-29T16:19:44Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["The natural language processing field has seen task-oriented dialog systems emerge as a strong area of interest in research and industry over the past years. However, the limited existence of complex and sufficiently annotated training data still places a bottleneck on the development of more advanced, domain-agnostic chatbots. Novel domains require extensive time and manual effort from experts when creating intents for new datasets to support dialog systems. This thesis analyzes a two-staged unsupervised semantic clustering and intent generation approach with multiple dataset adaptive interchangeable methods. We examine various pre-trained embeddings, scoring objectives for the number of clusters, unsupervised clustering algorithms, intent generation techniques, and utterance tokenization schemes. We then run experiments with these combinations on three datasets: SNIPS, MultiWOZ, and real-world chat data. This is followed by quantitative metric and in-depth qualitative cluster-based evaluation. We show the benefits of bigram frequency intent generation as datasets increase irregularity and confirm the success of the universal sentence encoder embeddings with K-Means clustering. Additionally, our examination of real-world data underlines the importance of fine-grained utterance tokenization and gives promise to the feasibility of research methods on unpublished data. Altogether, this thesis provides a comprehensive analysis covering the abilities of the the two-stage pipeline components to support open intent discovery for a variety of dataset characteristics, offering alternative solutions where beneficial for real-world applications. This gives insight to the optimal configuration to automatically generate a novel dialog training dataset from unstructured, unlabeled chat utterances. The code for this thesis can be found at https://github.com/jnwagner53/dialog-intent-generation."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/144901"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Open Intent Generation Through Unsupervised Semantic Clustering of Task-Oriented Dialog"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:24Z"}