Inducing Multilingual POS Taggers and NP Bracketers via Robust Projection Across Aligned Corpora

By David Yarowsky, G. Ngai. North American Chapter of the Association for Computational Linguistics, 2001

302 citations recorded by the source corpus.

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. First, experiments assess the accuracy of unmodified direct transfer of tags and brackets from the source language English to the target languages French and Chinese, both for noisy machine-aligned sentences and for clean hand-aligned sentences. Performance is then substantially boosted over both of these baselines by using training techniques optimized for very noisy data, yielding 94-96% core French part-of-speech tag accuracy and 90% French bracketing F-measure for stand-alone monolingual tools trained without the need for any human-annotated data in the given language.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/327c88dd06722a967be9c6b1176fbd79554967e7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Posterior Regularization for Structured Latent Variable Models (2010, background): “But their importance has grown far beyond machine translation: for instance, transferring annotations between languages by projecting POS taggers, NP chunkers and parsers through word alignment (Yarowsky and Ngai, 2001; Rogati et al., 2003; Hwa et al., 2005; Ganchev et al., 2009); discovery of parap”
The Web as a Parallel Corpus (2003, background): “…as the bridge, and then use robust statistical techniques in learning from the resulting noisy annotations (Cabezas, Dorr, and Resnik 2001; Diab and Resnik 2002; Hwa et al. 2002; Lopez et al. 2002; Yarowsky, Ngai, and Wicentowski 2001; Yarowsky and Ngai 2001; Riloff, Schafer, and Yarowsky 2002).”
Improving Vector Space Word Representations Using Multilingual Correlation (2014, background): “…pairs can be treated as evidence that semantics or information at a conceptual level (since both of them basically model word cooccurrence counts) transfers well across languages (Dyvik, 2004) although syntax has been projected across languages as well (Hwa et al., 2005; Yarowsky and Ngai, 2001).”
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary (2017, background): “Yarowsky and Ngai (2001) pioneered the use of parallel data for projecting POS tag information from one language to another language.”
Bootstrapping parsers via syntactic projection across parallel texts (2005, methodology): “Annotation projection using parallel text has been accomplished for shallower tasks (Yarowsky and Ngai 2001; Merlo, Stevenson, Tsang and Allaria 2002; Yarowsky, Ngai and Wicentowski 2001), but the projection of tree structures introduces additional complexity.”
Distributed Word Representation Learning for Cross-Lingual Dependency Parsing (2014, methodology): “…annotation projection methods have also demonstrated success in various other sequence labeling tasks including POS tagging (Das and Petrov, 2011; Yarowsky and Ngai, 2001), relation extraction (Kim et al., 2012), named entity recognition (Kim et al., 2010; Kim and Lee, 2012), constituent syntax…”
The Social Impact of Natural Language Processing (2016, background): “While there are many approaches to develop multi-lingual and cross-lingual NLP tools for linguistic outliers (Yarowsky and Ngai, 2001; Das and Petrov, 2011; Søgaard, 2011; Søgaard et al., 2015; Agić et al., 2015), there simply are more commercial incentives to overexpose English, rather than other l”
Improving Machine Translation Performance by Exploiting Non-Parallel Corpora (2005, background): “…and have been found useful in research on automatic lexical acquisition (Gale and Church 1991; Melamed 1997), cross-language information retrieval (Davis and Dunning 1995; Oard 1997), and annotation projection (Diab and Resnik 2002; Yarowsky and Ngai 2001; Yarowsky, Ngai, and Wi-centowski 2001).”
Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections (2011, background): “This can be seen as a rough approximation of Yarowsky and Ngai (2001).”
A Universal Part-of-Speech Tagset (2011, background): “In particular, there has been growing interest in both multi-lingual POS induction (Snyder et al., 2009; Naseem et al., 2009) and cross-lingual POS induction via treebank projection (Yarowsky and Ngai, 2001; Xi and Hwa, 2005; Das and Petrov, 2011).”
Multilingual Deep Learning (2013, background): “To overcome this problem of resource scarcity, recently there as been a lot of interest in reusing resources from a resource fortunate language to develop NLP capabilities in a resource deprived language [25] [6] [14] [23] [17] [15] [13] [10].”
Bilingual Word Representations with Monolingual Quality in Mind (2015, background): “, 1993), but also noun bracketing (Yarowsky and Ngai, 2001), entity clustering (Green et al.”
An Autoencoder Approach to Learning Bilingual Word Representations (2014, background): “Such aligned representations can potentially allow the use of resources from a resource fortunate language to develop NLP capabilities in a resource deprived language (Yarowsky and Ngai, 2001; Das and Petrov, 2011; Mihal-cea et al., 2007; Wan, 2009; Pad ´ o and Lapata, 2009).”