Báo cáo khoa học: "Finding Anchor Verbs for Biomedical IE Using Predicate-Argument Structures" potx
... Finding Anchor Verbs for Biomedical IE Using Predicate-Argument Structures Akane YAKUSHIJI† Yuka TATEISI‡† Yusuke MIYAO† †Department of Computer Science, University of Tokyo Hongo ... finding anchor verbs, although our final purpose is construction of extraction rules. Most anchor verbs take topi- cal nouns, i.e., nouns describing target entities for IE, as their argumen...
Ngày tải lên: 31/03/2014, 03:20
... 2012. c 2012 Association for Computational Linguistics Finding Salient Dates for Building Thematic Timelines R ´ emy Kessler LIMSI-CNRS Orsay, France kessler@limsi.fr Xavier Tannier Univ. Paris-Sud, LIMSI-CNRS Orsay, ... temporal information and uses only this information to detect salient dates for the construction of event timelines. Other types of content are used for initial them...
Ngày tải lên: 23/03/2014, 14:20
... full- form phrases; • Step-4: induce translation entries for Chinese abbreviations by using their full-form phrases as bridges; • Step-5: augment the baseline system with translation entries obtained ... Translation Induction for Chinese Abbreviations Given a Chinese abbreviation and its full-form, we induce English translation entries for the abbrevia- tion by using the full-form a...
Ngày tải lên: 20/02/2014, 09:20
Tài liệu Báo cáo khoa học: "A Unified Framework for Automatic Evaluation using N-gram Co-Occurrence Statistics" pptx
... A Unified Framework for Automatic Evaluation using N-gram Co-Occurrence Statistics Radu SORICUT Information Sciences Institute University of Southern California 4676 Admiralty ... variation, 83.04%. For comparison purposes, we also computed the value of R 2 for adequacy using the BLEU score formula given in (Papineni et al., 2002), for the 7 systems using the same one...
Ngày tải lên: 20/02/2014, 16:20
Báo cáo khoa học: "A Bilingual Concordancer for Domain-Specific Computer Assisted Translation" potx
... retrieved sentence pairs, we propose a correlation function modified from the Dice coefficient for assessing the correlation between the query and the translation equivalents. The performances ... Ming-Hong Bai 1,2 Yu-Ming Hsieh 1,2 Keh-Jiann Chen 1 Jason S. Chang 2 1 Institute of Information Science, Academia Sinica, Taiwan 2 Department of Computer Science, National Tsing-Hua Un...
Ngày tải lên: 07/03/2014, 18:20
Báo cáo khoa học: "A Support Platform for Event Detection using Social Intelligence" pot
... to present data for. 1 Introduction Social media and micro-blogs have entered the mainstream of society as a means for individu- als to stay in touch with friends, for companies to market products ... Association for Computational Linguistics, pages 69–72, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics A Support Platform for Event Detection...
Ngày tải lên: 08/03/2014, 21:20
Báo cáo khoa học: "An Automatic Method for Summary Evaluation Using Multiple Evaluation Results by a Manual Method" pptx
... For each step, we need to discuss the following points. (Step 1) 1. How many summaries, and what type (variety) of summaries should be prepared? Kazawa et al. prepared 6 summaries for ... Association for Computational Linguistics An Automatic Method for Summary Evaluation Using Multiple Evaluation Results by a Manual Method Hidetsugu Nanba Faculty of Information Sciences,...
Ngày tải lên: 17/03/2014, 04:20
Báo cáo khoa học: "Semi-supervised Training for the Averaged Perceptron POS Tagger" potx
... tags First letter of previous tag Word forms Current word form Previous word form Previous two word forms Following word form Following two word forms Last but one word form Current word affixes Prefixes ... significant margins (we have achieved 4.12 % relative error reduction for English and 4.86 % for Czech over the best pre- viously published results, single or combined), using a single...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "Designing spelling correctors for inflected languages using lexical transducers" pdf
... cess. A very important new feature is the use of user dictionaries whose entries can recognise both the original and inflected forms. In languages with a high level of inflection such as Basque ... transducers and is built using the fst library of Inxight 1. A lexi- cal transducer (Karttunen, 94) is a finite-state au- tomaton that maps inflected surface forms to lex- ical forms, a...
Ngày tải lên: 17/03/2014, 23:20
Báo cáo khoa học: "Automatic Evaluation Method for Machine Translation using Noun-Phrase Chunking" pptx
... of 7th NTCIR Workshop Meeting on Evaluation of Information Access Technolo- gies: Information Retrieval, Question Answer- ing and Cross-lingual Information Access, 389– 400. Gregor Leusch, Nicola ... correlation coefficients obtained using our method and other methods are statisti- cally significant at the 5% or lower signifi- cance level for adequacy. Results confirmed that our method using...
Ngày tải lên: 23/03/2014, 16:20