Báo cáo khoa học: "Using Bilingual Comparable Corpora and Semi-supervised Clustering for Topic Tracking" ppt

... Association for Computational Linguistics Using Bilingual Comparable Corpora and Semi-supervised Clustering for Topic Tracking Fumiyo Fukumoto Interdisciplinary Graduate School of Medicine and Engineering Univ. ... basic motivation for using bilin- gual corpora: bilingual corpora helps to collec t more information about the target topic. We there- fore extracted mo...

Ngày tải lên: 17/03/2014, 04:20

... Association for Computational Linguistics, pages 1336–1345, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Using Bilingual Parallel Corpora for Cross-Lingual ... Using Parallel Corpora for CLTE Bilingual parallel corpora represent a possible solu- tion to overcome the inadequacy of the existing re- sources, and to implement a portable...

Ngày tải lên: 17/03/2014, 00:20

... models used only t i for Hebrew and ATB and t i and µ i−1 for Arabic. Word bound- ary was predicted using t i in Arabic and Hebrew, and additionally using b i−1 and b i−2 for ATB. The unconstrained ... segmentation for alignment (Chung and Gildea, 2009; Habash and Sadat, 2006), we find that the best segmentation for alignment does not coincide with the gold-standard s...

Ngày tải lên: 17/03/2014, 00:20

... using only a bilingual dictionary. We first use the bilingual dictionary to find candi- date document alignments and then use them to find an interlingual representation. Since the candidate alignments ... translation and our approach use bilingual dictionary while CCA and OPCA use a training corpus of aligned documents. Since the bilingual dictionary is learnt from Eu- roparl data...

Ngày tải lên: 17/03/2014, 00:20

... (http://phylogenomics.berkeley.edu/cgi-bin/ muscle/input_muscle.py) and adjusted manually. Molecular phylogeny For the two sets of aligned globins (annelids on one hand and annelids, molluscs and arthropods on the other), Baye- sian ... Gil for collecting specimens of G. dibranchiata, and Dr David Lincoln for collecting specimens of A. ornata. We gratefully acknowledge the capta...

Ngày tải lên: 19/02/2014, 02:20

... 1993), using a standard data split (sections 2–21 for training, 22 for development and 23 for testing). We also used section 2 as a small training set for evaluating the performance of our model ... SR- TSG model for different languages and for unsuper- vised grammar induction. Acknowledgements We would like to thank Liang Huang for helpful comments and the three anonymous...

Ngày tải lên: 19/02/2014, 19:20

... results and Ta- ble 3 shows the final NER F1 results. We compare to the state-of-the-art methods of Ando and Zhang (2005), Suzuki and Isozaki (2008), and for NER—Lin and Wu (2009). Tables 2 and 3 ... words. Clustering methods and 385 distributional methods can overlap. For example, Pereira et al. (1993) begin with a cooccurrence matrix and transform this matrix into a clus...

Ngày tải lên: 20/02/2014, 04:20

... divided data into 80% for training, 10% for development, and 10% for test for our experiments. 5.1 Experiments on Dataset 1 Identification step: Table 3 and 4 show pros and cons sentences identification ... separates pro and con candidate sentences (CR and PR in Table 1) from sentences irrelevant to either of them (NR). The classification task then classifies candida...

Ngày tải lên: 20/02/2014, 12:20

... instantiation of span labels that it induces (for string matters), and its structure (for semantic matters). and (i-j) a span label. For a formula (m, T, t) resulting after first-order ... X -+ A B C D. For an atomic formula, the corresponding production will have an empty rhs, e.g. A 4 0 .6 The left and right hand side units of SLMG productions all take the form Aim] (...

Ngày tải lên: 20/02/2014, 19:20

... that the input move is lexically correct and tries to obtain a parse for it, employing syntactic and semantic relaxation techniques for handling ill-formed sentences (Huang 1988). If no acceptable ... understanding of spoken English, pitch and pause information have received the most attention due to ease of measurement and their relative importance (Cruttenden 1986, pp 3...

Ngày tải lên: 20/02/2014, 21:20