Paraphrase recognition is a form of natural language processing used in tutoring, question answering, and information retrieval systems. The context of the present work is an automated reading strategy trainer called iSTART (Interactive Strategy Trainer for Active Reading and Thinking). The ability to recognize the use of paraphrase—a complete, partial, or inaccurate paraphrase; with or without extra information—in the student's input is essential if the trainer is to give appropriate feedback. I analyzed the most common patterns of paraphrase and developed a means of representing the semantic structure of sentences. Paraphrases are recognized by transforming sentences into this representation and comparing them. To construct a precise semantic representation, it is important to understand the meaning of prepositions. Adding preposition disambiguation to the original system improved its accuracy by 20%. The preposition sense disambiguation module itself achieves about 80% accuracy for the top 10 most frequently used prepositions.
The main contributions of this work to the research community are the preposition classification and generalized preposition disambiguation processes, which are integrated into the paraphrase recognition system and are shown to be quite effective. The recognition model also forms a significant part of this contribution. The present effort includes the modeling of the paraphrase recognition process, featuring the Syntactic-Semantic Graph as a sentence representation, the implementation of a significant portion of this design demonstrating its effectiveness, the modeling of an effective preposition classification based on prepositional usage, the design of the generalized preposition disambiguation module, and the integration of the preposition disambiguation module into the paraphrase recognition system so as to gain significant improvement.
","abstract_html":"<p>Paraphrase recognition is a form of natural language processing used in tutoring, question answering, and information retrieval systems. The context of the present work is an automated reading strategy trainer called iSTART (Interactive Strategy Trainer for Active Reading and Thinking). The ability to recognize the use of paraphrase—a complete, partial, or inaccurate paraphrase; with or without extra information—in the student's input is essential if the trainer is to give appropriate feedback. I analyzed the most common patterns of paraphrase and developed a means of representing the semantic structure of sentences. Paraphrases are recognized by transforming sentences into this representation and comparing them. To construct a precise semantic representation, it is important to understand the meaning of prepositions. Adding preposition disambiguation to the original system improved its accuracy by 20%. The preposition sense disambiguation module itself achieves about 80% accuracy for the top 10 most frequently used prepositions.</p> <p>The main contributions of this work to the research community are the preposition classification and generalized preposition disambiguation processes, which are integrated into the paraphrase recognition system and are shown to be quite effective. The recognition model also forms a significant part of this contribution. The present effort includes the modeling of the paraphrase recognition process, featuring the Syntactic-Semantic Graph as a sentence representation, the implementation of a significant portion of this design demonstrating its effectiveness, the modeling of an effective preposition classification based on prepositional usage, the design of the generalized preposition disambiguation module, and the integration of the preposition disambiguation module into the paraphrase recognition system so as to gain significant improvement.</p>","abstract_has_math":false,"creators":["Boonthum, Chutima"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Irwin B. Levinstein","Shunichi Toida","Stewart N.T. Shen","Danielle S. McNamara","Johan Bollen"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2007,"date_issued":"2007-04-01T07:00:00Z","date_published":"2007-04-01T07:00:00Z","updated_at":"2026-07-24T03:34:11Z","subjects":["Paraphrase recognition","Reading","Computer Sciences","Educational Technology"],"languages":[],"rights":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["9780549040729"],"render_values":[{"text":"9780549040729","href":null,"code":true}]}]},"links":{"outbound_url":"https://digitalcommons.odu.edu/computerscience_etds/49","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Irwin B. Levinstein","Shunichi Toida","Stewart N.T. Shen","Danielle S. McNamara","Johan Bollen"]},{"key":"dc:creator","label":"Author","values":["Boonthum, Chutima"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-02-14T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Paraphrase recognition","Reading","Computer Sciences","Educational Technology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["9780549040729","https://digitalcommons.odu.edu/computerscience_etds/49"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Paraphrase recognition is a form of natural language processing used in tutoring, question answering, and information retrieval systems. The context of the present work is an automated reading strategy trainer called iSTART (Interactive Strategy Trainer for Active Reading and Thinking). The ability to recognize the use of paraphrase—a complete, partial, or inaccurate paraphrase; with or without extra information—in the student's input is essential if the trainer is to give appropriate feedback. I analyzed the most common patterns of paraphrase and developed a means of representing the semantic structure of sentences. Paraphrases are recognized by transforming sentences into this representation and comparing them. To construct a precise semantic representation, it is important to understand the meaning of prepositions. Adding preposition disambiguation to the original system improved its accuracy by 20%. The preposition sense disambiguation module itself achieves about 80% accuracy for the top 10 most frequently used prepositions.
The main contributions of this work to the research community are the preposition classification and generalized preposition disambiguation processes, which are integrated into the paraphrase recognition system and are shown to be quite effective. The recognition model also forms a significant part of this contribution. The present effort includes the modeling of the paraphrase recognition process, featuring the Syntactic-Semantic Graph as a sentence representation, the implementation of a significant portion of this design demonstrating its effectiveness, the modeling of an effective preposition classification based on prepositional usage, the design of the generalized preposition disambiguation module, and the integration of the preposition disambiguation module into the paraphrase recognition system so as to gain significant improvement.
"]},{"key":"dc:title","label":"Title","values":["Diagnosing Reading strategies: Paraphrase Recognition"]}]}],"canonical_facts":{"dc:contributor":["Irwin B. Levinstein","Shunichi Toida","Stewart N.T. Shen","Danielle S. McNamara","Johan Bollen"],"dc:creator":["Boonthum, Chutima"],"dc:date.available":["2019-02-14T08:00:00Z"],"dc:description.abstract":["Paraphrase recognition is a form of natural language processing used in tutoring, question answering, and information retrieval systems. The context of the present work is an automated reading strategy trainer called iSTART (Interactive Strategy Trainer for Active Reading and Thinking). The ability to recognize the use of paraphrase—a complete, partial, or inaccurate paraphrase; with or without extra information—in the student's input is essential if the trainer is to give appropriate feedback. I analyzed the most common patterns of paraphrase and developed a means of representing the semantic structure of sentences. Paraphrases are recognized by transforming sentences into this representation and comparing them. To construct a precise semantic representation, it is important to understand the meaning of prepositions. Adding preposition disambiguation to the original system improved its accuracy by 20%. The preposition sense disambiguation module itself achieves about 80% accuracy for the top 10 most frequently used prepositions.
The main contributions of this work to the research community are the preposition classification and generalized preposition disambiguation processes, which are integrated into the paraphrase recognition system and are shown to be quite effective. The recognition model also forms a significant part of this contribution. The present effort includes the modeling of the paraphrase recognition process, featuring the Syntactic-Semantic Graph as a sentence representation, the implementation of a significant portion of this design demonstrating its effectiveness, the modeling of an effective preposition classification based on prepositional usage, the design of the generalized preposition disambiguation module, and the integration of the preposition disambiguation module into the paraphrase recognition system so as to gain significant improvement.
"],"dc:identifier":["9780549040729","https://digitalcommons.odu.edu/computerscience_etds/49"],"dc:rights":["In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
"],"dc:subject":["Paraphrase recognition","Reading","Computer Sciences","Educational Technology"],"dc:title":["Diagnosing Reading strategies: Paraphrase Recognition"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T03:34:11Z"}