mlsanityData to 7 Oct 2026

Unsupervised Bilingual Lexicon Induction for Low Resource Languages

arXiv 2412.16894 ↗First posted 22 Dec 2024cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Bilingual lexicons play a crucial role in various Natural Language Processing tasks. However, many low-resource languages (LRLs) do not have such lexicons, and due to the same reason, cannot benefit from the supervised Bilingual Lexicon Induction (BLI) techniques. To address this, unsupervised BLI (UBLI) techniques were introduced. A prominent technique in this line is structure-based UBLI. It is an iterative method, where a seed lexicon, which is initially learned from monolingual embeddings is iteratively improved. There have been numerous improvements to this core idea, however they have been experimented with independently of each other. In this paper, we investigate whether using these techniques simultaneously would lead to equal gains. We use the unsupervised version of VecMap, a commonly used structure-based UBLI framework, and carry out a comprehensive set of experiments using the LRL pairs, English-Sinhala, English-Tamil, and English-Punjabi. These experiments helped us to identify the best combination of the extensions. We also release bilingual dictionaries for English-Sinhala and English-Punjabi.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 22 Dec 2024.

Builds on

30 of 51 references.

References · 30

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  4. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  5. 2016Bag of Tricks for Efficient Text Classificationcited by 869
  6. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  7. 2017Word Translation Without Parallel Datacited by 480
  8. 2013Exploiting Similarities among Languages for Machine Translationcited by 187
  9. 2023IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languagescited by 149
  10. 2017Unsupervised Neural Machine Translationcited by 148
  11. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
  12. 2018On the Limitations of Unsupervised Bilingual Dictionary Inductioncited by 61
18 more
  1. 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
  2. 2019How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptionscited by 48
  3. 2020DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionariescited by 20
  4. 2018Non-Adversarial Unsupervised Word Translationcited by 19
  5. 2021Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignmentcited by 19
  6. 2020Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translationcited by 16
  7. 2024Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corporacited by 13
  8. 2024Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignmentcited by 13
  9. 2021Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Inductioncited by 12
  10. 2024LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexiconscited by 11
  11. 2018Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluationcited by 8
  12. 2020Beyond Offline Mapping: Learning Cross Lingual Word Embeddings through Context Anchoringcited by 8
  13. 2017Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddingscited by 7
  14. 2020A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Inductioncited by 5
  15. 2020Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddingscited by 4
  16. 2023Sinhala-English Parallel Word Dictionary Datasetcited by 4
  17. 2024Shoulders of Giants: A Look at the Degree and Utility of Openness in NLP Researchcited by 4
  18. 2021Word Embedding Transformation for Robust Unsupervised Bilingual Lexicon Inductioncited by 2

Built on by

Not cited yet.