Multilingual Part-of-Speech Tagging: Two Unsupervised Approaches

@article{Naseem2009MultilingualPT,
  title={Multilingual Part-of-Speech Tagging: Two Unsupervised Approaches},
  author={Tahira Naseem and Benjamin Snyder and Jacob Eisenstein and Regina Barzilay},
  journal={J. Artif. Intell. Res.},
  year={2009},
  volume={36},
  pages={341-385}
}
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We consider two ways of applying this intuition to the problem of unsupervised part-of-speech tagging: a model that directly merges tag structures for a pair of languages into a single sequence and a second model which instead incorporates multilingual context using… Expand
Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections
TLDR
A novel approach for inducing unsupervised part-of-speech taggers for languages that have no labeled training data, but have translated text in a resource-rich language, using graph-based label propagation for cross-lingual knowledge transfer. Expand
Part-of-speech Taggers for Low-resource Languages using CCA Features
TLDR
A probability-based confidence model is developed to identify words with highly likely tag projections and use these words to train a multi-class SVM using the CCA features, which yields average performance of 85% accuracy for languages with almost no resources, outperforming a state-of-the-art partiallyobserved CRF model. Expand
A Bayesian Model of Multilingual Unsupervised Semantic Role Induction
TLDR
It is found that the biggest impact of adding a parallel corpus to training is actually the increase in mono-lingual data, with the alignments to another language resulting in small improvements, even with labeled data for the other language. Expand
A Bayesian mixture model for part-of-speech induction using multiple features
In this paper we present a fully unsupervised syntactic class induction system formulated as a Bayesian multinomial mixture model, where each word type is constrained to belong to a single class. ByExpand
Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging
TLDR
It is shown that additional token constraints can be projected from a resource-rich source language to a resourceful target language via word-aligned bitext, and empirically demonstrating the applicability of coupled token and type constraints across a diverse set of languages. Expand
A Universal Part-of-Speech Tagset
TLDR
This work proposes a tagset that consists of twelve universal part-of-speech categories and develops a mapping from 25 different treebank tagsets to this universal set, which when combined with the original treebank data produces a dataset consisting of common parts- of-speech for 22 different languages. Expand
Multilingual part-of-speech tagging with weightless neural networks
TLDR
Experimental evaluation indicates that mWANN-Tagger either outperforms or matches state-of-art methods in accuracy with very low standard deviation, i.e., lower than 0.25%. Expand
Unsupervised Structure Prediction with Non-Parallel Multilingual Guidance
We describe a method for prediction of linguistic structure in a language for which only unlabeled data is available, using annotated data from a set of one or more helper languages. Our approach isExpand
A Hierarchical Dirichlet Process Model for Joint Part-of-Speech and Morphology Induction
TLDR
This paper presents a fully unsupervised nonparametric Bayesian model that jointly induces POS tags and morphological segmentations and shows that learning both tasks jointly actually leads to better results than learning either task with gold standard data from the other task provided. Expand
Ten Pairs to Tag – Multilingual POS Tagging via Coarse Mapping between Embeddings
TLDR
It is demonstrated that accurate multilingual partof-speech (POS) tagging can be done with just a few (e.g., ten) word translation pairs, and the generated tags are used to predict typological properties of languages, obtaining a 50% error reduction relative to the prototype model. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 71 REFERENCES
Unsupervised Multilingual Learning for POS Tagging
TLDR
A hierarchical Bayesian model is formulated for jointly predicting bilingual streams of part-of-speech tags that learns language-specific features while capturing cross-lingual patterns in tag distribution for aligned words. Expand
Adding More Languages Improves Unsupervised Multilingual Part-of-Speech Tagging: a Bayesian Non-Parametric Approach
TLDR
A non-parametric Bayesian model is proposed that connects related tagging decisions across languages through the use of multilingual latent variables and shows that performance improves steadily as the number of languages increases. Expand
Part-of-Speech Tagging in Context
TLDR
A new HMM tagger is presented that exploits context on both sides of a word to be tagged, and it is shown how this new tagger achieves state-of-the-art results in a supervised, non-training intensive framework. Expand
A fully Bayesian approach to unsupervised part-of-speech tagging
TLDR
This model has the structure of a standard trigram HMM, yet its accuracy is closer to that of a state-of-the-art discriminative model (Smith and Eisner, 2005), up to 14 percentage points better than MLE. Expand
A Bayesian LDA-based model for semi-supervised part-of-speech tagging
TLDR
A novel Bayesian model for semi-supervised part-of-speech tagging that outperforms the best previously proposed model for this task on a standard dataset and introduces a model for determining the set of possible tags of a word which captures important dependencies in the ambiguity classes of words. Expand
Unsupervised multilingual learning
TLDR
A class of probabilistic models that exploit deep links among human languages as a form of naturally occurring supervision allow us to substantially improve performance for core text processing tasks, such as morphological segmentation, part-of-speech tagging, and syntactic parsing. Expand
Prototype-Driven Learning for Sequence Models
TLDR
This work investigates prototype-driven learning for primarily unsupervised sequence modeling, where prior knowledge is specified declaratively, by providing a few canonical examples of each target annotation label, then propagated across a corpus using distributional similarity features in a log-linear generative model. Expand
A Backoff Model for Bootstrapping Resources for Non-English Languages
TLDR
This paper proposes a novel approach of combining a bootstrapped resource with a small amount of manually annotated data and shows that this approach achieves a significant improvement over EM and self-training and systems that are only trained on manual annotations. Expand
Unsupervised Multilingual Learning for Morphological Segmentation
TLDR
A nonparametric Bayesian model is presented that jointly induces morpheme segmentations of each language under consideration and at the same time identifies cross-lingual morphem patterns, or abstract morphemes, of multiple languages. Expand
Tagging English Text with a Probabilistic Model
TLDR
Experminents show that the best training is obtained by using as much tagged text as possible, and show that Maximum Likelihood training, the procedure that is routinely used to estimate hidden Markov models parameters from training data, will not necessarily improve the tagging accuracy. Expand
...
1
2
3
4
5
...