Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/51960
Title: Automatic Evaluation of Machine Translation, Paraphrase Generation, and Summarization: A Linear-programming-based Analysis
Authors: LIU CHANG
Keywords: natural language process, automatic evaluation, machine translation evaluation, paraphrase evaluation, summarization evaluation, linear programming
Issue Date: 27-Aug-2013
Source: LIU CHANG (2013-08-27). Automatic Evaluation of Machine Translation, Paraphrase Generation, and Summarization: A Linear-programming-based Analysis. ScholarBank@NUS Repository.
Abstract: Automatic evaluations form an important part of Natural Language Processing (NLP) research. Despite their success, the mathematical foundations of most current automatic evaluation metrics are capable of modeling only simple features of n-gram matching, such as exact matches ? possibly after pre-processing ? and single word synonyms. We instead base our proposal TESLA on the very versatile linear programming formulation, which allows fractional n-gram weights and fractional similarity measures and is efficiently solvable. Variants of TESLA are devised for many different evaluation tasks: TESLA-M, TESLA-B, and TESLA-F for the machine translation evaluation of European languages, TESLA-CELAB for the machine translation evaluation of languages with ambiguous word boundaries such as Chinese, TESLA-PEM for paraphrase evaluation, and TESLA-S for summarization evaluation. Experiments show that they are very competitive on the standard test sets in their respective tasks, as measured by correlations with human judgments.
URI: http://scholarbank.nus.edu.sg/handle/10635/51960
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
liuchang2013automatic.pdf646.02 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

152
checked on Jan 19, 2018

Download(s)

160
checked on Jan 19, 2018

Google ScholarTM

Check


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