Automatically Inducing a Part-of-Speech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora

Fossum, Victoria; Abney, Steven

doi:10.1007/11562214_75

Cited by 17 publications

(26 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In cross-lingual POS tagging, mostly annotation projection has been explored (Fossum and Abney, 2005;Das and Petrov, 2011), since all features in POS tagging models are typically lexical. However, using bilingual word representations was recently explored as an alternative to projectionbased approaches (Gouws and Søgaard, 2015).…”

Section: Introductionmentioning

confidence: 99%

Inverted indexing for cross-lingual NLP

Søgaard

Agić²,

Alonso³

et al. 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 a novel, count-based approach to obtaining inter-lingual word representations based on inverted indexing of Wikipedia. We present experiments applying these representations to 17 datasets in document classification, POS tagging, dependency parsing, and word alignment. Our approach has the advantage that it is simple, computationally efficient and almost parameter-free, and, more importantly, it enables multi-source crosslingual learning. In 14/17 cases, we improve over using state-of-the-art bilingual embeddings.

show abstract

Section: Introductionmentioning

confidence: 99%

Inverted indexing for cross-lingual NLP

Søgaard

Agić²,

Alonso³

et al. 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

show abstract

“…Fossum and Abney (2005) found that using two source languages project-sources gave better results than simply using more data from one language. also found advantages to using multiple language sources for projecting parsing constraints.…”

Section: Multilingual Projectionmentioning

confidence: 99%

Part-of-speech Taggers for Low-resource Languages using CCA Features

Kim

Snyder

Sarikaya

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

In this paper, we address the challenge of creating accurate and robust partof-speech taggers for low-resource languages. We propose a method that leverages existing parallel data between the target language and a large set of resourcerich languages without ancillary resources such as tag dictionaries. Crucially, we use CCA to induce latent word representations that incorporate cross-genre distributional cues, as well as projected tags from a full array of resource-rich languages. We develop a probability-based confidence model to identify words with highly likely tag projections and use these words to train a multi-class SVM using the CCA features. Our method yields average performance of 85% accuracy for languages with almost no resources, outperforming a state-of-the-art partiallyobserved CRF model.

show abstract

“…It has also been used in cross-lingual POS tagging Fossum and Abney, 2005), NP-chunking ) and cross-lingual dependency parsing (Sukhareva and Chiarcos, 2014) before. and Fossum and Abney (2005) use word-aligned parallel translations of the Bible to project the predictions of POS taggers for several language pairs, including English, German, and Spanish to Czech and French. The resulting annotated target language corpora enable them to train POS taggers for these languages.…”

Section: Related Workmentioning

confidence: 99%

“…While it has been observed repeatedly that using multiple source languages improves performance Fossum and Abney, 2005;, most available techniques work best for closely related languages.…”

Section: Introductionmentioning

confidence: 99%

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

Agić

Hovy

Søgaard

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 a simple method for learning part-of-speech taggers for languages like Akawaio, Aukan, or Cakchiquel -languages for which nothing but a translation of parts of the Bible exists. By aggregating over the tags from a few annotated languages and spreading them via wordalignment on the verses, we learn POS taggers for 100 languages, using the languages to bootstrap each other. We evaluate our cross-lingual models on the 25 languages where test sets exist, as well as on another 10 for which we have tag dictionaries. Our approach performs much better (20-30%) than state-of-the-art unsupervised POS taggers induced from Bible translations, and is often competitive with weakly supervised approaches that assume high-quality parallel corpora, representative monolingual corpora with perfect tokenization, and/or tag dictionaries. We make models for all 100 languages available.

show abstract

Automatically Inducing a Part-of-Speech Tagger by Projecting from Multiple Source Languages Across Aligned Corpora

Cited by 17 publications

References 17 publications

Inverted indexing for cross-lingual NLP

Inverted indexing for cross-lingual NLP

Part-of-speech Taggers for Low-resource Languages using CCA Features

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

Contact Info

Product

Resources

About