Cross-lingual Word Embeddings beyond Zero-shot Machine Translation

11/03/2020
by   Shifei Chen, et al.
0

We explore the transferability of a multilingual neural machine translation model to unseen languages when the transfer is grounded solely on the cross-lingual word embeddings. Our experimental results show that the translation knowledge can transfer weakly to other languages and that the degree of transferability depends on the languages' relatedness. We also discuss the limiting aspects of the multilingual architectures that cause weak translation transfer and suggest how to mitigate the limitations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/01/2019

Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation

The recently proposed massively multilingual neural machine translation ...
research
03/11/2021

Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings

In this work we look into adding a new language to a multilingual NMT sy...
research
09/09/2021

Subword Mapping and Anchoring across Languages

State-of-the-art multilingual systems rely on shared vocabularies that s...
research
05/23/2022

Local Byte Fusion for Neural Machine Translation

Subword tokenization schemes are the dominant technique used in current ...
research
02/25/2022

The Reality of Multi-Lingual Machine Translation

Our book "The Reality of Multi-Lingual Machine Translation" discusses th...
research
05/23/2023

Pixel Representations for Multilingual Translation and Data-efficient Cross-lingual Transfer

We introduce and demonstrate how to effectively train multilingual machi...
research
12/10/2019

Machine Translation with Cross-lingual Word Embeddings

Learning word embeddings using distributional information is a task that...

Please sign up or login with your details

Forgot password? Click here to reset