Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation

• URL: http://arxiv.org/abs/2004.04002v2
• Date: Wed, 9 Dec 2020 08:03:58 GMT
• Title: Transfer learning and subword sampling for asymmetric-resource one-to-many neural translation
• Authors: Stig-Arne Gr\"onroos and Sami Virpioja and Mikko Kurimo
• Abstract summary: Methods for improving neural machine translation for low-resource languages are reviewed. Tests are carried out on three artificially restricted translation tasks and one real-world task. Experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.
• Score: 14.116412358534442
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There are several approaches for improving neural machine translation for low-resource languages: Monolingual data can be exploited via pretraining or data augmentation; Parallel corpora on related language pairs can be used via parameter sharing or transfer learning in multilingual models; Subword segmentation and regularization techniques can be applied to ensure high coverage of the vocabulary. We review these approaches in the context of an asymmetric-resource one-to-many translation task, in which the pair of target languages are related, with one being a very low-resource and the other a higher-resource language. We test various methods on three artificially restricted translation tasks -- English to Estonian (low-resource) and Finnish (high-resource), English to Slovak and Czech, English to Danish and Swedish -- and one real-world task, Norwegian to North S\'ami and Finnish. The experiments show positive effects especially for scheduled multi-task learning, denoising autoencoder, and subword sampling.

Related papers

• Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese [54.00582760714034]
  Cross-lingual NLP transfer can be improved by exploiting data and models of high-resource languages. We release a new web corpus of Faroese and Faroese datasets for named entity recognition (NER), semantic text similarity (STS) and new language models trained on all Scandinavian languages.
  arXiv  Detail & Related papers  (2023-04-18T08:42:38Z)
• Progressive Sentiment Analysis for Code-Switched Text Data [26.71396390928905]
  We focus on code-switched sentiment analysis where we have a labelled resource-rich language dataset and unlabelled code-switched data. We propose a framework that takes the distinction between resource-rich and low-resource language into account.
  arXiv  Detail & Related papers  (2022-10-25T23:13:53Z)
• Low-resource Neural Machine Translation with Cross-modal Alignment [15.416659725808822]
  We propose a cross-modal contrastive learning method to learn a shared space for all languages. Experimental results and further analysis show that our method can effectively learn the cross-modal and cross-lingual alignment with a small amount of image-text pairs.
  arXiv  Detail & Related papers  (2022-10-13T04:15:43Z)
• High-resource Language-specific Training for Multilingual Neural Machine Translation [109.31892935605192]
  We propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder. HLT-MT is further trained on all available corpora to transfer knowledge from high-resource languages to low-resource languages.
  arXiv  Detail & Related papers  (2022-07-11T14:33:13Z)
• Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model [16.872474334479026]
  We propose a simple refinement procedure to disentangle languages from a pre-trained multilingual UMT model. Our method achieves the state of the art in the fully unsupervised translation tasks of English to Nepali, Sinhala, Gujarati, Latvian, Estonian and Kazakh.
  arXiv  Detail & Related papers  (2022-05-31T05:14:50Z)
• Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data [40.11208706647032]
  The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and adversarial objectives to utilize monolingual data for low-resource adaptation.
  arXiv  Detail & Related papers  (2021-05-31T16:01:18Z)
• Extremely low-resource machine translation for closely related languages [0.0]
  This work focuses on closely related languages from the Uralic language family: from Estonian and Finnish. We find that multilingual learning and synthetic corpora increase the translation quality in every language pair. We show that transfer learning and fine-tuning are very effective for doing low-resource machine translation and achieve the best results.
  arXiv  Detail & Related papers  (2021-05-27T11:27:06Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora [63.5286019659504]
  We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus. Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
  arXiv  Detail & Related papers  (2020-10-27T22:24:01Z)
• 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)
• Cross-lingual, Character-Level Neural Morphological Tagging [57.0020906265213]
  We train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model.
  arXiv  Detail & Related papers  (2017-08-30T08:14:34Z)

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.