Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection
نویسندگان
چکیده
Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly. In this paper, we introduce a novel approach to sequence tagging that learns to correct the errors from cross-lingual projection using an explicit debiasing layer. This is framed as joint learning over two corpora, one tagged with gold standard and the other with projected tags. We evaluated with only 1,000 tokens tagged with gold standard tags, along with more plentiful parallel data. Our system equals or exceeds the state-of-the-art on eight simulated lowresource settings, as well as two real lowresource languages, Malagasy and Kinyarwanda.
منابع مشابه
Cross-Lingual Dependency Parsing with Universal Dependencies and Predicted PoS Labels
This paper presents cross-lingual models for dependency parsing using the first release of the universal dependencies data set. We systematically compare annotation projection with monolingual baseline models and study the effect of predicted PoS labels in evaluation. Our results reveal the strong impact of tagging accuracy especially with models trained on noisy projected data sets. This paper...
متن کاملIncreasing the Quality and Quantity of Source Language Data for Unsupervised Cross-Lingual POS Tagging
Bilingual corpora offer a promising bridge between resource-rich and resource-poor languages, enabling the development of natural language processing systems for the latter. English is often selected as the resource-rich language, but another choice might give better performance. In this paper, we consider the task of unsupervised cross-lingual POS tagging, and construct a model that predicts t...
متن کاملCross-lingual Character-Level Neural Morphological Tagging
Even for common NLP tasks, sufficient supervision is not available in many languages—morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among mu...
متن کاملEmpirical Gaussian priors for cross-lingual transfer learning
Sequence model learning algorithms typically maximize log-likelihood minus the norm of the model (or minimize Hamming loss + norm). In cross-lingual part-ofspeech (POS) tagging, our target language training data consists of sequences of sentences with word-by-word labels projected from translations in k languages for which we have labeled data, via word alignments. Our training data is therefor...
متن کاملCross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources
Training a POS tagging model with crosslingual transfer learning usually requires linguistic knowledge and resources about the relation between the source language and the target language. In this paper, we introduce a cross-lingual transfer learning model for POS tagging without ancillary resources such as parallel corpora. The proposed cross-lingual model utilizes a common BLSTM that enables ...
متن کامل