Bootstrapping Unsupervised Bilingual Lexicon Induction

Hauer, Bradley; Nicolai, Garrett; Kondrak, Grzegorz

doi:10.18653/v1/e17-2098

Cited by 13 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generative model for inducing a bilingual lexicon from monolingual corpora by exploiting orthographic and contextual similarities of words in two different languages was proposed by Haghighi et al [171]. Many methods, based on edit-distance and orthographic similarity are proposed for using linguist feature for word alignments supervised and unsupervised methods [172][173][174]. Riley and Gildea [175] proposed method to utilise the orthographic information in wordembedding based bilingual lexicon induction.…”

Section: Orthographic Information In Unsupervised Machine Translationmentioning

confidence: 99%

A Survey of Orthographic Information in Machine Translation

et al. 2021

View full text Add to dashboard Cite

Machine translation is one of the applications of natural language processing which has been explored in different languages. Recently researchers started paying attention towards machine translation for resource-poor languages and closely related languages. A widespread and underlying problem for these machine translation systems is the linguistic difference and variation in orthographic conventions which causes many issues to traditional approaches. Two languages written in two different orthographies are not easily comparable but orthographic information can also be used to improve the machine translation system. This article offers a survey of research regarding orthography’s influence on machine translation of under-resourced languages. It introduces under-resourced languages in terms of machine translation and how orthographic information can be utilised to improve machine translation. We describe previous work in this area, discussing what underlying assumptions were made, and showing how orthographic knowledge improves the performance of machine translation of under-resourced languages. We discuss different types of machine translation and demonstrate a recent trend that seeks to link orthographic information with well-established machine translation methods. Considerable attention is given to current efforts using cognate information at different levels of machine translation and the lessons that can be drawn from this. Additionally, multilingual neural machine translation of closely related languages is given a particular focus in this survey. This article ends with a discussion of the way forward in machine translation with orthographic information, focusing on multilingual settings and bilingual lexicon induction.

show abstract

Section: Orthographic Information In Unsupervised Machine Translationmentioning

confidence: 99%

A Survey of Orthographic Information in Machine Translation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…One idea is to train a model using bilingual information from corpora aligned at the sentence level (Zou et al, 2013;Hermann and Blunsom, 2014;Luong et al, 2015) and document level (Vulic and Moens, 2016;Levy et al, 2017). Another is to exploit the isomorphic structure (Conneau et al, 2017;Artetxe et al, 2018), dictionary (Mikolov et al, 2013;Faruqui and Dyer, 2014;Huang et al, 2015;Zhang et al, 2016), shared cognate, vocab (Hauer et al, 2017;Smith et al, 2017), numeral (Artetxe et al, 2017) through ad-hoc projection.…”

Section: Related Workmentioning

confidence: 99%

Modeling Code-Switch Languages Using Bilingual Parallel Corpus

Lee¹,

Li²

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Language modeling is the technique to estimate the probability of a sequence of words. A bilingual language model is expected to model the sequential dependency for words across languages, which is difficult due to the inherent lack of suitable training data as well as diverse syntactic structure across languages. We propose a bilingual attention language model (BALM) that simultaneously performs language modeling objective with a quasi-translation objective to model both the monolingual as well as the cross-lingual sequential dependency. The attention mechanism learns the bilingual context from a parallel corpus. BALM achieves state-of-theart performance on the SEAME code-switch database by reducing the perplexity of 20.5% over the best-reported result. We also apply BALM in bilingual lexicon induction, and language normalization tasks to validate the idea.

show abstract

“…DTLM achieved state-of-theart results on several tasks in which plain word types constitute the transduction target strings. Finally, our data augmentation approach is inspired by the self-training approach of Hauer et al (2017).…”

Section: Prior Workmentioning

confidence: 99%

Low-Resource G2P and P2G Conversion with Synthetic Training Data

Hauer¹,

Habibi²,

Luan³

et al. 2020

Proceedings of the 17th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

Self Cite

View full text Add to dashboard Cite

This paper presents the University of Alberta systems and results in the SIGMOR-PHON 2020 Task 1: Multilingual Graphemeto-Phoneme Conversion. Following previous SIGMORPHON shared tasks, we define a lowresource setting with 100 training instances. We experiment with three transduction approaches in both standard and low-resource settings, as well as on the related task of phoneme-to-grapheme conversion. We propose a method for synthesizing training data using a combination of diverse models.

show abstract

Bootstrapping Unsupervised Bilingual Lexicon Induction

Cited by 13 publications

References 9 publications

A Survey of Orthographic Information in Machine Translation

A Survey of Orthographic Information in Machine Translation

Modeling Code-Switch Languages Using Bilingual Parallel Corpus

Low-Resource G2P and P2G Conversion with Synthetic Training Data

Contact Info

Product

Resources

About