{"id":{"repo_id":"cambridge","oai_identifier":"oai:www.repository.cam.ac.uk:1810/284882"},"canonical_url":"https://search.dev.ndltd.org/etd/cambridge/oai:www.repository.cam.ac.uk:1810/284882","repository":{"repo_id":"cambridge","name":"Cambridge University","base_url":"https://api.repository.cam.ac.uk/server/oai/request"},"display":{"title":"Functional Distributional Semantics: Learning Linguistically Informed Representations from a Precisely Annotated Corpus","abstract":"The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors – but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about truth, a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a function, mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models.","abstract_html":"The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors – but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about truth, a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a function, mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models.","abstract_has_math":false,"creators":["Emerson, Guy"],"institution":"University of Cambridge","degree_name":"Doctor of Philosophy (PhD)","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Copestake, Ann"],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-11-24","date_published":"2018-11-24","updated_at":"2026-07-22T22:24:23Z","subjects":["formal semantics","distributional semantics","machine learning"],"languages":["en"],"rights":[],"rights_urls":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/72118acc-89b9-4373-b85b-c8cf27dd1326/download","https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["0000000231369682"],"render_values":[{"text":"0000-0002-3136-9682","href":"https://orcid.org/0000-0002-3136-9682","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.17863/CAM.32253","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Copestake, Ann"]},{"key":"dc:contributor.sponsor","label":"Sponsor","values":["Schiff Fund Studentship"]},{"key":"dc:creator","label":"Author","values":["Emerson, Guy"]},{"key":"dc:creator.authoridentifier","label":"Author Identifier","values":["0000000231369682"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2018-11-24"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Cambridge"]},{"key":"dc:relation.isreferencedby.uri","label":"Dc Relation Isreferencedby URI","values":["https://www.repository.cam.ac.uk/handle/1810/284882"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["formal semantics","distributional semantics","machine learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/72118acc-89b9-4373-b85b-c8cf27dd1326/download","https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.17863/CAM.32253"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/ff00603f-5080-4c25-abc1-70b1ace06eff/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors – but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about truth, a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a function, mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["b0941f727aa33c5601f7e135f1f8c1a0","87eda9de84448d1f82354d60eee3eb5f"]},{"key":"dc:title","label":"Title","values":["Functional Distributional Semantics: Learning Linguistically Informed Representations from a Precisely Annotated Corpus"]}]}],"canonical_facts":{"dc:contributor.advisor":["Copestake, Ann"],"dc:contributor.sponsor":["Schiff Fund Studentship"],"dc:creator":["Emerson, Guy"],"dc:creator.authoridentifier":["0000000231369682"],"dc:date.issued":["2018-11-24"],"dc:description.abstract":["The aim of distributional semantics is to design computational techniques that can automatically learn the meanings of words from a body of text. The twin challenges are: how do we represent meaning, and how do we learn these representations? The current state of the art is to represent meanings as vectors – but vectors do not correspond to any traditional notion of meaning. In particular, there is no way to talk about truth, a crucial concept in logic and formal semantics. In this thesis, I develop a framework for distributional semantics which answers this challenge. The meaning of a word is not represented as a vector, but as a function, mapping entities (objects in the world) to probabilities of truth (the probability that the word is true of the entity). Such a function can be interpreted both in the machine learning sense of a classifier, and in the formal semantic sense of a truth-conditional function. This simultaneously allows both the use of machine learning techniques to exploit large datasets, and also the use of formal semantic techniques to manipulate the learnt representations. I define a probabilistic graphical model, which incorporates a probabilistic generalisation of model theory (allowing a strong connection with formal semantics), and which generates semantic dependency graphs (allowing it to be trained on a corpus). This graphical model provides a natural way to model logical inference, semantic composition, and context-dependent meanings, where Bayesian inference plays a crucial role. I demonstrate the feasibility of this approach by training a model on WikiWoods, a parsed version of the English Wikipedia, and evaluating it on three tasks. The results indicate that the model can learn information not captured by vector space models."],"dc:format.checksum.md5":["b0941f727aa33c5601f7e135f1f8c1a0","87eda9de84448d1f82354d60eee3eb5f"],"dc:identifier.doi":["10.17863/CAM.32253"],"dc:identifier.uri":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/ff00603f-5080-4c25-abc1-70b1ace06eff/download"],"dc:language":["en"],"dc:publisher.institution":["University of Cambridge"],"dc:relation.isreferencedby.uri":["https://www.repository.cam.ac.uk/handle/1810/284882"],"dc:rights":["https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/72118acc-89b9-4373-b85b-c8cf27dd1326/download","https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:subject":["formal semantics","distributional semantics","machine learning"],"dc:title":["Functional Distributional Semantics: Learning Linguistically Informed Representations from a Precisely Annotated Corpus"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-22T22:24:23Z"}