{"id":{"repo_id":"cornell","oai_identifier":"oai:ecommons.cornell.edu:1813/103003"},"canonical_url":"https://search.ndltd.org/etd/cornell/oai:ecommons.cornell.edu:1813/103003","repository":{"repo_id":"cornell","name":"Cornell University","base_url":"https://ecommons.cornell.edu/server/oai/request"},"display":{"title":"A Model of Unsupervised Formal Learning for Natural Language","abstract":"Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language.","abstract_html":"Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language.","abstract_has_math":false,"creators":["Collard, Jacob Neil"],"institution":"Cornell University","degree_name":"Ph. D., Linguistics","degree_level":"Doctor of Philosophy","degree_discipline":"Linguistics","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":["Rooth, Mats"],"committee_members":["Bowers, John S.","Despic, Miloje"],"year":2020,"date_issued":"2020-08","date_published":"2020-08","updated_at":"2026-11-19T03:08:32Z","subjects":["combinatory categorial grammar","grammar formalisms","semantic parsing","syntactic theory","tree-adjoining grammar","unsupervised learning"],"languages":["en"],"rights":["Attribution 4.0 International"],"rights_urls":["https://creativecommons.org/licenses/by/4.0/"],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/fj3m-7673"],"render_values":[{"text":"https://doi.org/10.7298/fj3m-7673","href":"https://doi.org/10.7298/fj3m-7673","code":true}]},{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["13277971"],"render_values":[{"text":"13277971","href":null,"code":true}]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 12154","ProQuest Publication ID: 28031674"],"render_values":[{"text":"ProQuest Submission ID: 12154","href":null,"code":true},{"text":"ProQuest Publication ID: 28031674","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1813/103003","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/1813/103003","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%2F103003","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.chair","label":"Chair","values":["Rooth, Mats"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Bowers, John S.","Despic, Miloje"]},{"key":"dc:creator","label":"Author","values":["Collard, Jacob Neil"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-03-12T17:40:40Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-03-12T17:40:40Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-08"]},{"key":"dc:relation.uri","label":"Dc Relation URI","values":["https://catalog.library.cornell.edu/catalog/13277971"]},{"key":"dc:type","label":"Dc Type","values":["dissertation or thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Linguistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctor of Philosophy"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D., Linguistics"]},{"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":["combinatory categorial grammar","grammar formalisms","semantic parsing","syntactic theory","tree-adjoining grammar","unsupervised learning"]}]},{"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 4.0 International"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.bibid","label":"Dc Identifier Bibid","values":["13277971"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.7298/fj3m-7673"]},{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["ProQuest Submission ID: 12154","ProQuest Publication ID: 28031674"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1813/103003"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"cerif:openaire","label":"Cerif Openaire","values":["<Publication xmlns=\"https://www.openaire.eu/cerif-profile/1.1/\" id=\"bcf55bd7-5d62-467a-97f6-ddd0ea49364e\"> <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>A Model of Unsupervised Formal Learning for Natural Language</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020-08</PublicationDate> <DOI>https://doi.org/10.7298/fj3m-7673</DOI> <Authors> <Author> <DisplayName>Collard, Jacob Neil</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by/4.0/</License> <Keyword>combinatory categorial grammar</Keyword> <Keyword>grammar formalisms</Keyword> <Keyword>semantic parsing</Keyword> <Keyword>syntactic theory</Keyword> <Keyword>tree-adjoining grammar</Keyword> <Keyword>unsupervised learning</Keyword> <Abstract>Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"]},{"key":"cris:virtual.author","label":"Cris Virtual Author","values":["Collard, Jacob Neil"]},{"key":"cris:virtualsource.collection","label":"Cris Virtualsource Collection","values":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"]},{"key":"dc:description","label":"Description","values":["236 pages"]},{"key":"dc:description.abstract","label":"Abstract","values":["Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language."]