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

• URL: http://arxiv.org/abs/2204.14268v1
• Date: Fri, 29 Apr 2022 17:50:36 GMT
• Title: How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?
• Authors: Shiyue Zhang, Vishrav Chaudhary, Naman Goyal, James Cross, Guillaume Wenzek, Mohit Bansal, Francisco Guzman
• Abstract summary: We analyze how translation performance changes as the data ratios among languages vary in the tokenizer training corpus. We find that while relatively better performance is often observed when languages are more equally sampled, the downstream performance is more robust to language imbalance than we usually expected.
• Score: 86.48323488619629
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to balance languages in the corpus. However, few works have systematically answered how language imbalance in tokenizer training affects downstream performance. In this work, we analyze how translation performance changes as the data ratios among languages vary in the tokenizer training corpus. We find that while relatively better performance is often observed when languages are more equally sampled, the downstream performance is more robust to language imbalance than we usually expected. Two features, UNK rate and closeness to the character level, can warn of poor downstream performance before performing the task. We also distinguish language sampling for tokenizer training from sampling for model training and show that the model is more sensitive to the latter.

Related papers

• The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments [57.273662221547056]
  In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. We observe that the existence of a predominant language during training boosts the performance of less frequent languages. As we extend our analysis to real languages, we find that infrequent languages still benefit from frequent ones, yet whether language imbalance causes cross-lingual generalisation there is not conclusive.
  arXiv  Detail & Related papers  (2024-04-11T17:58:05Z)
• Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages [0.34998703934432673]
  We build a single-decoder neural machine translation system for Dravidian-Dravidian multilingual translation. Our model achieves scores within 3 BLEU of large-scale pivot-based models when it is trained on 50% of the language directions.
  arXiv  Detail & Related papers  (2023-08-10T13:38:09Z)
• Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios [4.631167282648452]
  We tackle the task of automatically discriminating between human and machine translations. We perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained language models.
  arXiv  Detail & Related papers  (2023-05-31T11:41:24Z)
• Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve [78.3500985535601]
  We find a surprising connection between multitask learning and robustness to neuron failures. Our experiments show that bilingual language models retain higher performance under various neuron perturbations. We provide a theoretical justification for this robustness by mathematically analyzing linear representation learning.
  arXiv  Detail & Related papers  (2022-10-20T22:23:27Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• Analysing The Impact Of Linguistic Features On Cross-Lingual Transfer [3.299672391663527]
  We analyze a state-of-the-art multilingual model and try to determine what impacts good transfer between languages. We show that looking at particular syntactic features is 2-4 times more helpful in predicting the performance than an aggregated syntactic similarity.
  arXiv  Detail & Related papers  (2021-05-12T21:22:58Z)
• Improving Cross-Lingual Reading Comprehension with Self-Training [62.73937175625953]
  Current state-of-the-art models even surpass human performance on several benchmarks. Previous works have revealed the abilities of pre-trained multilingual models for zero-shot cross-lingual reading comprehension. This paper further utilized unlabeled data to improve the performance.
  arXiv  Detail & Related papers  (2021-05-08T08:04:30Z)
• Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training [45.48003947488825]
  We study two widely used robust training methods: adversarial training and randomized smoothing. The experimental results demonstrate that robust training can improve zero-shot cross-lingual transfer for text classification.
  arXiv  Detail & Related papers  (2021-04-17T21:21:53Z)
• Balancing Training for Multilingual Neural Machine Translation [130.54253367251738]
  multilingual machine translation (MT) models can translate to/from multiple languages. Standard practice is to up-sample less resourced languages to increase representation. We propose a method that instead automatically learns how to weight training data through a data scorer.
  arXiv  Detail & Related papers  (2020-04-14T18:23:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.