English Generation from a Knowledge Base and Overly General Classes
نویسندگان
چکیده
In this paper, we describe the range of sentences that we synthesize from a knowledge base (KB) using a natural language generation (NLG) system. We give an overview of our NLG system, and then focus on the specific challenge in handling overly general classes such as Tangible-Entity and Physical-Object. Such classes are unavoidable in the KB, and it is undesirable to show them in an output for end users. Our approach has been implemented in an intelligent textbook application that helps students learn better.
منابع مشابه
From Importer of Knowledge to Researcher of the Self: Exploring the Utility of Collaborative Action Research in Distance Second Language Professional Development
Teacher professional development, as a burgeoning term, has attracted a surge of interest in English language teaching. In second language (L2) professional development, the common orthodoxy has been one which considers teachers as that of knowledge consumers. It is commonly argued that top-down approaches to teachers’ professional development has done little to maximize teachers’ professionali...
متن کاملMulti-lingual Sentence Generation from the PIVOT Interlingua
This paper proposes a strategy for French and Spanish sentence generation systems, based on the English generation system. The English generation mode! consists of four procedures, conceptual wording (sentence-structure planning), syntactic selection, ordering and morphological generation. The analysis of linguistic similarities and differences between English, French and Spanish reveals that a...
متن کاملRelationship between Iranian EFL High School Students’ Knowledge of Universal Grammar and their Performance on Standardized General English Proficiency Tests
This study investigated the relationship between Iranian high school students’ Universal Grammar knowledge and their performance on such standardized general English proficiency tests as PET and FCE internationally administered by Cambridge University. To this end, 108 students were randomly chosen from some high schools located in Malayer from Hamedan. Since this study was correlational in nat...
متن کاملThe impact of picture-based vs. context-based method on Iranian intermediate EFL learners' knowledge of prepositions
The present study aimed to investigate the effect of picture-based vs. context-base method onIranian intermediate EFL learners' knowledge of prepositions. The main question this study triedto answer were whether using picture-based vs. context-based method might enhance higherknowledge of prepositions in Iranian learners of English at intermediate level. To answer thequestions, 45 intermediate ...
متن کاملPHRED: A Generator for Natural Language Interfaces
PHRED (PHRasal English Diction is a natural language generator designed for use in a variety of domains. It was constructed to share a knowledge base with PHRAN (PHRasal ANalyzer) as part of a real-time user-friendly interface. The knowledge base consists of pattern-concept pairs, i.e., associations between linguistic structures and conceptual templates. Using this knowledge base, PHRED produce...
متن کامل