Determining Bias in Machine Translation with Deep Learning Techniques

The 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 gend...

Descripción completa

Detalles Bibliográficos
Autor: Escudé Font, Joel
Tipo de recurso: tesis de maestría
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/128025
Acceso en línea:https://hdl.handle.net/2117/128025
Access Level:acceso abierto
Palabra clave:Artificial intelligence
Computational linguistics
Machine translation
Deep learning
Machine learning
Bias
Debiasing
Word embeddings
Transformer
Natural language processing
Neural machine translation
Ai
Nlp
Nmt
Glove
Intel·ligència artificial
Classificació AMS::68 Computer science::68T Artificial intelligence
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descripción
Sumario:The 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.