Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation

• URL: http://arxiv.org/abs/2405.19290v3
• Date: Sun, 11 Aug 2024 06:48:40 GMT
• Title: Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation
• Authors: Langlin Huang, Yang Feng,
• Abstract summary: Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. We propose the Multi-Scale Contextualization (MSC) method, which learns contextualized information of varying scales across different hidden state dimensions. Experiments show that MSC significantly outperforms subword-based and other byte-based methods in both multilingual and out-of-domain scenarios.
• Score: 14.826948179996695
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned, making it hard to adapt to new words. Second, in multilingual translation, the imbalance in data volumes across different languages spreads to the vocabulary, exacerbating translations involving low-resource languages. While byte-based tokenization addresses these issues, byte-based models struggle with the low information density inherent in UTF-8 byte sequences. Previous works enhance token semantics through local contextualization but fail to select an appropriate contextualizing scope based on the input. Consequently, we propose the Multi-Scale Contextualization (MSC) method, which learns contextualized information of varying scales across different hidden state dimensions. It then leverages the attention module to dynamically integrate the multi-scale contextualized information. Experiments show that MSC significantly outperforms subword-based and other byte-based methods in both multilingual and out-of-domain scenarios. Code can be found in https://github.com/ictnlp/Multiscale-Contextualization.

Related papers

• MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation [13.70446799743065]
  Byte-based machine translation systems have shown significant potential in massively multilingual settings. Unicode encoding, which maps each character to specific byte(s), eliminates the emergence of unknown words, even in new languages. Local contextualization has proven effective in assigning initial semantics to tokens, improving sentence comprehension. We propose Adaptive MultiScale-Headed Attention (Ada-MSHA), adaptively selecting and mixing attention heads, which are treated as contextualization experts.
  arXiv  Detail & Related papers  (2024-11-03T08:15:43Z)
• Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation [9.794506112999823]
  In this paper, we define word-level information transfer pathways via word equivalence classes and rely on graph networks to fuse word embeddings across languages. Our experiments demonstrate the advantages of our approach: 1) embeddings of words with similar meanings are better aligned across languages, 2) our method achieves consistent BLEU improvements of up to 2.3 points for high- and low-resource MNMT, and 3) less than 1.0% additional trainable parameters are required with a limited increase in computational costs.
  arXiv  Detail & Related papers  (2023-05-23T16:11:00Z)
• Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation [103.90963418039473]
  Bi-ACL is a framework that uses only target-side monolingual data and a bilingual dictionary to improve the performance of the MNMT model. We show that Bi-ACL is more effective both in long-tail languages and in high-resource languages.
  arXiv  Detail & Related papers  (2023-05-22T07:31:08Z)
• Romanization-based Large-scale Adaptation of Multilingual Language Models [124.57923286144515]
  Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. We study and compare a plethora of data- and parameter-efficient strategies for adapting the mPLMs to romanized and non-romanized corpora of 14 diverse low-resource languages. Our results reveal that UROMAN-based transliteration can offer strong performance for many languages, with particular gains achieved in the most challenging setups.
  arXiv  Detail & Related papers  (2023-04-18T09:58:34Z)
• Local Byte Fusion for Neural Machine Translation [19.16966721276286]
  Subword tokenization schemes are the dominant technique used in current NLP models. Byte-based methods i.e. tokenization into byte sequences are an alternative. Experiments on multilingual translation, zero-shot cross-lingual transfer, and domain adaptation reveal a consistent improvement over traditional models.
  arXiv  Detail & Related papers  (2022-05-23T17:49:02Z)
• Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding [90.87454350016121]
  We develop novel code-switching schemes to generate hard negative examples for contrastive learning at all levels. We develop a label-aware joint model to leverage label semantics for cross-lingual knowledge transfer.
  arXiv  Detail & Related papers  (2022-05-07T13:44:28Z)
• Continual Learning in Multilingual NMT via Language-Specific Embeddings [92.91823064720232]
  It consists in replacing the shared vocabulary with a small language-specific vocabulary and fine-tuning the new embeddings on the new language's parallel data. Because the parameters of the original model are not modified, its performance on the initial languages does not degrade.
  arXiv  Detail & Related papers  (2021-10-20T10:38:57Z)
• Mixed Attention Transformer for LeveragingWord-Level Knowledge to Neural Cross-Lingual Information Retrieval [15.902630454568811]
  We propose a novel Mixed Attention Transformer (MAT) that incorporates external word level knowledge, such as a dictionary or translation table. By encoding the translation knowledge into an attention matrix, the model with MAT is able to focus on the mutually translated words in the input sequence.
  arXiv  Detail & Related papers  (2021-09-07T00:33:14Z)
• Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation [53.22775597051498]
  We present a continual pre-training framework on mBART to effectively adapt it to unseen languages. Results show that our method can consistently improve the fine-tuning performance upon the mBART baseline. Our approach also boosts the performance on translation pairs where both languages are seen in the original mBART's pre-training.
  arXiv  Detail & Related papers  (2021-05-09T14:49:07Z)
• Sparsely Factored Neural Machine Translation [3.4376560669160394]
  A standard approach to incorporate linguistic information to neural machine translation systems consists in maintaining separate vocabularies for each of the annotated features. We propose a method suited for such a case, showing large improvements in out-of-domain data, and comparable quality for the in-domain data. Experiments are performed in morphologically-rich languages like Basque and German, for the case of low-resource scenarios.
  arXiv  Detail & Related papers  (2021-02-17T18:42:00Z)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)

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.