Comparative morphology

Xem 1-20 trên 22 kết quả Comparative morphology
  • We report in this paper our work on accurately generating case markers and suffixes in English-to-Hindi SMT. Hindi is a relatively free word-order language, and makes use of a comparatively richer set of case markers and morphological suffixes for correct meaning representation. From our experience of large-scale English-Hindi MT, we are convinced that fluency and fidelity in the Hindi output get an order of magnitude facelift if accurate case markers and suffixes are produced.

    pdf9p hongphan_1 14-04-2013 26 3   Download

  • If unsupervised morphological analyzers could approach the effectiveness of supervised ones, they would be a very attractive choice for improving MT performance on low-resource inflected languages. In this paper, we compare performance gains for state-of-the-art supervised vs. unsupervised morphological analyzers, using a state-of-theart Arabic-to-English MT system.

    pdf6p nghetay_1 07-04-2013 18 2   Download

  • We present a class-based language model that clusters rare words of similar morphology together. The model improves the prediction of words after histories containing outof-vocabulary words. The morphological features used are obtained without the use of labeled data. The perplexity improvement compared to a state of the art Kneser-Ney model is 4% overall and 81% on unknown histories.

    pdf5p hongdo_1 12-04-2013 22 2   Download

  • We propose a method to automatically train lemmatization rules that handle prefix, infix and suffix changes to generate the lemma from the full form of a word. We explain how the lemmatization rules are created and how the lemmatizer works. We trained this lemmatizer on Danish, Dutch, English, German, Greek, Icelandic, Norwegian, Polish, Slovene and Swedish full form-lemma pairs respectively. We obtained significant improvements of 24 percent for Polish, 2.3 percent for Dutch, 1.5 percent for English, 1.2 percent for German and 1.

    pdf9p hongphan_1 14-04-2013 49 2   Download

  • This paper discusses the supervised learning of morphology using stochastic transducers, trained using the ExpectationMaximization (EM) algorithm. Two approaches are presented: first, using the transducers directly to model the process, and secondly using them to define a similarity measure, related to the Fisher kernel method (Jaakkola and Haussler, 1998), and then using a Memory-Based Learning (MBL) technique. These are evaluated and compared on data sets from English, German, Slovene and Arabic. ...

    pdf8p bunmoc_1 20-04-2013 12 2   Download

  • We propose a novel method for learning morphological paradigms that are structured within a hierarchy. The hierarchical structuring of paradigms groups morphologically similar words close to each other in a tree structure. This allows detecting morphological similarities easily leading to improved morphological segmentation. Our evaluation using (Kurimo et al., 2011a; Kurimo et al., 2011b) dataset shows that our method performs competitively when compared with current state-ofart systems.

    pdf10p bunthai_1 06-05-2013 13 2   Download

  • Concerning different approaches to automatic PoS tagging: EngCG-2, a constraintbased morphological tagger, is compared in a double-blind test with a state-of-the-art statistical tagger on a common disambiguation task using a common tag set. The experiments show that for the same amount of remaining ambiguity, the error rate of the statistical tagger is one order of magnitude greater than that of the rule-based one. The two related issues of priming effects compromising the results and disagreement between human annotators are also addressed. ...

    pdf8p bunthai_1 06-05-2013 22 2   Download

  • We experiment with splitting words into their stem and suffix components for modeling morphologically rich languages. We show that using a morphological analyzer and disambiguator results in a significant perplexity reduction in Turkish. We present flexible n-gram models, FlexGrams, which assume that the n−1 tokens that determine the probability of a given token can be chosen anywhere in the sentence rather than the preceding n − 1 positions. Our final model achieves 27% perplexity reduction compared to the standard n-gram model. ...

    pdf4p hongphan_1 15-04-2013 20 1   Download

  • We started by noting Compartamos’s outsize return on equity above 50 percent in 2004. The return compares very favorably with Citigroup’s 2004 return on equity of 16 percent, for example. Table 3 shows that the median return on equity for nongovernmental microfinance organizations is 3 percent and, for microfinance banks, 10 percent. The figures are impressive, but well below returns for either Citigroup or Compartamos in 2004. The numbers are larger, though, when we condition on profitability (columns 4, 8, and 12; here the returns to equity are 11.4 and 11.5).

    pdf33p taisaovanchuavo 23-01-2013 30 5   Download

  • The Silverman needle, designed in 1938, was first to be used to take prostatic tissue by Peirson and Nickerson and they published their cohort of 36 patients (Peirson and Nickerson, 1943). They were able to achieve satisfactory histological specimens in 86% of cases. A specific comparison of the Franzen and Silverman needles was undertaken by Hendry and Williams and their findings were published in 1971 (Hendry and Williams, 1971).

