MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation

• URL: http://arxiv.org/abs/2411.01474v2
• Date: Fri, 07 Feb 2025 04:10:36 GMT
• Title: MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation
• Authors: Langlin Huang, Mengyu Bu, Yang Feng,
• Abstract summary: Byte-based machine translation systems have shown significant potential in massively multilingual settings. Unicode encoding maps each character to specific byte(s) eliminating 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 Mixture of Contextualization Experts (MoCE), adaptively selecting and mixing attention heads, which are treated as contextualization experts.
• Score: 13.70446799743065
• License:
• Abstract: 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. This avoids out-of-vocabulary risk in multilingual translation and enables broad language scalability. However, byte-level tokenization results in sequences that are hard to interpret due to limited semantic information per byte. Local contextualization has proven effective in assigning initial semantics to tokens, improving sentence comprehension. Nevertheless, variations in encoding rules across languages necessitate an adaptive approach for effective contextualization. To this end, we propose Mixture of Contextualization Experts (MoCE), adaptively selecting and mixing attention heads, which are treated as contextualization experts. This enhances the flexibility of contextualization scales and allows models to search for better contextualization combinations. Experiment results show that our method outperforms existing methods without extensive manual adjustment of hyper-parameters and surpasses subword-based models with fewer parameters in Ted-59 dataset. Our code is available at https://github.com/ictnlp/MoCE.

Related papers

• LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation [43.26446958873554]
  Large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. LandeRMT is a framework that selectively finetunes LLMs to textbfMachine textbfTranslation with diverse translation training data.
  arXiv  Detail & Related papers  (2024-09-29T02:39:42Z)
• MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization [81.83460411131931]
  In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. We propose multilingual adaptive gradient-based tokenization to reduce over-segmentation via adaptive gradient-based subword tokenization.
  arXiv  Detail & Related papers  (2024-07-11T18:59:21Z)
• Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation [14.826948179996695]
  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.
  arXiv  Detail & Related papers  (2024-05-29T17:19:04Z)
• A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching [60.51839859852572]
  We propose to resolve the text into multi concepts for multilingual semantic matching to liberate the model from the reliance on NER models. We conduct comprehensive experiments on English datasets QQP and MRPC, and Chinese dataset Medical-SM.
  arXiv  Detail & Related papers  (2024-03-05T13:55:16Z)
• 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)
• Exposing Cross-Lingual Lexical Knowledge from Multilingual Sentence Encoders [85.80950708769923]
  We probe multilingual language models for the amount of cross-lingual lexical knowledge stored in their parameters, and compare them against the original multilingual LMs. We also devise a novel method to expose this knowledge by additionally fine-tuning multilingual models. We report substantial gains on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-30T13:23:16Z)
• To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP [0.0]
  We investigate three categories of text augmentation methodologies which perform changes on the syntax. We compare them on part-of-speech tagging, dependency parsing and semantic role labeling for a diverse set of language families. Our results suggest that the augmentation techniques can further improve over strong baselines based on mBERT.
  arXiv  Detail & Related papers  (2021-11-18T10:52:48Z)
• Evaluating the Morphosyntactic Well-formedness of Generated Texts [88.20502652494521]
  We propose L'AMBRE -- a metric to evaluate the morphosyntactic well-formedness of text. We show the effectiveness of our metric on the task of machine translation through a diachronic study of systems translating into morphologically-rich languages.
  arXiv  Detail & Related papers  (2021-03-30T18:02:58Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)
• Intrinsic Probing through Dimension Selection [69.52439198455438]
  Most modern NLP systems make use of pre-trained contextual representations that attain astonishingly high performance on a variety of tasks. Such high performance should not be possible unless some form of linguistic structure inheres in these representations, and a wealth of research has sprung up on probing for it. In this paper, we draw a distinction between intrinsic probing, which examines how linguistic information is structured within a representation, and the extrinsic probing popular in prior work, which only argues for the presence of such information by showing that it can be successfully extracted.
  arXiv  Detail & Related papers  (2020-10-06T15:21:08Z)

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.