Description

• Title:
  Comparison and Adaptation of Automatic Evaluation Metrics for Quality Assessment of Re-Speaking
• Creator:
  Wołk, Krzysztof;
  Koržinek, Danijel
• Description:
  Re-speaking is a mechanism for obtaining high quality subtitles for use in livebroadcast and other public events. Because it relies on humans performing theactual re-speaking, the task of estimating the quality of the results is non-trivial.Most organisations rely on humans to perform the actual quality assessment,but purely automatic methods have been developed for other similar problems,like Machine Translation. This paper will try to compare several of thesemethods: BLEU, EBLEU, NIST, METEOR, METEOR-PL, TER and RIBES.These will then be matched to the human-derived NER metric, commonly usedin re-speaking.
• Object availability:
  free access
• Rights:
  Copyright (c) 2017 Computer Science
• Date:
  2017.06.23
• Type:
  info:eu-repo/semantics/article;
  info:eu-repo/semantics/publishedVersion;
  Peer-reviewed Article
• Language:
  English
• Source:
  Computer Science; Vol. 18 No. 2; 129;
  2300-7036;
  1508-2806
• Format:
  application/pdf
• Publisher:
  AGH University of Krakow, Faculty of Computer Science
• Relation: https://journals.agh.edu.pl/csci/article/view/1858/1743
• Subject:
  evaluation metrics;
  speech;
  respeaking;
  machine translation;
  evaulation
• Identifier: https://journals.agh.edu.pl/csci/article/view/1858 ;
  10.7494/csci.2017.18.2.129
• Data provider:
  AGH University of Science and Technology Journals
• Can I use it?:
  seek permission
• Type:
  text