Pauses as Indicators of Cognitive Effort in Post-editing Machine Translation Output

O’Brien, Sharon

doi:10.1556/acr.7.2006.1.1

Cited by 83 publications

(42 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It was observed that a number of data points in the present study (21%) had PR values of 1, which was also observed by O'Brien (2006). These data points represent occasions where no modification is performed in the MT output-i.e.…”

Section: Pause Ratio and Cognitive Effortsupporting

confidence: 82%

“…Recent research on cognitive effort in post-editing has primarily focused on contrasting cognitive effort with the task demands (e.g. O'Brien 2006). Among other things, correlations between these two constructs allow post-editing effort to be predicted based on specific characteristics of the source text or the MT output.…”

Section: Review Of Literaturementioning

confidence: 99%

“…Excluding all such pauses would require a detailed classification of the cognitive processes that take place during each pause, which is not straightforward based on current methods (cf. O'Brien 2006;Kumpulainen 2015). An approximation can nevertheless be achieved by excluding pauses that are not both preceded and followed by typing events in the process of working through a sentence.…”

Section: Pause Ratio and Cognitive Effortmentioning

confidence: 99%

See 2 more Smart Citations

How do measures of cognitive effort relate to each other? A multivariate analysis of post-editing process data

Vieira

2016

Machine Translation

View full text Add to dashboard Cite

There has been growing interest of late in the cognitive effort required by post-editing of machine translation. Compared to number of editing operations, cognitive (or mental) effort is frequently considered a more decisive indicator of the overall effort expended by post-editors. Estimating cognitive effort is not straightforward, however. Previous studies often triangulate different measures to obtain a consensus, but little post-editing research to date has attempted to show how measures of cognitive effort relate to each other in a multivariate analysis. This paper addresses this by presenting an exploratory comparison of cognitive measures based on eye tracking, pauses, editing time, and subjective ratings collected in a post-editing task carried out by professional and non-professional participants. All measures correlated with each other, but a principal components analysis showed that the measures cluster together in different ways. In particular, measures that increase with task time alone behaved differently from the others, with higher mutual associations and higher reliability. Regarding differences between professional and non-professional participants, it was observed that subjective ratings were overall more strongly associated with objective measures in the case of professionals. Surprising findings from previous research based on pause ratio are discussed. The paper argues that a pause typology will benefit the study of pause lengths and cognitive effort in post-editing.

show abstract

Section: Pause Ratio and Cognitive Effortsupporting

confidence: 82%

Section: Review Of Literaturementioning

confidence: 99%

Section: Pause Ratio and Cognitive Effortmentioning

confidence: 99%

See 1 more Smart Citation

How do measures of cognitive effort relate to each other? A multivariate analysis of post-editing process data

Vieira

2016

Machine Translation

View full text Add to dashboard Cite

show abstract

“…12. Yamada (2012) calculates this "baseline" as a GTM score of 0.46, which would correspond to the 70% fuzzy-match level below which O'Brien (2008) finds that translators' stress level increases (see O'Brien 2007aO'Brien , 2007b). …”

