I2R at NTCIR5
نویسندگان
چکیده
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¶W QHHG WR SUH VSHFLI\ WKH QXPEHU RI SVHXGR UHOHYDQFH GRFXPHQWV ([SHULHQFHV VKRZ RXU PHWKRG DFKLHYHV PHDQ DYHUDJH SUHFLVLRQ RQ 7 RQO\ UXQ 7LWOH EDVHG DW ULJLG UHOD[ UHOHYDQW MXGJPHQW DQG PHDQ DYHUDJH SUHFLVLRQ RQ ' RQO\ UXQ VKRUW GHVFULSWLRQ EDVHG DW ULJLG UHOD[ UHOHYDQW MXGJPHQW LQ 6/,5 RQ &KLQHVH /DQJXDJH .H\ZRUGV 'RFXPHQW 5H UDQNLQJ 7HUP ([WUDFWLRQ &KLQHVH ,QIRUPDWLRQ 5HWULHYDO 4XHU\ ([SDQVLRQ
منابع مشابه
CMU JAVELIN System for NTCIR5 CLQA1
In this paper, we describe the JAVELIN Cross Language Question Answering system, which includes modules for question analysis, keyword translation, document retrieval, information extraction and answer generation. In the NTCIR5 CLQA1 evaluation, our system achieved 7.5% and 10.0% accuracy in the English-to-Chinese and English-to-Japanese subtasks, respectively. An overall analysis and a detaile...
متن کاملI2R-NUS-MSRA at TAC 2011: Entity Linking
In this paper, we report the joint participation of I2R-NUS team and MSRA team in entity linking task for Knowledge Base Population at Text Analysis Conference 2011. I2R-NUS team submitted two results with the full system and the partial system for diagnosis purpose. Both results incorporate the new technologies: acronym expansion, instance selection and topic modeling proposed in our recent pa...
متن کاملCAMA: Efficient Modeling of the Capture Effect for Low-Power
BEHNAM DEZFOULI and MARJAN RADI, Department of Computer Science, Faculty of Computing, Universiti Teknologi Malaysia (UTM), Malaysia; Networking Protocols Department, Institute for Infocomm Research (I2R), A*STAR, Singapore KAMIN WHITEHOUSE, Department of Computer Science, University of Virginia, USA SHUKOR ABD RAZAK, Department of Computer Science, Faculty of Computing, Universiti Teknologi Ma...
متن کاملNUS-I2R: Learning a Combined System for Entity Linking
In this paper, we report the joint participation of NUS and I2R team in Knowledge Base Population at Text analysis conference 2010. For Entity Linking, we analyze IR approaches and SVM classification in the disambiguation stage and develop a supervised learner for combining these approaches. The combined system performs better than the individual components and achieves results much better than...
متن کاملThe BM-I2R Haitian-Créole-to-English translation system description for the WMT 2011 evaluation campaign
This work describes the Haitian-Créole to English statistical machine translation system built by Barcelona Media Innovation Center (BM) and Institute for Infocomm Research (I2R) for the 6th Workshop on Statistical Machine Translation (WMT 2011). Our system carefully processes the available data and uses it in a standard phrase-based system enhanced with a source context semantic feature that h...
متن کامل