Learning Language-Specific Layers for Multilingual Machine Translation

• URL: http://arxiv.org/abs/2305.02665v1
• Date: Thu, 4 May 2023 09:18:05 GMT
• Title: Learning Language-Specific Layers for Multilingual Machine Translation
• Authors: Telmo Pessoa Pires, Robin M. Schmidt, Yi-Hsiu Liao, Stephan Peitz
• Abstract summary: We introduce Language-Specific Transformer Layers (LSLs) LSLs allow us to increase model capacity, while keeping the amount of computation and the number of parameters used in the forward pass constant. We study the best way to place these layers using a neural architecture search inspired approach, and achieve an improvement of 1.3 chrF (1.5 spBLEU) points over not using LSLs on a separate decoder architecture, and 1.9 chrF (2.2 spBLEU) on a shared decoder one.
• Score: 1.997704019887898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding losing gender and formality information when translating through English). On the downside, adding more languages reduces model capacity per language, which is usually countered by increasing the overall model size, making training harder and inference slower. In this work, we introduce Language-Specific Transformer Layers (LSLs), which allow us to increase model capacity, while keeping the amount of computation and the number of parameters used in the forward pass constant. The key idea is to have some layers of the encoder be source or target language-specific, while keeping the remaining layers shared. We study the best way to place these layers using a neural architecture search inspired approach, and achieve an improvement of 1.3 chrF (1.5 spBLEU) points over not using LSLs on a separate decoder architecture, and 1.9 chrF (2.2 spBLEU) on a shared decoder one.

Related papers

• On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation [104.85258654917297]
  We find that failing in encoding discriminative target language signal will lead to off-target and a closer lexical distance. We propose Language Aware Vocabulary Sharing (LAVS) to construct the multilingual vocabulary. We conduct experiments on a multilingual machine translation benchmark in 11 languages.
  arXiv  Detail & Related papers  (2023-05-18T12:43:31Z)
• Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders [77.2101943305862]
  We propose a deep encoder with multiple shallow decoders (DEMSD) where each shallow decoder is responsible for a disjoint subset of target languages. DEMSD model with 2-layer decoders is able to obtain a 1.8x speedup on average compared to a standard transformer model with no drop in translation quality.
  arXiv  Detail & Related papers  (2022-06-05T01:15:04Z)
• Examining Scaling and Transfer of Language Model Architectures for Machine Translation [51.69212730675345]
  Language models (LMs) process sequences in a single stack of layers, and encoder-decoder models (EncDec) utilize separate layer stacks for input and output processing. In machine translation, EncDec has long been the favoured approach, but with few studies investigating the performance of LMs.
  arXiv  Detail & Related papers  (2022-02-01T16:20:15Z)
• Breaking Down Multilingual Machine Translation [74.24795388967907]
  We show that multilingual training is beneficial to encoders in general, while it only benefits decoders for low-resource languages (LRLs) Our many-to-one models for high-resource languages and one-to-many models for LRLs outperform the best results reported by Aharoni et al.
  arXiv  Detail & Related papers  (2021-10-15T14:57:12Z)
• Adapting Monolingual Models: Data can be Scarce when Language Similarity is High [3.249853429482705]
  We investigate the performance of zero-shot transfer learning with as little data as possible. We retrain the lexical layers of four BERT-based models using data from two low-resource target language varieties. With high language similarity, 10MB of data appears sufficient to achieve substantial monolingual transfer performance.
  arXiv  Detail & Related papers  (2021-05-06T17:43:40Z)
• Improving Zero-Shot Translation by Disentangling Positional Information [24.02434897109097]
  We show that a main factor causing the language-specific representations is the positional correspondence to input tokens. We gain up to 18.5 BLEU points on zero-shot translation while retaining quality on supervised directions.
  arXiv  Detail & Related papers  (2020-12-30T12:20:41Z)
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [105.41167108465085]
  Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages. We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC) LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language. We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
  arXiv  Detail & Related papers  (2020-10-27T13:12:17Z)
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation [81.7786241489002]
  Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics. We propose random online backtranslation to enforce the translation of unseen training language pairs.
  arXiv  Detail & Related papers  (2020-04-24T17:21:32Z)

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.