{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_48153"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_48153","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"Modeling physical causality of action verbs for grounded language understanding","abstract":"Building systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other's intention, to connect language with concepts in the world, and to make inference based on what we hear or read. Commonsense knowledge is generally shared among cognitive capable individuals, thus it is rarely stated in human language. This makes it very difficult for artificial agents to acquire commonsense knowledge from language corpora. To address this problem, this dissertation investigates the acquisition of commonsense knowledge, especially knowledge related to basic actions upon the physical world and how that influences language processing and grounding.Linguistics studies have shown that action verbs often denote some change of state (CoS) as the result of an action. For example, the result of \"slice a pizza\" is that the state of the object (pizza) changes from one big piece to several smaller pieces. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. Artificial agents often do not have this kind of basic commonsense causality knowledge, which makes it difficult for these agents to work with humans and to reason, learn, and perform actions.To address this problem, this dissertation models dimensions of physical causality associated with common action verbs. Based on such modeling, several approaches are developed to incorporate causality knowledge to language grounding, visual causality reasoning, and commonsense story comprehension.","abstract_html":"Building systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other&#x27;s intention, to connect language with concepts in the world, and to make inference based on what we hear or read. Commonsense knowledge is generally shared among cognitive capable individuals, thus it is rarely stated in human language. This makes it very difficult for artificial agents to acquire commonsense knowledge from language corpora. To address this problem, this dissertation investigates the acquisition of commonsense knowledge, especially knowledge related to basic actions upon the physical world and how that influences language processing and grounding.Linguistics studies have shown that action verbs often denote some change of state (CoS) as the result of an action. For example, the result of &quot;slice a pizza&quot; is that the state of the object (pizza) changes from one big piece to several smaller pieces. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. Artificial agents often do not have this kind of basic commonsense causality knowledge, which makes it difficult for these agents to work with humans and to reason, learn, and perform actions.To address this problem, this dissertation models dimensions of physical causality associated with common action verbs. Based on such modeling, several approaches are developed to incorporate causality knowledge to language grounding, visual causality reasoning, and commonsense story comprehension.","abstract_has_math":false,"creators":["Gao, Qiaozi"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Chai, Joyce Y.","Tan, Pang-Ning","Ross, Arun","Morris, Daniel"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-11-18T18:53:19Z","subjects":["Natural language processing (Computer science)","Expert systems (Computer science)","Commonsense reasoning","Artificial intelligence"],"languages":["English"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:48153","isbn:9781085751063","isbn:1085751066","oclc:1138555889","umi:22619505","local:Gao_grad.msu_0128D_17129"],"render_values":[{"text":"etd:48153","href":null,"code":true},{"text":"isbn:9781085751063","href":null,"code":true},{"text":"isbn:1085751066","href":null,"code":true},{"text":"oclc:1138555889","href":null,"code":true},{"text":"umi:22619505","href":null,"code":true},{"text":"local:Gao_grad.msu_0128D_17129","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_48153","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chai, Joyce Y.","Tan, Pang-Ning","Ross, Arun","Morris, Daniel"]},{"key":"dc:creator","label":"Author","values":["Gao, Qiaozi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Text","Theses"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Natural language processing (Computer science)","Expert systems (Computer science)","Commonsense reasoning","Artificial intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:48153","isbn:9781085751063","isbn:1085751066","oclc:1138555889","umi:22619505","local:Gao_grad.msu_0128D_17129"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Building systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other's intention, to connect language with concepts in the world, and to make inference based on what we hear or read. Commonsense knowledge is generally shared among cognitive capable individuals, thus it is rarely stated in human language. This makes it very difficult for artificial agents to acquire commonsense knowledge from language corpora. To address this problem, this dissertation investigates the acquisition of commonsense knowledge, especially knowledge related to basic actions upon the physical world and how that influences language processing and grounding.Linguistics studies have shown that action verbs often denote some change of state (CoS) as the result of an action. For example, the result of \"slice a pizza\" is that the state of the object (pizza) changes from one big piece to several smaller pieces. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. Artificial agents often do not have this kind of basic commonsense causality knowledge, which makes it difficult for these agents to work with humans and to reason, learn, and perform actions.To address this problem, this dissertation models dimensions of physical causality associated with common action verbs. Based on such modeling, several approaches are developed to incorporate causality knowledge to language grounding, visual causality reasoning, and commonsense story comprehension.","Thesis (Ph. D.)--Michigan State University. Computer Science, 2019","Includes bibliographical references (pages 94-108)"]},{"key":"dc:format","label":"Dc Format","values":["x, 108 pages","application/pdf"]},{"key":"dc:title","label":"Title","values":["Modeling physical causality of action verbs for grounded language understanding"]}]}],"canonical_facts":{"dc:contributor":["Chai, Joyce Y.","Tan, Pang-Ning","Ross, Arun","Morris, Daniel"],"dc:creator":["Gao, Qiaozi"],"dc:date":["2019"],"dc:description":["Building systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other's intention, to connect language with concepts in the world, and to make inference based on what we hear or read. Commonsense knowledge is generally shared among cognitive capable individuals, thus it is rarely stated in human language. This makes it very difficult for artificial agents to acquire commonsense knowledge from language corpora. To address this problem, this dissertation investigates the acquisition of commonsense knowledge, especially knowledge related to basic actions upon the physical world and how that influences language processing and grounding.Linguistics studies have shown that action verbs often denote some change of state (CoS) as the result of an action. For example, the result of \"slice a pizza\" is that the state of the object (pizza) changes from one big piece to several smaller pieces. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. Artificial agents often do not have this kind of basic commonsense causality knowledge, which makes it difficult for these agents to work with humans and to reason, learn, and perform actions.To address this problem, this dissertation models dimensions of physical causality associated with common action verbs. Based on such modeling, several approaches are developed to incorporate causality knowledge to language grounding, visual causality reasoning, and commonsense story comprehension.","Thesis (Ph. D.)--Michigan State University. Computer Science, 2019","Includes bibliographical references (pages 94-108)"],"dc:format":["x, 108 pages","application/pdf"],"dc:identifier":["etd:48153","isbn:9781085751063","isbn:1085751066","oclc:1138555889","umi:22619505","local:Gao_grad.msu_0128D_17129"],"dc:language":["English"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Natural language processing (Computer science)","Expert systems (Computer science)","Commonsense reasoning","Artificial intelligence"],"dc:title":["Modeling physical causality of action verbs for grounded language understanding"],"dc:type":["Text","Theses"]},"updated_at":"2026-11-18T18:53:19Z"}