Improving multilingual NMT by projecting language representations

Machine Translation (MT), is one of the most important tasks related to natural language processing which facilitates seamless communication across different languages by automating the translation process, thereby significantly reducing communication costs. In this context, a multilingual neural ma...

Descripción completa

Detalles Bibliográficos
Autor: García Gilabert, Javier
Tipo de recurso: tesis de maestría
Fecha de publicación:2024
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:2117/416255
Acceso en línea:https://hdl.handle.net/2117/416255
Access Level:acceso abierto
Palabra clave:Machine translating
Artificial intelligence
traducció automàtica
representacions agnòstiques
machine translation
agnostic representations
Traducció automàtica
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descripción
Sumario:Machine Translation (MT), is one of the most important tasks related to natural language processing which facilitates seamless communication across different languages by automating the translation process, thereby significantly reducing communication costs. In this context, a multilingual neural machine translation (MNMT) system emerges as a cost-effective solution, capable of handling translations across multiple language pairs. An interesting property of MNMT systems is their ability to perform zero-shot translation, where the model translates between language pairs it has not explicitly seen before. This feature is particularly promising as it could potentially reduce the extensive resources and parameters typically required for MNMT models. Traditionally, MNMT models were thought to utilize a representation space independent of any specific language. This interlingua representation would allow the model to encode phrases conveying the same meaning similarly, regardless of the language, thereby aiding the translation process. However, in practice, it has been shown that this interlingua representation space is not as robust as previously assumed. In this project, we aim to study how MNMT representations still exhibit language dependent information and devise techniques to improve the model's representation. To achieve this goal, we propose some methods based on language projections.