Section: Notesmentioning

confidence: 99%

Translation Skill-Sets in a Machine-Translation Age

Pym

2014

meta

149

View full text Add to dashboard Cite

Résumé de l'article L'intégration de la traduction automatique statistique (TA) aux logiciels de mémoire de traduction (MT) est en train de produire une gamme de technologies de MT/TA qui devraient remplacer dans de nombreux domaines la traduction entièrement humaine. Ce processus ouvre la voie à son tour à une transformation des compétences procédurales des traducteurs. Dans la mesure où les experts non traducteurs peuvent prendre en charge certaines tâches dans certains domaines, on s'attend à ce que les traducteurs s'occupent de plus en plus de la post-édition, sans avoir besoin de connaissances approfondies sur le contenu des textes, et éventuellement avec une insistance moindre sur la compétence dans la langue étrangère. Cette reconfiguration de l'espace traductif l'ouvre aussi aux fonctions productives des bases de données MT/TA, en sorte que l'on ne reconnaît plus l'organisation binaire autour du couple « source » et « cible » : nous avons affaire maintenant à un « texte de départ » accompagné de matériaux également de départ comme le sont les mémoires de traduction autorisées, les glossaires, les bases terminologiques et les propositions qui proviennent de la traduction automatique. Afin d'identifier les savoir-faire nécessaires pour travailler dans cet espace, on a recours ici à une approche « négative » et minimaliste : il faut tout d'abord identifier les problèmes de prise de décision qui résultent de l'emploi de des technologies MT/TA, pour ensuite essayer de décrire les compétences procédurales correspondantes. Nous proposons dix compétences de ce genre, organisées en trois groupes assez traditionnels : apprendre à apprendre, apprendre à accorder une confiance relative et raisonnée aux sources d'information, et apprendre à adapter la révision et la correction aux nécessités de la technologie. L'acquisition de ces compétences peut être favorisée par une pédagogie qui intègre les espaces adéquats pour le cours de traduction, l'emploi transversal des technologies MT/TA, l'autoanalyse des processus traductifs, ainsi que les projets collaboratifs qui font appel aux experts non traducteurs. RÉSUMÉL'intégration de la traduction automatique statistique (TA) aux logiciels de mémoire de traduction (MT) est en train de produire une gamme de technologies de MT/TA qui devraient remplacer dans de nombreux domaines la traduction entièrement humaine. Ce processus ouvre la voie à son tour à une transformation des compétences procédu-rales des traducteurs. Dans la mesure où les experts non traducteurs peuvent prendre en charge certaines tâches dans certains domaines, on s'attend à ce que les traducteurs s'occupent de plus en plus de la post-édition, sans avoir besoin de connaissances approfondies sur le contenu des textes, et éventuellement avec une insistance moindre sur la compétence dans la langue étrangère. Cette reconfiguration de l'espace traductif l'ouvre aussi aux fonctions productives des bases de données MT/TA, en sorte que l'on ne reconnaît plus l'organisation binaire autour du couple « source » et « cibl...

show abstract

“…This focus has been heightened with the increased use of other technologies such as MT and some external factors, particularly the global recession that began in 2007(DePalma et al 2013. Research on translation with TM or MT post-editing has often measured effort required by the translator (Krings 2001, O'Brien 2006, most usually using measures of productivity or temporal effort (O'Brien 2005, Carl et al 2011, as productivity is of particular industrial interest in applied translation research. Several studies used effort measures to compare translation assisted by TM and MT post-editing (Guerberof 2012).…”

Section: Introductionmentioning

confidence: 99%

Productivity and Lexical Pragmatic Features in a Contemporary CAT Environment: An Exploratory Study in English to Japanese

Moorkens

Sasamoto

2017

HJLCB

View full text Add to dashboard Cite

As the translation profession has become more technologized, translators increasingly work within an interface that combines translation from scratch, translation memory suggestions, machine translation post-editing, and terminological resources. This study analyses user activity data from one such interface, and measures temporal effort for English to Japanese translation at the segment level. Using previous studies of translation within the framework of relevance theory as a starting point, various features and edits were identified and annotated within the texts, in order to find whether there was a relationship between their prevalence and translation effort. Although this study is exploratory in nature, there was an expectation based on previous studies that procedurally encoded utterances would be associated with greater translation effort. This expectation was complicated by the choice of a language pair in which there has been little research applying relevance theory to translation, and by contemporary research that has made the distinction between procedural and conceptual encoding appear more fluid than previously believed. Our findings are that some features that lean more towards procedural encoding (such as prevalence of pronouns and manual addition of postpositions) are associated with increased temporal effort, although the small sample size makes it impossible to generalise. Segments translated with the aid of translation memory showed the least average temporal effort, and segments translated using machine translation appeared to require more effort than translation from scratch.

show abstract

Pauses as Indicators of Cognitive Effort in Post-editing Machine Translation Output

Cited by 83 publications

References 10 publications

How do measures of cognitive effort relate to each other? A multivariate analysis of post-editing process data

How do measures of cognitive effort relate to each other? A multivariate analysis of post-editing process data

Translation Skill-Sets in a Machine-Translation Age

Productivity and Lexical Pragmatic Features in a Contemporary CAT Environment: An Exploratory Study in English to Japanese

Contact Info

Product

Resources

About