Title
PREFER: using a graph-based approach to generate paraphrases for language learning
Abstract
Paraphrasing is an important aspect of language competence; however, EFL learners have long had difficulty paraphrasing in their writing owing to their limited language proficiency. Therefore, automatic paraphrase suggestion systems can be useful for writers. In this paper, we present PREFER, a paraphrase reference tool for helping language learners improve their writing skills. In this paper, we attempt to transform the paraphrase generation problem into a graphical problem in which the phrases are treated as nodes and translation similarities as edges. We adopt the PageRank algorithm to rank and filter the paraphrases generated by the pivot-based paraphrase generation method. We manually evaluate the performance of our method and assess the effectiveness of PREFER in language learning. The results show that our method successfully preserves both the semantic meaning and syntactic structure of the query phrase. Moreover, the students' writing performance improve most with the assistance of PREFER.
Year
Venue
Keywords
2012
BEA@NAACL-HLT
paraphrase reference tool,pivot-based paraphrase generation method,writing skill,automatic paraphrase suggestion system,language learning,language competence,graphical problem,limited language proficiency,language learner,graph-based approach,paraphrase generation problem
Field
DocType
Citations 
Graph,Language proficiency,Linguistic competence,Computer science,Phrase,Paraphrase,Language acquisition,Natural language processing,Artificial intelligence,Writing skills,Linguistics,Syntactic structure
Conference
3
PageRank 
References 
Authors
0.40
8
5
Name
Order
Citations
PageRank
Mei-Hua Chen1125.69
Shih-Ting Huang2708.56
Chung-Chi Huang3289.43
Hsien-Chin Liou4284.25
Jason S. Chang534562.64