Enhancing multi-lingual information extraction via cross-media inference and fusion

Adam Lee, Marissa Passantino, Heng Ji, Guojun Qi, Thomas Huang

Research output: Contribution to conferencePaper

Abstract

We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level knowledge (concepts, relations and events). Beyond standard information fusion, we exploited video extraction results and significantly improved text Information Extraction. We further extended our methods to multi-lingual environment (English, Arabic and Chinese) by presenting a case study on cross-lingual comparable corpora acquisition based on video comparison.

Original languageEnglish (US)
Pages630-638
Number of pages9
StatePublished - Dec 1 2010
Event23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China
Duration: Aug 23 2010Aug 27 2010

Other

Other23rd International Conference on Computational Linguistics, Coling 2010
CountryChina
CityBeijing
Period8/23/108/27/10

Fingerprint

Cross Media
Information fusion
video
event
Fusion
Inference
Information Extraction

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Lee, A., Passantino, M., Ji, H., Qi, G., & Huang, T. (2010). Enhancing multi-lingual information extraction via cross-media inference and fusion. 630-638. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Enhancing multi-lingual information extraction via cross-media inference and fusion. / Lee, Adam; Passantino, Marissa; Ji, Heng; Qi, Guojun; Huang, Thomas.

2010. 630-638 Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.

Research output: Contribution to conferencePaper

Lee, A, Passantino, M, Ji, H, Qi, G & Huang, T 2010, 'Enhancing multi-lingual information extraction via cross-media inference and fusion', Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China, 8/23/10 - 8/27/10 pp. 630-638.
Lee A, Passantino M, Ji H, Qi G, Huang T. Enhancing multi-lingual information extraction via cross-media inference and fusion. 2010. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.
Lee, Adam ; Passantino, Marissa ; Ji, Heng ; Qi, Guojun ; Huang, Thomas. / Enhancing multi-lingual information extraction via cross-media inference and fusion. Paper presented at 23rd International Conference on Computational Linguistics, Coling 2010, Beijing, China.9 p.
@conference{38cac085c26a4977b97f557d4d0c65eb,
title = "Enhancing multi-lingual information extraction via cross-media inference and fusion",
abstract = "We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level knowledge (concepts, relations and events). Beyond standard information fusion, we exploited video extraction results and significantly improved text Information Extraction. We further extended our methods to multi-lingual environment (English, Arabic and Chinese) by presenting a case study on cross-lingual comparable corpora acquisition based on video comparison.",
author = "Adam Lee and Marissa Passantino and Heng Ji and Guojun Qi and Thomas Huang",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
pages = "630--638",
note = "23rd International Conference on Computational Linguistics, Coling 2010 ; Conference date: 23-08-2010 Through 27-08-2010",

}

TY - CONF

T1 - Enhancing multi-lingual information extraction via cross-media inference and fusion

AU - Lee, Adam

AU - Passantino, Marissa

AU - Ji, Heng

AU - Qi, Guojun

AU - Huang, Thomas

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level knowledge (concepts, relations and events). Beyond standard information fusion, we exploited video extraction results and significantly improved text Information Extraction. We further extended our methods to multi-lingual environment (English, Arabic and Chinese) by presenting a case study on cross-lingual comparable corpora acquisition based on video comparison.

AB - We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts) into a coherent common representation including multi-level knowledge (concepts, relations and events). Beyond standard information fusion, we exploited video extraction results and significantly improved text Information Extraction. We further extended our methods to multi-lingual environment (English, Arabic and Chinese) by presenting a case study on cross-lingual comparable corpora acquisition based on video comparison.

UR - http://www.scopus.com/inward/record.url?scp=80053431447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053431447&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:80053431447

SP - 630

EP - 638

ER -