Morphology and reranking for the statistical parsing of Spanish

Cowan, Brooke; Collins, Michael

doi:10.3115/1220575.1220675

Cited by 16 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regard to morphological features this is in line with a number of recent studies showing the importance of morphology for parsing languages with less rigid word order, including work on Spanish (Cowan and Collins, 2005), Hebrew (Tsarfaty, 2006;Tsarfaty and Sima'an, 2007), Turkish , and Swedish (Øvrelid and Nivre, 2007).…”

Section: Resultssupporting

confidence: 58%

Parsing the SynTagRus treebank of Russian

Nivre

Boguslavsky

Iomdin

2008

Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08

View full text Add to dashboard Cite

We present the first results on parsing the SYNTAGRUS treebank of Russian with a data-driven dependency parser, achieving a labeled attachment score of over 82% and an unlabeled attachment score of 89%. A feature analysis shows that high parsing accuracy is crucially dependent on the use of both lexical and morphological features. We conjecture that the latter result can be generalized to richly inflected languages in general, provided that sufficient amounts of training data are available.

show abstract

Section: Resultssupporting

confidence: 58%

Parsing the SynTagRus treebank of Russian

Nivre

Boguslavsky

Iomdin

2008

Proceedings of the 22nd International Conference on Computational Linguistics - COLING '08

View full text Add to dashboard Cite

show abstract

“…We parsed the test sentences for each of the languages aside from Czech. We used Cowan and Collins (2005)'s parser for Spanish, Arun and Keller (2005)'s for French, Dubey (2005)'s for German, and Bikel (2002)'s for English.…”

Section: Ranking Translations Of Syntactic Constituentsmentioning

confidence: 99%

(Meta-) evaluation of machine translation

Callison-Burch

Fordyce²,

Koehn

et al. 2007

Proceedings of the Second Workshop on Statistical Machine Translation - StatMT '07

223

183

View full text Add to dashboard Cite

This paper evaluates the translation quality of machine translation systems for 8 language pairs: translating French, German, Spanish, and Czech to English and back. We carried out an extensive human evaluation which allowed us not only to rank the different MT systems, but also to perform higher-level analysis of the evaluation process. We measured timing and intra-and inter-annotator agreement for three types of subjective evaluation. We measured the correlation of automatic evaluation metrics with human judgments. This meta-evaluation reveals surprising facts about the most commonly used methodologies.

show abstract

“…11 Recently, there have been some attempts to adapt parsers developed for English to other languages (Levy and Manning, 2003;Cowan and Collins, 2005). Adapting lexicalized parsers to other languages in not a trivial task as it requires at least the specification of head rules, and has had limited success.…”

Section: Multilingual Parsingmentioning

confidence: 99%

Coarse-to-Fine Natural Language Processing

Klein

Petrov

2012

Theory and Applications of Natural Language Processing

View full text Add to dashboard Cite

State-of-the-art natural language processing models are anything but compact. Syntactic parsers have huge grammars, machine translation systems have huge transfer tables, and so on across a range of tasks. With such complexity come two challenges. First, how can we learn highly complex models? Second, how can we efficiently infer optimal structures within them?Hierarchical coarse-to-fine methods address both questions. Coarse-to-fine approaches exploit a sequence of models which introduce complexity gradually. At the top of the sequence is a trivial model in which learning and inference are both cheap. Each subsequent model refines the previous one, until a final, full-complexity model is reached. Because each refinement introduces only limited complexity, both learning and inference can be done in an incremental fashion. In this dissertation, we describe several coarse-to-fine systems.In the domain of syntactic parsing, complexity is in the grammar. We present a latent variable approach which begins with an X-bar grammar and learns to iteratively refine grammar categories. For example, noun phrases might be split into subcategories for subjects and objects, singular and plural, and so on. This splitting process admits an efficient incremental inference scheme which reduces parsing times by orders of magnitude. Fur-1 thermore, it produces the best parsing accuracies across an array of languages, in a fully language-general fashion.In the domain of acoustic modeling for speech recognition, complexity is needed to model the rich phonetic properties of natural languages. Starting from a mono-phone model, we learn increasingly refined models that capture phone internal structures, as well as contextdependent variations in an automatic way. Our approaches reduces error rates compared to other baseline approaches, while streamlining the learning procedure.In the domain of machine translation, complexity arises because there and too many target language word types. To manage this complexity, we translate into target language clusterings of increasing vocabulary size. This approach gives dramatic speed-ups while additionally increasing final translation quality.

show abstract

Morphology and reranking for the statistical parsing of Spanish

Cited by 16 publications

References 11 publications

Parsing the SynTagRus treebank of Russian

Parsing the SynTagRus treebank of Russian

(Meta-) evaluation of machine translation

Coarse-to-Fine Natural Language Processing

Contact Info

Product

Resources

About