},{"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"]},{"key":"dc:title","label":"Title","values":["A Model of Unsupervised Formal Learning for Natural Language"]},{"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=\"bcf55bd7-5d62-467a-97f6-ddd0ea49364e\"> <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>A Model of Unsupervised Formal Learning for Natural Language</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020-08</PublicationDate> <DOI>https://doi.org/10.7298/fj3m-7673</DOI> <Authors> <Author> <DisplayName>Collard, Jacob Neil</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <OrgUnit /> </Publisher> </Publishers> <License>https://creativecommons.org/licenses/by/4.0/</License> <Keyword>combinatory categorial grammar</Keyword> <Keyword>grammar formalisms</Keyword> <Keyword>semantic parsing</Keyword> <Keyword>syntactic theory</Keyword> <Keyword>tree-adjoining grammar</Keyword> <Keyword>unsupervised learning</Keyword> <Abstract>Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language.</Abstract> <Access xmlns=\"http://purl.org/coar/access_right\" > </Access> </Publication>"],"cris:virtual.author":["Collard, Jacob Neil"],"cris:virtualsource.collection":["5893a6ea-7af3-41d7-abc6-04bcd26ab5df"],"dc:contributor.chair":["Rooth, Mats"],"dc:contributor.committeemember":["Bowers, John S.","Despic, Miloje"],"dc:creator":["Collard, Jacob Neil"],"dc:date.accessioned":["2021-03-12T17:40:40Z"],"dc:date.available":["2021-03-12T17:40:40Z"],"dc:date.issued":["2020-08"],"dc:description":["236 pages"],"dc:description.abstract":["Formal language theory has shown that strong notions of learnability do not apply directly to classes of formal language that may include natural languages, regardless of the number of strings presented to the learner. However, research in statistical learning has shown that neural network language models can predict certain linguistic properties when trained on text alone. Unsupervised statistical models that leverage grammar formalisms have not yet achieved the same level of performance, despite advantages in interpretability. I introduce a variably supervised learning algorithms that can directly apply the rules of a number of different grammar formalisms to learn from natural language texts. This algorithm, the Missing Link algorithm, allows for the direct comparison of different grammar formalisms and learning environments. I compare results for Combinatory Categorial Grammars, Tree-Adjoining Grammars, and Relational Grammars with a number of different parameters. These results show that weakly equivalent grammar formalisms, such as CCGs and TAGs, perform differently in unsupervised learning and that directly encoding linguistic features into Relational Grammars can improve performance at specific linguistic tasks, at least in English. I also show that the same algorithm can be used to learn simple a semantics semantics using Abstract Meaning Representations. These results open new lines of research into the exploration of learning models for natural language."],"dc:description.collection":["Cornell Theses and Dissertations"],"dc:format.mimetype":["application/pdf"],"dc:identifier.bibid":["13277971"],"dc:identifier.doi":["https://doi.org/10.7298/fj3m-7673"],"dc:identifier.other":["ProQuest Submission ID: 12154","ProQuest Publication ID: 28031674"],"dc:identifier.uri":["https://hdl.handle.net/1813/103003"],"dc:language.iso":["en"],"dc:relation.uri":["https://catalog.library.cornell.edu/catalog/13277971"],"dc:rights":["Attribution 4.0 International"],"dc:rights.uri":["https://creativecommons.org/licenses/by/4.0/"],"dc:subject":["combinatory categorial grammar","grammar formalisms","semantic parsing","syntactic theory","tree-adjoining grammar","unsupervised learning"],"dcterms:license":["https://hdl.handle.net/1813/59810"],"dc:title":["A Model of Unsupervised Formal Learning for Natural Language"],"dc:type":["dissertation or thesis"],"dspace:entity.type":["Publication"],"others:access_status":["open.access"],"thesis:degree_discipline":["Linguistics"],"thesis:degree_level":["Doctor of Philosophy"],"thesis:degree_name":["Ph. D., Linguistics"],"thesis:institution_name":["Cornell University"]},"updated_at":"2026-11-19T03:08:32Z"}