Báo cáo khoa học: "Towards Robust Animacy Classification Using Morphosyntactic Distributional Features" potx

... Towards Robust Animacy Classification Using Morphosyntactic Distributional Features Lilja Øvrelid NLP-unit, Dept. of Swedish G¨oteborg ... classi- fication of animacy for Norwegian common nouns is achievable using distributional data from a mor- phosyntactically annotated corpus. The chosen morphosyntactic features of animacy have proven to ... etc. 47 This paper presents...

Ngày tải lên: 24/03/2014, 03:20

... The Target Classification In order to be able to evaluate the clusters out- put by the algorithm, we need to establish a man- ual classification of sample verbs. We assume the manual classification ... (Ko- rhonen, 2002b). For the verb classification task, we use a hierarchical clustering algorithm, and we com- pare the output clusters to a manually constructed classification developed b...

Ngày tải lên: 08/03/2014, 04:22

... the cross-language text classification problem reduces to a standard classification problem in the cross- lingual space. Note that the existing methods for cross-language text classification can be ... cross- lingual sentiment classification. In Proceedings of ACL/AFNLP-09, pages 235–243, Singapore. Tong Zhang. 2004. Solving large scale linear predic- tion problems using stochastic gradi...

Ngày tải lên: 23/03/2014, 16:20

... a way of using information on the hierarchy of labels for improving fine-grained genre classification. To the best of our knowl- edge, this is the first work presenting structural genre classification ... covering the subgenres of fic- tion. In this paper we present a method of using the hierarchy of labels to improve the classification accuracy. As a testbed for this approach we use the B...

Ngày tải lên: 30/03/2014, 21:20

... domains, or when labeled training data is not plentiful, we show that using web-scale N-gram features is essen- tial for achieving robust performance. 1 Introduction Many NLP systems use web-scale ... out-of-the-box on new domains, and how can we best design our systems for robust open-domain performance? Our results show that using web-scale N-gram data in supervised systems advances...

Ngày tải lên: 20/02/2014, 04:20

... pages 423–430, Sapporo, Japan, July. G. Leech and A. Wilson. 1996. EAGLES recommen- dations for the morphosyntactic annotation of cor- pora. Version of March 1996. T. Lu ´ ıs and D.M. de Matos. 2009. ... Rochester, NY, April. 669 S. Petrova, C. Chiarcos, J. Ritz, M. Solf, and A. Zeldes. 2009. Building and using a richly annotated inter- linear diachronic corpus: The case of Old High Ger-...

Ngày tải lên: 23/03/2014, 16:20

... rapid access to the information in the dictionary via the dictionary head words. The idea of using the machine-readable source of a published dictionary has occurred to a wide range of researchers ... cannot correct this last type of error, however, we have developed a system which is sufficiently robust to handle the other problems described above. Rather than apply these progra...

Ngày tải lên: 22/02/2014, 09:20

... natural language processing sys- tems today strives for the construction of robust and portable systems) A system is robust, if it can handle a large variety of user inputs without giving up ... (;ci'many lhnaih !,1'~!! at I)! ll)iBM I.BITNI'71' ABSTRACT The desire to construct robust and portable na- tural language systems has led to research on how a core...

Ngày tải lên: 22/02/2014, 10:20

... June 2005. c 2005 Association for Computational Linguistics Towards Finding and Fixing Fragments: Using ML to Identify Non-Sentential Utterances and their Antecedents in Multi-Party Dialogue David ... processing (full parses, and also in- formation about discourse structure) and hence are not very robust. We have defined a well-defined subtask of this problem, namely identifying frag- ments...

Ngày tải lên: 08/03/2014, 04:22

... genre classification that is cross-lingual. Cross-lingual genre classification (CLGC) differs 11 from both poly-lingual and language-independent genre classification. CLGC entails training a genre classification ... Bonnie Webber. 2011. Stable classification of text genres. Comput. Linguist., 37:385–393. Peter Prettenhofer and Benno Stein. 2010. Cross- language text classification using...

Ngày tải lên: 17/03/2014, 22:20