Density-Driven Cross-Lingual Transfer of Dependency Parsers

Rasooli, Mohammad Sadegh; Collins, Michael

doi:10.18653/v1/d15-1039

Cited by 47 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang and Manning (2014) proposed a variant of annotation projection which projects expectations of tags and uses them as constraints to train a model based on generalized expectation criteria. Annotation projection has also been applied to several other cross-lingual NLP tasks, including word sense disambiguation (Diab and Resnik, 2002), part-of-speech (POS) tagging (Yarowsky et al, 2001) and dependency parsing (Rasooli and Collins, 2015). Wikipedia has been exploited to generate weakly labeled multilingual NER training data.…”

Section: Related Workmentioning

confidence: 99%

Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection

Ni¹,

Dinu²,

Florian³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

123

119

View full text Add to dashboard Cite

The state-of-the-art named entity recognition (NER) systems are supervised machine learning models that require large amounts of manually annotated data to achieve high accuracy. However, annotating NER data by human is expensive and time-consuming, and can be quite difficult for a new language. In this paper, we present two weakly supervised approaches for cross-lingual NER with no human annotation in a target language. The first approach is to create automatically labeled NER data for a target language via annotation projection on comparable corpora, where we develop a heuristic scheme that effectively selects goodquality projection-labeled data from noisy data. The second approach is to project distributed representations of words (word embeddings) from a target language to a source language, so that the sourcelanguage NER system can be applied to the target language without re-training. We also design two co-decoding schemes that effectively combine the outputs of the two projection-based approaches. We evaluate the performance of the proposed approaches on both in-house and open NER data for several target languages. The results show that the combined systems outperform three other weakly supervised approaches on the CoNLL data.

show abstract

Section: Related Workmentioning

confidence: 99%

Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection

Ni¹,

Dinu²,

Florian³

2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

123

119

View full text Add to dashboard Cite

show abstract

“…Since 2001, in addition to POS-tagging, annotation projection has been successfully applied to other tasks such as named entity recognition Enghoff et al, 2018), word sense tagging (Bentivogli et al, 2004), semantic role labeling Lapata, 2005, 2009;van der Plas et al, 2011;Aminian et al, 2017), or dependency parsing Tiedemann, 2014;Rasooli and Collins, 2015;Agić et al, 2016;. Kim et al (2011) presented an integration into a full pipeline for information extraction.…”

Section: Related Workmentioning

confidence: 99%

Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging

Huck¹,

Dutka²,

Fraser³

2019

Proceedings of the Sixth Workshop On

View full text Add to dashboard Cite

We tackle the important task of part-of-speech tagging using a neural model in the zeroresource scenario, where we have no access to gold-standard POS training data. We compare this scenario with the low-resource scenario, where we have access to a small amount of gold-standard POS training data. Our experiments focus on Ukrainian as a representative of under-resourced languages. Russian is highly related to Ukrainian, so we exploit gold-standard Russian POS tags. We consider four techniques to perform Ukrainian POS tagging: zero-shot tagging and cross-lingual annotation projection (for the zero-resource scenario), and compare these with self-training and multilingual learning (for the low-resource scenario). We find that cross-lingual annotation projection works particularly well in the zero-resource scenario.

show abstract

“…The use of dense projected structures is presented by Rasooli and Collins (2015), to obtaining high-quality projections that improve cross-lingual parsing performance.…”

Section: Related Workmentioning

confidence: 99%

New treebank or repurposed? On the feasibility of cross-lingual parsing of Romance languages with Universal Dependencies

2017

View full text Add to dashboard Cite

This paper addresses the feasibility of cross-lingual parsing with Universal Dependencies (UD) between Romance languages, analyzing its performance when compared to the use of manually annotated resources of the target languages. Several experiments take into account factors such as the lexical distance between the source and target varieties, the impact of delexicalization, the combination of different source treebanks or the adaptation of resources to the target language, among others. The results of these evaluations show that the direct application of a parser from one Romance language to another reaches similar labeled attachment score (LAS) values to those obtained with a manual annotation of about 3,000 tokens in the target language, and unlabeled attachment score (UAS) results equivalent to the use of around 7,000 tokens, depending on the case. These numbers can noticeably increase by performing a focused selection of the source treebanks. Furthermore, the removal of the words in the training corpus (delexicalization) is not useful in most cases of cross-lingual parsing of Romance languages. The lessons learned with the performed experiments were used to build a new UD treebank for Galician, with 1,000 sentences manually corrected after an automatic cross-lingual annotation. Several evaluations in this new resource show that a cross-lingual parser built with the best combination and adaptation of the source treebanks performs better (77 percent LAS and 82 percent UAS) than using more than 16,000 (for LAS results) and more than 20,000 (UAS) manually labeled tokens of Galician.

show abstract

Density-Driven Cross-Lingual Transfer of Dependency Parsers

Cited by 47 publications

References 20 publications

Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection

Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection

Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging

New treebank or repurposed? On the feasibility of cross-lingual parsing of Romance languages with Universal Dependencies

Contact Info

Product

Resources

About