•    Freeware
  •    Shareware
  •    Research
  •    Localization Tools 20
  •    Publications 707
  •    Validators 2
  •    Mobile Apps 22
  •    Fonts 31
  •    Guidelines/ Draft Standards 3
  •    Documents 13
  •    General Tools 38
  •    NLP Tools 105
  •    Linguistic Resources 255
  Catalogue
Evaluation of any Machine Translation (MT) system is an important step towards improving its accuracy. In this paper, we aretrying to evaluate Hindi-English module through two most widely used MT systems - Bing (Microsoft) and Google. These MTsystems are Statistics-Based MT systems (SBMT) and are capable of providing translation in many languages across the globeother than Hindi-English. For the purpose of evaluation, we tested Health and General cooking data and evaluated the Englishoutput text. Human evaluation strategy has been used for the purpose of evaluation, on the basis of which problem areas in both the MT systems were identified and compared to reach a conclusive analysis in terms of the output’s fluency and
comprehensibility. The comparative analysis helps in understanding not only which system is better but also what works best forautomatic translation and under what circumstances. The discrepancies found are discussed with some suggestions towards theirsolution

Added on March 22, 2016

48

  More Details
  • Contributed by : Atul Kr Ojha
  • Product Type : Research Paper
  • License Type : Freeware
  • System Requirement : Not Applicable
  • Author : Atul Kr. Ojha, Akanksha Bansal, Sumedh Hadke and Girish Nath Jha
Author Community Profile :

  Reviews 
By : indian April 27, 2016
Research Paper with only Abstract ? What you guys are doing ?