Iappraise: A manual machine translation evaluation environment supporting eye-tracking

Ahmed Abdelali, Nadir Durrani, Francisco Guzmán

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

We present iAppraise: An open-source framework that enables the use of eye-tracking for MT evaluation. It connects Appraise, an opensource toolkit for MT evaluation, to a low-cost eye-tracking device, to make its usage accessible to a broader audience. It also provides a set of tools for extracting and exploiting gaze data, which facilitate eye-tracking analysis. In this paper, we describe different modules of the framework, and explain how the tool can be used in a MT evaluation scenario. During the demonstration, the users will be able to perform an evaluation task, observe their own reading behavior during a replay of the session, and export and extract features from the data.

Original languageEnglish
Pages17-21
Number of pages5
Publication statusPublished - 2016
Event2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2016 - San Diego, United States
Duration: 12 Jun 201617 Jun 2016

Conference

Conference2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2016
Country/TerritoryUnited States
CitySan Diego
Period12/06/1617/06/16

Fingerprint

Dive into the research topics of 'Iappraise: A manual machine translation evaluation environment supporting eye-tracking'. Together they form a unique fingerprint.

Cite this