Advances in Intelligent MultiMedia: MultiModal semantic representation

P McKevitt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Intelligent MultiMedia or MultiModal systems involve the computer processing, understanding and production of inputs and outputs from at least speech, text, and visual information in terms of semantic representations. One of the central questions for these systems is what form of semantic representation should be used. Here, we look at current trends in multimodal semantic representation which are mainly XML and frame- based, relate our experiences in the development of multimodal systems (CHAMELEON and CONFUCIUS) and conclude that producer/consumer, intention (speech acts), semantic-content, and timestamps are four important components of any multimodal semantic representation.
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsH Sakaki
Place of PublicationMeisei University (Hino Campus), Hino-shi, Tokyo, Japan
Pages2-13
Number of pages12
Publication statusPublished - Aug 2005
EventProc. of the Pacific Rim International Conference on Computational Linguistics (PACLING-05) - Meisei University (Hino Campus), Hino-shi, Tokyo, Japan
Duration: 1 Aug 2005 → …

Conference

ConferenceProc. of the Pacific Rim International Conference on Computational Linguistics (PACLING-05)
Period1/08/05 → …

Fingerprint

Semantics
XML
Processing

Cite this

McKevitt, P. (2005). Advances in Intelligent MultiMedia: MultiModal semantic representation. In H. Sakaki (Ed.), Unknown Host Publication (pp. 2-13). Meisei University (Hino Campus), Hino-shi, Tokyo, Japan.
McKevitt, P. / Advances in Intelligent MultiMedia: MultiModal semantic representation. Unknown Host Publication. editor / H Sakaki. Meisei University (Hino Campus), Hino-shi, Tokyo, Japan, 2005. pp. 2-13
@inproceedings{9feb9f592e4e4ba8a5b5fa948694ca71,
title = "Advances in Intelligent MultiMedia: MultiModal semantic representation",
abstract = "Intelligent MultiMedia or MultiModal systems involve the computer processing, understanding and production of inputs and outputs from at least speech, text, and visual information in terms of semantic representations. One of the central questions for these systems is what form of semantic representation should be used. Here, we look at current trends in multimodal semantic representation which are mainly XML and frame- based, relate our experiences in the development of multimodal systems (CHAMELEON and CONFUCIUS) and conclude that producer/consumer, intention (speech acts), semantic-content, and timestamps are four important components of any multimodal semantic representation.",
author = "P McKevitt",
year = "2005",
month = "8",
language = "English",
pages = "2--13",
editor = "H Sakaki",
booktitle = "Unknown Host Publication",

}

McKevitt, P 2005, Advances in Intelligent MultiMedia: MultiModal semantic representation. in H Sakaki (ed.), Unknown Host Publication. Meisei University (Hino Campus), Hino-shi, Tokyo, Japan, pp. 2-13, Proc. of the Pacific Rim International Conference on Computational Linguistics (PACLING-05), 1/08/05.

Advances in Intelligent MultiMedia: MultiModal semantic representation. / McKevitt, P.

Unknown Host Publication. ed. / H Sakaki. Meisei University (Hino Campus), Hino-shi, Tokyo, Japan, 2005. p. 2-13.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Advances in Intelligent MultiMedia: MultiModal semantic representation

AU - McKevitt, P

PY - 2005/8

Y1 - 2005/8

N2 - Intelligent MultiMedia or MultiModal systems involve the computer processing, understanding and production of inputs and outputs from at least speech, text, and visual information in terms of semantic representations. One of the central questions for these systems is what form of semantic representation should be used. Here, we look at current trends in multimodal semantic representation which are mainly XML and frame- based, relate our experiences in the development of multimodal systems (CHAMELEON and CONFUCIUS) and conclude that producer/consumer, intention (speech acts), semantic-content, and timestamps are four important components of any multimodal semantic representation.

AB - Intelligent MultiMedia or MultiModal systems involve the computer processing, understanding and production of inputs and outputs from at least speech, text, and visual information in terms of semantic representations. One of the central questions for these systems is what form of semantic representation should be used. Here, we look at current trends in multimodal semantic representation which are mainly XML and frame- based, relate our experiences in the development of multimodal systems (CHAMELEON and CONFUCIUS) and conclude that producer/consumer, intention (speech acts), semantic-content, and timestamps are four important components of any multimodal semantic representation.

M3 - Conference contribution

SP - 2

EP - 13

BT - Unknown Host Publication

A2 - Sakaki, H

CY - Meisei University (Hino Campus), Hino-shi, Tokyo, Japan

ER -

McKevitt P. Advances in Intelligent MultiMedia: MultiModal semantic representation. In Sakaki H, editor, Unknown Host Publication. Meisei University (Hino Campus), Hino-shi, Tokyo, Japan. 2005. p. 2-13