{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/112985"},"canonical_url":"https://search.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/112985","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"Reasoning and Learning in Interactive Natural Language Systems","abstract":"Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities.","abstract_html":"Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities.","abstract_has_math":false,"creators":["Suhr, Alane"],"institution":"Cornell University","degree_name":"Ph. D., Computer Science","degree_level":"Doctor of Philosophy","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":["Artzi, Yoav"],"committee_members":["Naaman, Mor","Snavely, Keith"],"year":2022,"date_issued":"2022-12","date_published":"2022-12","updated_at":"2026-11-19T03:10:05Z","subjects":["computer vision","language grounding","machine learning","natural language processing"],"languages":["en"],"rights":["Attribution-ShareAlike 4.0 International"],"rights_urls":["https://creativecommons.org/licenses/by-sa/4.0/"],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/5hyz-cx31"],"render_values":[{"text":"https://doi.org/10.7298/5hyz-cx31","href":"https://doi.org/10.7298/5hyz-cx31","code":true}]},{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["15644156"],"render_values":[{"text":"15644156","href":null,"code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13391","ProQuest Publication ID: 29998020"],"render_values":[{"text":"ProQuest Submission ID: 13391","href":null,"code":true},{"text":"ProQuest Publication ID: 29998020","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1813/112985","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/1813/112985","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://ecommons.cornell.edu/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Aecommons.cornell.edu%3A1813%2F112985","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.chair","label":"Chair","values":["Artzi, Yoav"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Naaman, Mor","Snavely, Keith"]},{"key":"dc:creator","label":"Author","values":["Suhr, Alane"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-03-31T16:38:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-12"]},{"key":"dc:relation.uri","label":"Dc Relation URI","values":["https://newcatalog.library.cornell.edu/catalog/15644156"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctor of Philosophy"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D., Computer Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Cornell University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["computer vision","language grounding","machine learning","natural language processing"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution-ShareAlike 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["15644156"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/5hyz-cx31"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 13391","ProQuest Publication ID: 29998020"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/112985"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"cerif:openaire","label":"Cerif Openaire","values":["<Publication xmlns=\"https://www.openaire.eu/cerif-profile/1.1/\" id=\"e1d3696a-d626-4b2a-9082-c21c1e9d98d4\"> <Type xmlns=\"https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types\">http://purl.org/coar/resource_type/c_1843</Type> <Language>en</Language> <Title>Reasoning and Learning in Interactive Natural Language Systems</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2022-12</PublicationDate> <DOI>https://doi.org/10.7298/5hyz-cx31</DOI> <Authors> <Author> <DisplayName>Suhr, Alane</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by-sa/4.0/</License> <Keyword>computer vision</Keyword> <Keyword>language grounding</Keyword> <Keyword>machine learning</Keyword> <Keyword>natural language processing</Keyword> <Abstract>Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"]},{"key":"cris:virtual.author","label":"Cris Virtual Author","values":["Suhr, Alane"]},{"key":"cris:virtualsource.collection","label":"Cris Virtualsource Collection","values":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"]},{"key":"dc:description","label":"Description","values":["264 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities."]},{"key":"dc:description.collection","label":"Dc Description Collection","values":["Cornell Theses and Dissertations"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dcterms:license","label":"Dcterms License","values":["https://hdl.handle.net/1813/59810.2"]},{"key":"dc:title","label":"Title","values":["Reasoning and Learning in Interactive Natural Language Systems"]},{"key":"dspace:entity.type","label":"Dspace Entity Type","values":["Publication"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"cerif:openaire":["<Publication xmlns=\"https://www.openaire.eu/cerif-profile/1.1/\" id=\"e1d3696a-d626-4b2a-9082-c21c1e9d98d4\"> <Type xmlns=\"https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types\">http://purl.org/coar/resource_type/c_1843</Type> <Language>en</Language> <Title>Reasoning and Learning in Interactive Natural Language Systems</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2022-12</PublicationDate> <DOI>https://doi.org/10.7298/5hyz-cx31</DOI> <Authors> <Author> <DisplayName>Suhr, Alane</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by-sa/4.0/</License> <Keyword>computer vision</Keyword> <Keyword>language grounding</Keyword> <Keyword>machine learning</Keyword> <Keyword>natural language processing</Keyword> <Abstract>Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"],"cris:virtual.author":["Suhr, Alane"],"cris:virtualsource.collection":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"],"dc:contributor.chair":["Artzi, Yoav"],"dc:contributor.committeemember":["Naaman, Mor","Snavely, Keith"],"dc:creator":["Suhr, Alane"],"dc:date.accessioned":["2023-03-31T16:38:18Z"],"dc:date.issued":["2022-12"],"dc:description":["264 pages"],"dc:description.abstract":["Systems that support expressive, situated natural language interactions are essential for expanding access to complex computing systems, such as robots and databases, to non-experts. Reasoning and learning in such natural language interactions is a challenging open problem. For example, resolving sentence meaning requires reasoning not only about word meaning, but also about the interaction context, including the history of the interaction and the situated environment. In addition, the sequential dynamics that arise between user and system in and across interactions make learning from static data, i.e., supervised data, both challenging and ineffective. However, these same interaction dynamics result in ample opportunities for learning from implicit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn, improve, and adapt their language use through interaction, without additional annotation effort. This thesis will focus on these challenges and opportunities."],"dc:description.collection":["Cornell Theses and Dissertations"],"dc:format.mimetype":["application/pdf"],"dc:identifier.bibid":["15644156"],"dc:identifier.doi":["https://doi.org/10.7298/5hyz-cx31"],"dc:identifier.other":["ProQuest Submission ID: 13391","ProQuest Publication ID: 29998020"],"dc:identifier.uri":["https://hdl.handle.net/1813/112985"],"dc:language.iso":["en"],"dc:relation.uri":["https://newcatalog.library.cornell.edu/catalog/15644156"],"dc:rights":["Attribution-ShareAlike 4.0 International"],"dc:rights.uri":["https://creativecommons.org/licenses/by-sa/4.0/"],"dc:subject":["computer vision","language grounding","machine learning","natural language processing"],"dcterms:license":["https://hdl.handle.net/1813/59810.2"],"dc:title":["Reasoning and Learning in Interactive Natural Language Systems"],"dc:type":["dissertation or thesis"],"dspace:entity.type":["Publication"],"others:access_status":["open.access"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Doctor of Philosophy"],"thesis:degree_name":["Ph. D., Computer Science"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-11-19T03:10:05Z"}