{"id":{"repo_id":"unm","oai_identifier":"oai:digitalrepository.unm.edu:cs_etds-1039"},"canonical_url":"https://search.dev.ndltd.org/etd/unm/oai:digitalrepository.unm.edu:cs_etds-1039","repository":{"repo_id":"unm","name":"University of New Mexico","base_url":"https://digitalrepository.unm.edu/do/oai/"},"display":{"title":"Artificial Conversations for Chatter Bots Using Knowledge Representation, Learning, and Pragmatics","abstract":"Chatter bots are software programs that engage in artificial conversations through a text-based input medium. Many businesses have automated their online customer service support by deploying chatter bots. These customer service chatter bots interact with customers, answer their queries, and address service related issues. Traditional chatter bots perform best in artificial conversations consisting of pairs of utterance exchanges such as question-answer sessions, where the context may or may not switch with every exchange pair. They perform poorly in longer conversations, where the context is maintained over several pairs of utterance exchanges. Existing approaches to artificial conversation generation focus on linguistic and grammatical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances. This research explores techniques to go beyond individual sentence-level interactions to model the higher level conversation process. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. This dissertation presents a modular, robust, and scalable architecture that combines content semantics and pragmatic semantics to generate higher quality artificial conversations in the customer service domain. The conversational process is modeled using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. This research leverages specific concepts from conversation theory and speech act theory. For evaluation purposes, the artificial conversations are graded by a panel of human judges using criteria that include Grice's cooperative maxims.","abstract_html":"Chatter bots are software programs that engage in artificial conversations through a text-based input medium. Many businesses have automated their online customer service support by deploying chatter bots. These customer service chatter bots interact with customers, answer their queries, and address service related issues. Traditional chatter bots perform best in artificial conversations consisting of pairs of utterance exchanges such as question-answer sessions, where the context may or may not switch with every exchange pair. They perform poorly in longer conversations, where the context is maintained over several pairs of utterance exchanges. Existing approaches to artificial conversation generation focus on linguistic and grammatical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances. This research explores techniques to go beyond individual sentence-level interactions to model the higher level conversation process. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. This dissertation presents a modular, robust, and scalable architecture that combines content semantics and pragmatic semantics to generate higher quality artificial conversations in the customer service domain. The conversational process is modeled using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. This research leverages specific concepts from conversation theory and speech act theory. For evaluation purposes, the artificial conversations are graded by a panel of human judges using criteria that include Grice's cooperative maxims.","abstract_has_math":false,"creators":["Chakrabarti, Chayan"],"institution":null,"degree_name":"Computer Science","degree_level":"Dissertation","degree_discipline":"Department of Computer Science","degree_department":null,"school":null,"contributors":["Luger, George","Caudell, Thomas","Tapia, Lydia","Wooters, Chuck","Turner, Jessica"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-05-01T07:00:00Z","date_published":"2010-05-01T07:00:00Z","updated_at":"2026-07-24T05:26:00Z","subjects":["Artificial Conversations","Conversation Engineering","Computational Pragmatics","Applied Linguistics"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalrepository.unm.edu/cs_etds/40"],"render_values":[{"text":"https://digitalrepository.unm.edu/cs_etds/40","href":"https://digitalrepository.unm.edu/cs_etds/40","code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/1928/24299","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Luger, George","Caudell, Thomas","Tapia, Lydia","Wooters, Chuck","Turner, Jessica"]},{"key":"dc:creator","label":"Author","values":["Chakrabarti, Chayan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Conversations","Conversation Engineering","Computational Pragmatics","Applied Linguistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/1928/24299","https://digitalrepository.unm.edu/cs_etds/40"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Chatter bots are software programs that engage in artificial conversations through a text-based input medium. Many businesses have automated their online customer service support by deploying chatter bots. These customer service chatter bots interact with customers, answer their queries, and address service related issues. Traditional chatter bots perform best in artificial conversations consisting of pairs of utterance exchanges such as question-answer sessions, where the context may or may not switch with every exchange pair. They perform poorly in longer conversations, where the context is maintained over several pairs of utterance exchanges. Existing approaches to artificial conversation generation focus on linguistic and grammatical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances. This research explores techniques to go beyond individual sentence-level interactions to model the higher level conversation process. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. This dissertation presents a modular, robust, and scalable architecture that combines content semantics and pragmatic semantics to generate higher quality artificial conversations in the customer service domain. The conversational process is modeled using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. This research leverages specific concepts from conversation theory and speech act theory. For evaluation purposes, the artificial conversations are graded by a panel of human judges using criteria that include Grice's cooperative maxims."]},{"key":"dc:title","label":"Title","values":["Artificial Conversations for Chatter Bots Using Knowledge Representation, Learning, and Pragmatics"]}]}],"canonical_facts":{"dc:contributor":["Luger, George","Caudell, Thomas","Tapia, Lydia","Wooters, Chuck","Turner, Jessica"],"dc:creator":["Chakrabarti, Chayan"],"dc:description.abstract":["Chatter bots are software programs that engage in artificial conversations through a text-based input medium. Many businesses have automated their online customer service support by deploying chatter bots. These customer service chatter bots interact with customers, answer their queries, and address service related issues. Traditional chatter bots perform best in artificial conversations consisting of pairs of utterance exchanges such as question-answer sessions, where the context may or may not switch with every exchange pair. They perform poorly in longer conversations, where the context is maintained over several pairs of utterance exchanges. Existing approaches to artificial conversation generation focus on linguistic and grammatical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances. This research explores techniques to go beyond individual sentence-level interactions to model the higher level conversation process. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. This dissertation presents a modular, robust, and scalable architecture that combines content semantics and pragmatic semantics to generate higher quality artificial conversations in the customer service domain. The conversational process is modeled using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. This research leverages specific concepts from conversation theory and speech act theory. For evaluation purposes, the artificial conversations are graded by a panel of human judges using criteria that include Grice's cooperative maxims."],"dc:identifier":["http://hdl.handle.net/1928/24299","https://digitalrepository.unm.edu/cs_etds/40"],"dc:language":["English"],"dc:subject":["Artificial Conversations","Conversation Engineering","Computational Pragmatics","Applied Linguistics"],"dc:title":["Artificial Conversations for Chatter Bots Using Knowledge Representation, Learning, and Pragmatics"],"thesis:degree_discipline":["Department of Computer Science"],"thesis:degree_level":["Dissertation","Doctoral"],"thesis:degree_name":["Computer Science"]},"updated_at":"2026-07-24T05:26:00Z"}