Báo cáo khoa học: "Combining Multiple Knowledge Sources for Dialogue Segmentation in Multimedia Archives" ppt

... Computational Linguistics Combining Multiple Knowledge Sources for Dialogue Segmentation in Multimedia Archives Pei-Yun Hsueh School of Informatics University of Edinburgh Edinburgh, UK EH8 9WL p.hsueh@ed.ac.uk Johanna ... of Informatics University of Edinburgh Edinburgh, UK EH8 9WL J.Moore@ed.ac.uk Abstract Automatic segmentation is important for making multimedia archi...

Ngày tải lên: 23/03/2014, 18:20

... INTEGRATING MULTIPLE KNOWLEDGE SOURCES FOR DETECTION AND CORRECTION OF REPAIRS IN HUMAN-COMPUTER DIALOG* John Bear, John Dowding, Elizabeth Shriberg t SRI International Menlo Park, California ... alone contains insufficient information for reliably correcting these sentences. The relevant substring is taken to be the phrase constituting the matched string plus in- terven...

Ngày tải lên: 31/03/2014, 06:20

... interest 1 1 interest rate -2 -1 principal and interest -1 1 national interest in 1 2 interest and dividends -3 -1 sale of an interest -2 in the interest of -1 2 an interest in a 1 3 interest ... morphological form of w in the sentence s. For a noun, the value for this feature is either singular or plural; for a verb, the value is one of infinitive (as in the uninfl...

Ngày tải lên: 23/03/2014, 20:21

... examined various resources for acquiring paraphrases, including thesauri, monolin- gual corpora, bilingual corpora, and the web. The- sauri, such as WordNet, have been widely used for extracting ... Niu 2 , Ming Zhou 2 , Ting Liu 1 , Sheng Li 1 1 Harbin Institute of Technology, Harbin, China {zhaosq,tliu,lisheng}@ir.hit.edu.cn 2 Microsoft Research Asia, Beijing, China {chengniu,mingzhou}@...

Ngày tải lên: 17/03/2014, 02:20

... according to this scheme. A more detailed description of how DATALOG constructs interpreta- tions is contained in another report [8]. During parsing, semantic information is col- lected in "semantic" ... operate in parallel, communicating information back and forth. This communication (represented by the "interface" portions of the diagram) allows a lin- gui...

Ngày tải lên: 17/03/2014, 19:21

... corpus for frequency measure- ments and exacting selectional constraints. 2.2 Combining linguistic resources In this section, we present an algorithm for merging data from the four resources in ... in a system. In this paper, we present work in building a rich, large-scale, and reusable lexicon for gener- ation by combining multiple, heterogeneous lin- guistic resources...

Ngày tải lên: 31/03/2014, 04:20

... Proceedings of the 18th Inter- national Conference on Machine Learning, pages 282–289, San Francisco, California, USA. Associ- ation for Computing Machinery. Minh-Thang Luong, Preslav Nakov, and Min-Yen Kan. ... fluency problem in English- Hindi SMT. In Proceedings of the Joint Confer- ence of the 47th Annual Meeting of the Associa- tion for Computational Linguistics and the 4th In-...

Ngày tải lên: 30/03/2014, 21:20

... an inducible, Ca 2+ -independent form (i-mtNOS). In iNOS + ⁄ + mice, sepsis induced a significant increase in i-mtNOS activity, whereas mtNOS activity remained unchanged (Fig. 1A). Control iNOS – ... transformation of l-arginine to l-citrulline, due to mtNOS inhibition (14.67 ± 3.09 versus 1.09 ± 0.87 pmol citrullineÆmin )1 Æmg )1 protein, CLP and CLP + l-NMMA, respectively) [9,11,12]. iNO...

Ngày tải lên: 19/02/2014, 00:20

... re-ranking model performs rather well for a limited number of candidate structures, and out- performs Charniak’s model when k = 5. In this case we observe a small boost in performance for the ... likelihoods of generating three aspects of the structure, according to the three models (BGM, BEM, WFM) specified in equations (2-4) and explained in the main text. 3 A probabilistic Model...

Ngày tải lên: 20/02/2014, 04:20

... meth- ods for language models applied to ad hoc information retrieval. In Proceedings of SIGIR, pages 334-342. 662 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, ... to a linear ranking framework for question retrieval in which different models are incorporated as features. We consider learning a relevance function of the following general,...

Ngày tải lên: 20/02/2014, 04:20