Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation

05/22/2023
by   Wen Lai, et al.
0

Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration. The data imbalance problem refers to the imbalance in the amount of parallel corpora for all language pairs, especially for long-tail languages (i.e., very low-resource languages). The representation degeneration problem refers to the problem of encoded tokens tending to appear only in a small subspace of the full space available to the MNMT model. To solve these two issues, we propose Bi-ACL, a framework that uses only target-side monolingual data and a bilingual dictionary to improve the performance of the MNMT model. We define two modules, named bidirectional autoencoder and bidirectional contrastive learning, which we combine with an online constrained beam search and a curriculum learning sampling strategy. Extensive experiments show that our proposed method is more effective both in long-tail languages and in high-resource languages. We also demonstrate that our approach is capable of transferring knowledge between domains and languages in zero-shot scenarios.

READ FULL TEXT
research
09/09/2021

Competence-based Curriculum Learning for Multilingual Machine Translation

Currently, multilingual machine translation is receiving more and more a...
research
10/20/2022

SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages

In recent years, multilingual machine translation models have achieved p...
research
05/20/2019

Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation

To improve low-resource Neural Machine Translation (NMT) with multilingu...
research
04/29/2022

How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?

A multilingual tokenizer is a fundamental component of multilingual neur...
research
05/11/2023

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models

Large language models (LLMs) have shown surprisingly good performance in...
research
09/09/2021

Distributionally Robust Multilingual Machine Translation

Multilingual neural machine translation (MNMT) learns to translate multi...
research
09/28/2022

Multilingual Transitivity and Bidirectional Multilingual Agreement for Multilingual Document-level Machine Translation

Multilingual machine translation has been proven an effective strategy t...

Please sign up or login with your details

Forgot password? Click here to reset