When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages
Most existing approaches for unsupervised bilingual lexicon induction (BLI) depend on good quality static or contextual embeddings requiring large monolingual corpora for both languages. However, unsupervised BLI is most likely to be useful for low-resource languages (LRLs), where large datasets are not available. Often we are interested in building bilingual resources for LRLs against related high-resource languages (HRLs), resulting in severely imbalanced data settings for BLI. We first show that state-of-the-art BLI methods in the literature exhibit near-zero performance for severely data-imbalanced language pairs, indicating that these settings require more robust techniques. We then present a new method for unsupervised BLI between a related LRL and HRL that only requires inference on a masked language model of the HRL, and demonstrate its effectiveness on truly low-resource languages Bhojpuri and Magahi (with <5M monolingual tokens each), against Hindi. We further present experiments on (mid-resource) Marathi and Nepali to compare approach performances by resource range, and release our resulting lexicons for five low-resource Indic languages: Bhojpuri, Magahi, Awadhi, Braj, and Maithili, against Hindi.
Code (1)
Tasks
Bilingual Lexicon InductionLanguage ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Borrow a Little from your Rich Cousin: Using Embeddings and Polarities of English Words for Multilingual Sentiment Classification
In this paper, we provide a solution to multilingual sentiment classification using deep learning. Given input text in a language, we use word translation into English and then the embeddings of these English words to tr…
Feature EngineeringGeneral ClassificationMachine TranslationSentence Classification+6An nth-cousin mating model and the n-anacci numbers
In seeking to understand the size of inbred pedigrees, J. Lachance (J. Theor. Biol. 261, 238-247, 2009) studied a population model in which, for a fixed value of $n$, each mating occurs between $n$th cousins. We explain …
Similarities and Differences between Machine Learning and Traditional Advanced Statistical Modeling in Healthcare Analytics
Data scientists and statisticians are often at odds when determining the best approach, machine learning or statistical modeling, to solve an analytics challenge. However, machine learning and statistical modeling are mo…
BIG-bench Machine LearningFocus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation
We study unsupervised domain adaptation (UDA) for semantic segmentation. Currently, a popular UDA framework lies in self-training which endows the model with two-fold abilities: (i) learning reliable semantics from the l…
Domain AdaptationSemantic SegmentationUnsupervised Domain AdaptationSimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
Training and evaluating robot policies in the real world is costly and difficult to scale. We introduce SimFoundry, a modular and automated system for zero-shot real-to-sim scene construction from a video. SimFoundry gen…
Scene Generation