539 research outputs found
Sort by
Dependency Relations Labeller for Czech
No full textWe present a MIRA-based labeller designed to assign dependency relation labels to edges in a dependency parse tree, tuned for Czech language. The labeller was created to be used as a second stage to unlabelled dependency parsers but can also improve output from labelled dependency parsers. We evaluate two existing techniques which can be used for labelling and experiment with combining them together. We describe the feature set used. Our final setup significantly outperforms the best results from the CoNLL 2009 shared task
Rule-based Machine Translation between Indonesian and Malaysian
No full textWe describe the development of a bidirectional rule-based machine translation system between Indonesian and Malaysian (id-ms), two closely related Austronesian languages natively spoken by approximately 35 million people. The system is based on the re-use of free and publicly available resources, such as the Apertium machine translation platform and Wikipedia articles. We also present our approaches to overcome the data scarcity problems in both languages by exploiting the morphology similarities between the two
Exploiting Reducibility in Unsupervised Dependency Parsing
No full textPredstavujeme novy pristup k nerizenemu zavislostnimu parsingu zalozenemu na mire vypustitelnosti jednotlivych sekvenci slov
Manually Classified Errors in English-Slovak Translation
No full textOutputs of three English-Slovak machine translation systems for 50 sentences randomly selected from WMT 2011 test set. The translations were manually processed and the errors were marked and classified according to the scheme by Vilar et al. (David Vilar, Jia Xu, Luis Fernando D’Haro, Hermann Ney: Error Analysis of Statistical Machine Translation Output, Proceedings of LREC-2006, 2006
Indonesian Dependency Treebank: Annotation and Parsing
No full textWe also show ensemble dependency parsing and self training approaches applicable to under-resourced languages using our manually annotated dependency structures. We show that for an under-resourced language, the use of tuning data for a meta classifier is more effective than using it as additional training data for individual parsers. This meta-classifier creates an ensemble dependency parser and increases the dependency accuracy by 4.92% on average and 1.99% over the best individual models on average. As the data sizes grow for the the under-resourced language a meta classifier can easily adapt. To the best of our knowledge this is the first full implementation of a dependency parser for Indonesian. Using self-training in combination with our Ensemble SVM Parser we show additional improvement. Using this parsing model we plan on expanding the size of the corpus by using a semi-supervised approach by applying the parser and correcting the errors, reducing the amount of annotation time needed
Formemes in English-Czech Deep Syntactic MT
Get PDFOne of the most notable recent improvements of the TectoMT English-to-Czech translation is a systematic and theoretically supported revision of formemes—the annotation of morpho-syntactic features of content words in deep dependency syntactic structures based on the Prague tectogrammatics theory. Our modifications aim at reducing data sparsity, increasing consistency across languages and widening the usage area of this markup. Formemes can be used not only in MT, but in various other NLP tasks
Morphological Processing for English-Tamil Statistical Machine Translation
No full textVarious experiments from literature suggest that in statistical machine translation (SMT), applying either pre-processing or post-processing to morphologically rich languages leads to better translation quality. In this work, we focus on the English-Tamil language pair. We implement suffix-separation rules for both of the languages and evaluate the impact of this
preprocessing on translation quality of the phrase-based as well as hierarchical model in terms of BLEU score and a small manual evaluation. The results confirm that our simple suffix-based morphological processing helps to obtain better translation performance. A by-product of our
efforts is a new parallel corpus of 190k sentence pairs gathered from the web
Towards an Indonesian-English SMT System: A Case Study of an Under-Studied and Under-Resourced Language, Indonesian
Get PDFThis paper describes a work on preparing an Indonesian-English Statistical Machine Translation (SMT) System. It includes the creation of Indonesian morphological analyzer, MorphInd, and the composing of an Indonesian-English parallel corpus, IDENTIC. We build an SMT system using the state-of-the-art phrase-based SMT system, MOSES. We show several scenarios where the morphological tool is used to incorporate morphological information in the SMT system trained with the composed parallel corpus
Data-Driven Methods for Spoken Language Understanding
No full textThis chapter described data-driven methods suitable for development of spoken language understanding components in dialogue systems
Tailored Feature Extraction for Lexical Disambiguation of English Verbs Based on Corpus Pattern Analysis
No full textWe give a report on a detailed study of automatic lexical disambiguation of 30 sample English
verbs. We have trained and evaluate several statistical classifiers that use both morphosyntactic
and semantic features to assign semantic patterns according to a pattern lexicon.
Our system of semantic classification draws on the Corpus Pattern Analysis (CPA) — a novel
lexicographic method that seeks to cluster verb uses according to the morpho-syntactic, lexical
and semantic/pragmatic similarity of their contexts rather than their grouping according to
abstract semantic definitions. In this paper we mainly concentrate on the procedures for feature
extraction and feature selection. We show that features tailored to particular verbs using
contextual clues given by the CPA method and explicitly described in the pattern lexicon have
potential to significantly improve accuracy of supervised statistical classifiers