Tài liệu Báo cáo khoa học: "Using Automatically Transcribed Dialogs to Learn User Models in a Spoken Dialog System" doc

... Laboratory AT&T Labs — Research Florham Park, NJ 07932, USA jdw@research.att.com Abstract We use an EM algorithm to learn user mod- els in a spoken dialog system. Our method requires automatically transcribed ... Dialogs to Learn User Models in a Spoken Dialog System Umar Syed Department of Computer Science Princeton University Princeton, NJ 08540, USA...

Ngày tải lên: 20/02/2014, 09:20

... with Semantic Affinity Pat- terns and Relevant Regions. In Proc. Joint Confer- ence on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, 2007, pages ... Christopher Manning. 2005. Incorporating Non-local Information into Information Extraction Systems by Gibbs Sam- pling. In Proc. 43rd Annual Meeting of the Associa- tion for Computational...

Ngày tải lên: 20/02/2014, 04:20

... Gao, J., Goodman, J., Li, M. and Lee K.F. 2002. To- ward a Unified Approach to Statistical Lan- guage Modeling for Chinese, ACM Transactions on Asian Language Information Processing, 1(1):3-33. ... system and user WP data- base. From Table 3c, we get the average tonal and toneless STW improvements of the MSIME and the BiGram by using the WSM as an adap- tation processing are 37.2...

Ngày tải lên: 20/02/2014, 12:20

... diacylhydrazine toxicity to Lepidop- teran and Coleopteran insect pests. QSAR Comb Sci 27, 1098–1112. 20 Wheelock CE, Nakagawa Y, Harada T, Oikawa N, Akamatsu M, Smagghe G, Stefanou D, Iatrou K & Swevers ... Resistance and cross-resistance to imidacloprid and thiamethoxam in the Colorado potato beetle Leptinotarsa decemlineata . Pest Manag Sci 63, 32–41. 29 Khelifi M, Lague C & d...

Ngày tải lên: 18/02/2014, 08:20

... (anglicisms) are used in a German- language Internet hip hop forum, and what factors contribute to their uptake. 1 Introduction Because English has established itself as something of a global ... compounding). The baseline classifier We used MALLET (Mc- Callum, 2002) to train a maximum entropy classi- fier, using character 1- through 6-grams (including word boundaries) as features....

Ngày tải lên: 19/02/2014, 19:20

... chain corresponding to the catalytic domain (C domain); and the B chain corresponding to the translocation domain (T domain) and the receptor-binding domain. The C and T domains remain covalently linked by a disulfide ... Following binding to its cell-surface receptor, diphtheria toxin is internalized through the clathrin-coated pathway. The acidic pH in the endo- some triggers a c...

Ngày tải lên: 16/02/2014, 09:20

... the range of 5–10 kDa, typically including two dominating peaks at approximately m ⁄ z 7000. As mycelia and spores largely remained intact, and the extraction solution contained acetonitrile and ... signals of m ⁄ z 8859, 8802 and 7521 appearing (Fig. 4B). To obtain a preliminary correlation of observed masses with hydrophobin data, we again calculated from the available sequence data set...

Ngày tải lên: 19/02/2014, 02:20

... 2010. c 2010 Association for Computational Linguistics Using Smaller Constituents Rather Than Sentences in Active Learning for Japanese Dependency Parsing Manabu Sassano Yahoo Japan Corporation Midtown Tower, 9-7-1 ... Akasaka, Minato-ku, Tokyo 107-6211, Japan msassano@yahoo-corp.jp Sadao Kurohashi Graduate School of Informatics, Kyoto University Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501,...

Ngày tải lên: 20/02/2014, 04:20

... source and target domains. In particular, no labeled data is provided for the target domain. In this paper, we describe a cross-domain senti- ment classification method using an automatically created ... previously been applied to the task of cross-domain sentiment classification. In our method, we use the automatically created thesaurus to expand feature vectors in a binary...

Ngày tải lên: 20/02/2014, 04:20

... subtrees are specified in advance, in an adaptor grammar the subtrees, as well as their probabilities, are learnt from the train- ing data. In order to make parsing and inference tractable we require ... the adaptor grammar inference procedure is that it gives us a way of learning these interacting linguistic structures simultaneously. Adaptor grammars are also interesting because th...

Ngày tải lên: 20/02/2014, 09:20