Work

Comparing Phrase-based and Syntax-based Paraphrase Generation

Year: 2011

Type: article

Abstract: Paraphrase generation can be regarded as machine translation where source and target language are the same. We use the Moses statistical machine translation toolkit for paraphrasing, comparing phrase-based to syntax-based approaches. Data is derived from a recently released, large scale (2.1M tokens) paraphrase corpus for Dutch. Preliminary results indicate that the phrase-based approach performs better in terms of NIST scores and produces paraphrases at a greater distance from the source. 1

Authors: Sander Wubben, Erwin Marsi, Antal van den Bosch, Emiel Krahmer

Institutions: Tilburg University, Norwegian University of Science and Technology

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1508161424

FWCI: 0.525

Cites: 33

Cited by: 2

Related to: 10