Show simple item record

dc.contributorRuiz Costa-Jussà, Marta
dc.contributor.authorEscudé Font, Joel
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2019-01-31T11:49:12Z
dc.date.available2019-01-31T11:49:12Z
dc.date.issued2019-01
dc.identifier.urihttp://hdl.handle.net/2117/128025
dc.description.abstractThe presence of biases in artificial intelligence is arising as a social challenge. In the particular application of machine translation, when you translate a sentence to a non-gender neutral language like Spanish, from a less gender neutral language like English, the model makes a guess on the gender of the subject. These models are trained on available large text corpora which contains biases and stereotypes. As a consequence, models inherit these social constructs. An example of this is the fact that "friend" in the English sentence "She works in a hospital, my friend is a nurse" would be correctly translated to "amiga" (feminine of friend) in Spanish, while "She works in a hospital, my friend is a doctor" would be incorrectly translated to "amigo" (masculine of friend) in Spanish. An experimental setting is defined, we use a set of debiased pre-trained word embeddings, vector representation of words, in the Transformer, a neural network architecture for machine translation, to study how debiasing affects the translation models. We show that the performance of the models is not compromised for debiased embeddings and the proposed system learns to neutralize previously existing biases.
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshArtificial intelligence
dc.subject.otherComputational linguistics
dc.subject.otherMachine translation
dc.subject.otherDeep learning
dc.subject.otherMachine learning
dc.subject.otherArtificial intelligence
dc.subject.otherBias
dc.subject.otherDebiasing
dc.subject.otherWord embeddings
dc.subject.otherTransformer
dc.subject.otherNatural language processing
dc.subject.otherNeural machine translation
dc.subject.otherAi
dc.subject.otherNlp
dc.subject.otherNmt
dc.subject.otherGlove
dc.titleDetermining Bias in Machine Translation with Deep Learning Techniques
dc.typeMaster thesis
dc.subject.lemacIntel·ligència artificial
dc.subject.amsClassificació AMS::68 Computer science::68T Artificial intelligence
dc.identifier.slugFME-1698
dc.rights.accessOpen Access
dc.date.updated2019-01-23T06:25:51Z
dc.audience.educationlevelMàster
dc.audience.mediatorUniversitat Politècnica de Catalunya. Facultat de Matemàtiques i Estadística


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-ShareAlike 3.0 Spain