Dynamic programming for re-mapping noisy fixations in translation tasks

Eyetrackers which allow for free head movements are in many cases imprecise to the extent that reading patterns become heavily distorted. The poor usability and interpretability of these gaze patterns is corroborated by a "naïve" fixation-to-symbol mapping, which often wrongly maps the pos...

Full description

Saved in:
Bibliographic Details
Main Author: Michael Carl
Format: Article
Language:English
Published: MDPI AG 2013-08-01
Series:Journal of Eye Movement Research
Subjects:
Online Access:https://bop.unibe.ch/JEMR/article/view/2358
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850173112745721856
author Michael Carl
author_facet Michael Carl
author_sort Michael Carl
collection DOAJ
description Eyetrackers which allow for free head movements are in many cases imprecise to the extent that reading patterns become heavily distorted. The poor usability and interpretability of these gaze patterns is corroborated by a "naïve" fixation-to-symbol mapping, which often wrongly maps the possibly drifted center of the observed fixation onto the symbol directly below it. In this paper I extend this naïve fixation-to-symbol mapping by introducing background knowledge about the translation task. In a first step, the sequence of fixation-to-symbol mappings is extended into a lattice of several possible fixated symbols, including those on the line above and below the naïve fixation mapping. In a second step a dynamic programming algorithm applies a number of heuristics to find the best path through the lattice, based on the probable distance in characters, in words and in pixels between successive fixations and the symbol locations, so as to smooth the gazing path according to the background gazing model. A qualitative and quantitative evaluation shows that the algorithm increases the accuracy of the re-mapped symbol sequence.
format Article
id doaj-art-d181ca5b80094bf3b2c4f3fde3623361
institution OA Journals
issn 1995-8692
language English
publishDate 2013-08-01
publisher MDPI AG
record_format Article
series Journal of Eye Movement Research
spelling doaj-art-d181ca5b80094bf3b2c4f3fde36233612025-08-20T02:19:55ZengMDPI AGJournal of Eye Movement Research1995-86922013-08-016210.16910/jemr.6.2.5Dynamic programming for re-mapping noisy fixations in translation tasksMichael Carl0Copenhagen Business SchoolEyetrackers which allow for free head movements are in many cases imprecise to the extent that reading patterns become heavily distorted. The poor usability and interpretability of these gaze patterns is corroborated by a "naïve" fixation-to-symbol mapping, which often wrongly maps the possibly drifted center of the observed fixation onto the symbol directly below it. In this paper I extend this naïve fixation-to-symbol mapping by introducing background knowledge about the translation task. In a first step, the sequence of fixation-to-symbol mappings is extended into a lattice of several possible fixated symbols, including those on the line above and below the naïve fixation mapping. In a second step a dynamic programming algorithm applies a number of heuristics to find the best path through the lattice, based on the probable distance in characters, in words and in pixels between successive fixations and the symbol locations, so as to smooth the gazing path according to the background gazing model. A qualitative and quantitative evaluation shows that the algorithm increases the accuracy of the re-mapped symbol sequence.https://bop.unibe.ch/JEMR/article/view/2358fixation-to-symbol mappingdrift in gaze datadrift-correction algorithm
spellingShingle Michael Carl
Dynamic programming for re-mapping noisy fixations in translation tasks
Journal of Eye Movement Research
fixation-to-symbol mapping
drift in gaze data
drift-correction algorithm
title Dynamic programming for re-mapping noisy fixations in translation tasks
title_full Dynamic programming for re-mapping noisy fixations in translation tasks
title_fullStr Dynamic programming for re-mapping noisy fixations in translation tasks
title_full_unstemmed Dynamic programming for re-mapping noisy fixations in translation tasks
title_short Dynamic programming for re-mapping noisy fixations in translation tasks
title_sort dynamic programming for re mapping noisy fixations in translation tasks
topic fixation-to-symbol mapping
drift in gaze data
drift-correction algorithm
url https://bop.unibe.ch/JEMR/article/view/2358
work_keys_str_mv AT michaelcarl dynamicprogrammingforremappingnoisyfixationsintranslationtasks