Itzulpen Automatikoko Sistemen Analisia: Genero Alborapenaren Kasua

Abstract

Lan honen helburua euskal komunitatean oso erabiliak diren hiru itzultzaile automatikoek generoa nola tratatzenduten aztertzea da. Tresna komertzial hauek geroz eta erabiliagoak direnez, ezinbestekoa da ikustea zein dengizartean dauden estereotipoen birsorkuntzan duten rola. Analisi honetan ogibide ezberdinetan aurki daitezkeengenero alborapenak aztertu dira, genero marka modu ezberdinetan erabiltzen duten bi hizkuntza erabiliz: euskara(genero marka neutroa duena) eta gaztelera (generoa ezberdintzen dituen markak erabiltzen dituena). Itzulpennorabideak eta jatorrizko esaldiaren testuinguruak itzulpenetan zein eragin duten aztertu da.Esperimentuhauei esker, nabarian gelditu da nola generoa esplizitua egitea ez den nahikoa alborapenak ebazteko. Albora-pen hauen nabarmentzea kalitate handiagoko eta bidezkoagoa den agertoki baterako lehen pauso bezala ikusten da.

The aim of this work is to analyze the gender bias in three automatic translation systems widely used by theBasque community. As these commercial tools have become more popular, it is essential to see what role they playin the recreation of stereotypes defined in society. In this analysis, the gender bias found in different professionshas been studied using two languages that treat gender differently: basque (which has a neutral gender mark)and spanish (which uses marks that differentiate gender). The impact of the contextual information in the originalsentence and the effect of the translation directions have been analyzed. These experiments have shown how usingcontextual information for making gender explicit is not enough for resolving gender bias. Highlighting thesebiases is seen as a priority towards higher quality translations and a fairer scenario.