mlsanityData to 14 Oct 2026

Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding

arXiv 2305.12371 ↗First posted 21 May 2023cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the morphologies of the two languages and also the morphosyntax transfer. Even so, their performance for translation in Indian language to Indian language scenario is still not as good as for resource-rich languages. One reason for this is the relative morphological richness of Indian languages, while another is that most of them fall into the extremely low resource or zero-shot categories. Since most major Indian languages use Indic or Brahmi origin scripts, the text written in them is highly phonetic in nature and phonetically similar in terms of abstract letters and their arrangements. We use these characteristics of Indian languages and their scripts to propose an approach based on common multilingual Latin-based encodings (WX notation) that take advantage of language similarity while addressing the morphological complexity issue in NMT. These multilingual Latin-based encodings in NMT, together with Byte Pair Embedding (BPE) allow us to better exploit their phonetic and orthographic as well as lexical similarities to improve the translation quality by projecting different but similar languages on the same orthographic-phonetic character space. We verify the proposed approach by demonstrating experiments on similar language pairs (Gujarati-Hindi, Marathi-Hindi, Nepali-Hindi, Maithili-Hindi, Punjabi-Hindi, and Urdu-Hindi) under low resource conditions. The proposed approach shows an improvement in a majority of cases, in one case as much as ~10 BLEU points compared to baseline techniques for similar language pairs. We also get up to ~1 BLEU points improvement on distant and zero-shot language pairs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 83 references that are in the map. First posted on arXiv 21 May 2023.

Builds on

23 of 83 references.

References · 23

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  6. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  7. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  8. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  9. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  10. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  11. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  12. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
11 more
  1. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  2. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  3. 2020Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translationcited by 43
  4. 2020PMIndia -- A Collection of Parallel Corpora of Languages of Indiacited by 42
  5. 2021IndicBART: A Pre-trained Model for Indic Natural Language Generationcited by 39
  6. 2020Revisiting Low Resource Status of Indian Languages in Machine Translationcited by 12
  7. 2016The word entropy of natural languagescited by 6
  8. 2020Linguistic Resources for Bhojpuri, Magahi and Maithili: Statistics about them, their Similarity Estimates, and Baselines for Three Applicationscited by 6
  9. 2020A Survey of Orthographic Information in Machine Translationcited by 5
  10. 2020Evolutionary Multi Objective Optimization Algorithm for Community Detection in Complex Social Networkscited by 2
  11. 2022The boundaries of meaning: a case study in neural machine translationcited by 1

Built on by

Not cited yet.