    pdf472p ti_du_hoang 10-08-2012 27 4   Download

  • In the last decade the progress of molecular biology has made a strong influence on the theoretical framework of population genetics and evolution. Introduction of molecular techniques in this area has resulted in many new discoveries. As a result, a new interdisciplinary science, which may be called 'Molecular Population Genetics and Evolution', has emerged. In this book I have attempted to discuss the development and outline of this science. In recent years a large number of papers have been published on this subject.

    pdf290p camchuong_1 04-12-2012 15 4   Download

  • Computer Tomography (CT) is considered the gold standard for assessing the morphological changes of lung parenchyma. Although novel CT techniques have substantially decreased the radiation dose, radiation exposure is still high. Magnetic Resonance Imaging (MRI) has been established as a radiation- free alternative to CT for several lung diseases, but its role in infectious diseases still needs to be explored further. Therefore, the purpose of our study was to compare MRI with high resolution CT (HRCT) for assessing pulmonary tuberculosis.

    pdf7p taisaocothedung 12-01-2013 13 2   Download

  • Tuyển tập các báo cáo nghiên cứu về lâm nghiệp được đăng trên tạp chí lâm nghiệp quốc tế đề tài: morphological characteristics, root growth potential and flushing response of rooted cuttings compared with transplants of Sitka spruce...

    pdf10p toshiba7 05-10-2011 14 1   Download

  • A market-leading dental anatomy textbook for dental, dental hygiene, and dental assisting students, Woelfel's Dental Anatomy focuses on anatomy of the human mouth and teeth, and is designed to help the student understand the relationship of the teeth to one another, and to the bones, muscles, nerves, and vessels associated with the teeth and face. This text does more than simply explain dental anatomy; it links the anatomy to clinical practice, giving readers a stronger and more practical understanding of tooth structure and function, morphology, anatomy, and terminology.

    pdf514p hyperion75 21-01-2013 35 7   Download

  • Vitrification has been investigated for tissue-engineered bone and blood vessels. Liu & McGrath (2003) explored the potential of vitrification for the cryopreservation of tissueengineered bone constructs consisting of a hydroxyapatite scaffold-cell complex. Cell survival was 92.0% for suspended cells and 43.0% for attached cells. In terms of tissueengineered blood vessel constructs, the effects of vitrification and conventional cryopreservation were compared (Elder et al., 2005). Collagen-based vascular constructs were used as models in this study.

    pdf304p kmkmkmkmkm 08-09-2012 25 4   Download

  • Hungarian is a stereotype of morphologically rich and non-configurational languages. Here, we introduce results on dependency parsing of Hungarian that employ a 80K, multi-domain, fully manually annotated corpus, the Szeged Dependency Treebank. We show that the results achieved by state-of-the-art data-driven parsers on Hungarian and English (which is at the other end of the configurational-nonconfigurational spectrum) are quite similar to each other in terms of attachment scores.

    pdf11p bunthai_1 06-05-2013 17 3   Download

  • We investigate the controversial issue about the upper bound of interjudge agreement in the use of a low-level grammatical representation. Pessimistic views suggest that several percent of words in running text are undecidable in terms of part-of-speech categories. Our experiments with 55kW data give reason for optimism: linguists with only 30 hours' training apply the EngCG-2 morphological tags with almost 100% interjudge agreement.

    pdf5p bunthai_1 06-05-2013 15 3   Download

  • We apply pattern-based methods for collecting hypernym relations from the web. We compare our approach with hypernym extraction from morphological clues and from large text corpora. We show that the abundance of available data on the web enables obtaining good results with relatively unsophisticated techniques.

    pdf4p hongvang_1 16-04-2013 18 2   Download

  • We extend the factored translation model (Koehn and Hoang, 2007) to allow translations of longer phrases composed of factors such as POS and morphological tags to act as templates for the selection and reordering of surface phrase translation. We also reintroduce the use of alignment information within the decoder, which forms an integral part of decoding in the Alignment Template System (Och, 2002), into phrase-based decoding. Results show an increase in translation performance of up to 1.0% BLEU for out-of-domain French–English translation.

    pdf8p bunthai_1 06-05-2013 18 2   Download

  • Arabic morphology is complex, partly because of its richness, and partly because of common irregular word forms, such as broken plurals (which resemble singular nouns), and nouns with irregular gender (feminine nouns that look masculine and vice versa). In addition, Arabic morphosyntactic agreement interacts with the lexical semantic feature of rationality, which has no morphological realization. In this paper, we present a series of experiments on the automatic prediction of the latent linguistic features of functional gender and number, and rationality in Arabic.

    pdf11p bunthai_1 06-05-2013 19 2   Download


Đồng bộ tài khoản