Adding more languages improves unsupervised multilingual part-of-speech tagging
Published 1 January 2009Open access
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, Regina Barzilay
Citations37
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
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.
Abstract
We investigate the problem of unsupervised part-of-speech tagging when raw parallel data is available in a large number of languages. Patterns of ambiguity vary greatly across languages and therefore even unannotated multilingual data can serve as a learning signal. We propose a non-parametric Bayesian model that connects related tagging decisions across languages through the use of multilingual latent variables. Our experiments show that performance improves steadily as the number of languages increases.
Keywords
Computer Science
BiometrikaMonte Carlo sampling methods using Markov chains and their applications
15,200 Citations1970W. Keith Hastings
Computational LinguisticsA Systematic Comparison of Various Statistical Alignment Models
3,928 Citations2003Franz Josef Och, Hermann Ney
An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
The Annals of StatisticsMixtures of Dirichlet Processes with Applications to Bayesian Nonparametric Problems
2,030 Citations1974C. Antoniak
This paper gives a formal definition for Dirichlet process mixtures and develops several theorems about their properties, the most important of which is a closure property for such mixtures.
A Constructive Definition of Dirichlet Priors
1,611 Citations1991Jayaram Sethuraman
BiometrikaMonte Carlo Sampling Methods Using Markov Chains and Their Applications
1,469 Citations1970W. K. Hastings
Edinburgh Research Explorer (University of Edinburgh)A fully Bayesian approach to unsupervised part-of-speech tagging
280 Citations2007Sharon Goldwater, Thomas L. Griffiths
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.
Inducing multilingual POS taggers and NP bracketers via robust projection across aligned corpora
247 Citations2001David Yarowsky, Grace Ngai
This paper investigates the potential for projecting linguistic annotations including part-of-speech tags and base noun phrase bracketings from one language to another via automatically word-aligned parallel corpora.
A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation
181 Citations2007Masao Utiyama, Hitoshi Isahara
The phrase translation strategy significantly outperformed the sentence translation strategy and its relative performance was 0.92 to 0.97 compared to directly trained SMT systems.
Edinburgh Research Explorer (University of Edinburgh)Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora
126 Citations2007Trevor Cohn, Mirella Lapata
Experimental results demonstrate BLEU improvements for triangulated models over a standard phrase-based system and central to this approach is triangulation, the process of translating from a source to a target language via an intermediate third language.
Statistical multi-source translation
89 Citations2001Franz Josef Och, Hermann Ney
In various tests, it is shown that these methods can significantly improve translation quality and compare the quality of statistical machine translation systems for many European languages in the same domain.
Unsupervised multilingual learning for POS tagging
71 Citations2008Benjamin Snyder, Tahira Naseem +2 more
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.
A Cross-language Approach to Rapid Creation of New Morpho-syntactically Annotated Resources
30 Citations2006Anna Feldman, Jirka Hana +1 more
This work takes a novel approach to rapid, low-cost development of morpho-syntactically annotated resources without using parallel corpora or bilingual lexicons, and presents an alternative evaluation metric for this system, where it is shown how much human labor will be needed to convert the result of the tagging to a high precision annotated resource.
Inducing a multilingual dictionary from a parallel multitext in related languages
9 Citations2005Dmitriy Genzel
This work builds a multilingual dictionary induction system for a family of related resource-poor languages that assumes only the presence of a single medium-length multitext (the Bible).