{"id":{"repo_id":"texas-state","oai_identifier":"oai:digital.library.txst.edu:10877/19140"},"canonical_url":"https://search.dev.ndltd.org/etd/texas-state/oai:digital.library.txst.edu:10877/19140","repository":{"repo_id":"texas-state","name":"Texas State University","base_url":"https://digital.library.txst.edu/server/oai/request"},"display":{"title":"A Sentence Generator for Natural Language Evaluators","abstract":"By the tum of the century, it is expected that most computer applications will include a natural language processing component. Both developers and consumers of NLP systems have expressed a need for standard natural language system evaluators. Automated natural language evaluators appear to be the only logical solution to the overwhelming number of NLP systems that have been produced, are being produced, and will be produced. The system described within is based on the Benchmark Evaluation Tool [7] and is the first step toward fully automating the evaluation process. This effort was accomplished in two phases. In phase one, we identified a subset of the Benchmark Evaluation Tool for each class of NLP systems. And in phase two, we designed and implemented a natural language generation system to generate non-causal semantically meaningful test sentences. We followed an Object-Oriented Design (OOD) strategy [1]. In this approach all concepts, including semantic and syntactic rules are defined as objects. Each test sentence is generated as a chain of words satisfying a number semantic, syntactic and contextual constraints. The constraints imposed on the generation process increase dynamically while the sentence is being generated. This strategy guarantees semantic cohesiveness while maintaining syntactic integrity.","abstract_html":"By the tum of the century, it is expected that most computer applications will include a natural language processing component. Both developers and consumers of NLP systems have expressed a need for standard natural language system evaluators. Automated natural language evaluators appear to be the only logical solution to the overwhelming number of NLP systems that have been produced, are being produced, and will be produced. The system described within is based on the Benchmark Evaluation Tool [7] and is the first step toward fully automating the evaluation process. This effort was accomplished in two phases. In phase one, we identified a subset of the Benchmark Evaluation Tool for each class of NLP systems. And in phase two, we designed and implemented a natural language generation system to generate non-causal semantically meaningful test sentences. We followed an Object-Oriented Design (OOD) strategy [1]. In this approach all concepts, including semantic and syntactic rules are defined as objects. Each test sentence is generated as a chain of words satisfying a number semantic, syntactic and contextual constraints. The constraints imposed on the generation process increase dynamically while the sentence is being generated. This strategy guarantees semantic cohesiveness while maintaining syntactic integrity.","abstract_has_math":false,"creators":["Gandy, Howard Craig"],"institution":"Southwest Texas State University","degree_name":"Master of Science","degree_level":"Masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Kaikhah, Khosrow"],"committee_chairs":[],"committee_members":["Hwang, Caneo Jinshong","Ogden, Robert D."],"year":1994,"date_issued":"1994-12","date_published":"1994-12","updated_at":"2026-07-27T21:22:35Z","subjects":["natural language processing","object-oriented programming","computational linguistics"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10877/19140","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kaikhah, Khosrow"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Hwang, Caneo Jinshong","Ogden, Robert D."]},{"key":"dc:creator","label":"Author","values":["Gandy, Howard Craig"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-07-17T17:34:04Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-07-17T17:34:04Z"]},{"key":"dc:date.issued","label":"Date","values":["1994-12"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Southwest Texas State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["natural language processing","object-oriented programming","computational linguistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10877/19140"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["By the tum of the century, it is expected that most computer applications will include a natural language processing component. Both developers and consumers of NLP systems have expressed a need for standard natural language system evaluators. Automated natural language evaluators appear to be the only logical solution to the overwhelming number of NLP systems that have been produced, are being produced, and will be produced. The system described within is based on the Benchmark Evaluation Tool [7] and is the first step toward fully automating the evaluation process. This effort was accomplished in two phases. In phase one, we identified a subset of the Benchmark Evaluation Tool for each class of NLP systems. And in phase two, we designed and implemented a natural language generation system to generate non-causal semantically meaningful test sentences. We followed an Object-Oriented Design (OOD) strategy [1]. In this approach all concepts, including semantic and syntactic rules are defined as objects. Each test sentence is generated as a chain of words satisfying a number semantic, syntactic and contextual constraints. The constraints imposed on the generation process increase dynamically while the sentence is being generated. This strategy guarantees semantic cohesiveness while maintaining syntactic integrity."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["1 file (.pdf)"]},{"key":"dc:title","label":"Title","values":["A Sentence Generator for Natural Language Evaluators"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kaikhah, Khosrow"],"dc:contributor.committeemember":["Hwang, Caneo Jinshong","Ogden, Robert D."],"dc:creator":["Gandy, Howard Craig"],"dc:date.accessioned":["2024-07-17T17:34:04Z"],"dc:date.available":["2024-07-17T17:34:04Z"],"dc:date.issued":["1994-12"],"dc:description.abstract":["By the tum of the century, it is expected that most computer applications will include a natural language processing component. Both developers and consumers of NLP systems have expressed a need for standard natural language system evaluators. Automated natural language evaluators appear to be the only logical solution to the overwhelming number of NLP systems that have been produced, are being produced, and will be produced. The system described within is based on the Benchmark Evaluation Tool [7] and is the first step toward fully automating the evaluation process. This effort was accomplished in two phases. In phase one, we identified a subset of the Benchmark Evaluation Tool for each class of NLP systems. And in phase two, we designed and implemented a natural language generation system to generate non-causal semantically meaningful test sentences. We followed an Object-Oriented Design (OOD) strategy [1]. In this approach all concepts, including semantic and syntactic rules are defined as objects. Each test sentence is generated as a chain of words satisfying a number semantic, syntactic and contextual constraints. The constraints imposed on the generation process increase dynamically while the sentence is being generated. This strategy guarantees semantic cohesiveness while maintaining syntactic integrity."],"dc:format":["Text"],"dc:format.medium":["1 file (.pdf)"],"dc:identifier.uri":["https://hdl.handle.net/10877/19140"],"dc:language.iso":["en"],"dc:subject":["natural language processing","object-oriented programming","computational linguistics"],"dc:title":["A Sentence Generator for Natural Language Evaluators"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Southwest Texas State University"]},"updated_at":"2026-07-27T21:22:35Z"}