If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages

Agić, Željko; Hovy, Dirk; Søgaard, Anders

doi:10.3115/v1/p15-2044

Cited by 42 publications

(52 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, we plan to investigate other methods for seed pairs selection, settings with scarce resources (Agić et al, 2015;Zhang et al, 2016), other context types inspired by recent work in the monolingual settings (Levy and Goldberg, 2014a;Melamud et al, 2016), as well as model adaptations that can work with multi-word expressions. Encouraged by the excellent results, we also plan to test the portability of the approach to more language pairs, and other tasks and applications.…”

Section: Discussionmentioning

confidence: 99%

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

Vulić¹,

Korhonen²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

A shared bilingual word embedding space (SBWES) is an indispensable resource in a variety of cross-language NLP and IR tasks. A common approach to the SB-WES induction is to learn a mapping function between monolingual semantic spaces, where the mapping critically relies on a seed word lexicon used in the learning process. In this work, we analyze the importance and properties of seed lexicons for the SBWES induction across different dimensions (i.e., lexicon source, lexicon size, translation method, translation pair reliability). On the basis of our analysis, we propose a simple but effective hybrid bilingual word embedding (BWE) model. This model (HYBWE) learns the mapping between two monolingual embedding spaces using only highly reliable symmetric translation pairs from a seed document-level embedding space. We perform bilingual lexicon learning (BLL) with 3 language pairs and show that by carefully selecting reliable translation pairs our new HYBWE model outperforms benchmarking BWE learning models, all of which use more expensive bilingual signals. Effectively, we demonstrate that a SBWES may be induced by leveraging only a very weak bilingual signal (document alignments) along with monolingual data.

show abstract

Section: Discussionmentioning

confidence: 99%

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

Vulić¹,

Korhonen²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…Täckström et al (2013a) further improve this to 89% by leveraging Wiktionary. For some languages, there are even less resources available; Agić et al (2015b) were able to reach accuracies around 70% by using partial or full Bible translation. Our methods could thus be applied even in a more realistic scenario, where gold POS tags are not available for the target text, by using a weaklysupervised POS tagger.…”

Section: Related Workmentioning

confidence: 99%

KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer

Rosa¹,

Žabokrtský²

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

We present KL cpos 3 , a language similarity measure based on Kullback-Leibler divergence of coarse part-of-speech tag trigram distributions in tagged corpora. It has been designed for multilingual delexicalized parsing, both for source treebank selection in single-source parser transfer, and for source treebank weighting in multi-source transfer. In the selection task, KL cpos 3 identifies the best source treebank in 8 out of 18 cases. In the weighting task, it brings +4.5% UAS absolute, compared to unweighted parse tree combination.

show abstract

“…A new tagger is then trained on the target side, with some smoothing to reduce the noise caused by alignment errors. Follow-up work has focused on the inclusion of several source languages (Fossum and Abney, 2005), more accurate projection algorithms (Das and Petrov, 2011;Duong et al, 2013), the integration of external lexicon sources (Li et al, 2012;Täckström et al, 2013), the extension from part-of-speech tagging to full morphological tagging (Buys and Botha, 2016), and the investigation of truly low-resource settings by resorting to Bible translations (Agić et al, 2015). A related approach (Aepli et al, 2014) uses majority voting to disambiguate tags proposed by several source languages.…”

Section: Related Workmentioning

confidence: 99%

Multi-source morphosyntactic tagging for spoken Rusyn

Scherrer¹,

Rabus²

2017

Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)

View full text Add to dashboard Cite

This paper deals with the development of morphosyntactic taggers for spoken varieties of the Slavic minority language Rusyn. As neither annotated corpora nor parallel corpora are electronically available for Rusyn, we propose to combine existing resources from the etymologically close Slavic languages Russian, Ukrainian, Slovak, and Polish and adapt them to Rusyn. Using MarMoT as tagging toolkit, we show that a tagger trained on a balanced set of the four source languages outperforms single language taggers by about 9%, and that additional automatically induced morphosyntactic lexicons lead to further improvements. The best observed accuracies for Rusyn are 82.4% for part-of-speech tagging and 75.5% for full morphological tagging.

show abstract

If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages

Cited by 42 publications

References 9 publications

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer

Multi-source morphosyntactic tagging for spoken Rusyn

Contact Info

Product

Resources

About