Vicinity-driven paragraph and sentence alignment for comparable corpora

File Description SizeFormat 
1612.04113v1.pdfWorking paper65.49 kBAdobe PDFView/Open
Title: Vicinity-driven paragraph and sentence alignment for comparable corpora
Authors: Paetzold, GH
Specia, L
Item Type: Working Paper
Abstract: Parallel corpora have driven great progress in the field of Text Simplification. However, most sentence alignment algorithms either offer a limited range of alignment types supported, or simply ignore valuable clues present in comparable documents. We address this problem by introducing a new set of flexible vicinity-driven paragraph and sentence alignment algorithms that 1-N, N-1, N-N and long distance null alignments without the need for hard-to-replicate supervised models.
Issue Date: 13-Dec-2016
URI: http://hdl.handle.net/10044/1/63805
Publisher: arXiv
Copyright Statement: © The Authors.
Keywords: cs.CL
Publication Status: Published
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx