Results 1 - 10 of 1,803

Evaluating Speech-Driven IR in the NTCIR-3 Web Retrieval Task

by Atsushi Fujii, Katunobu Itou - In Proceedings of the 3rd NTCIR Workshop on Research in Information Retrieval, Automatic Text Summarization and Question Answering , 2003
"... Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates retrieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web retrieva ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates retrieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web

University of tokyo/ricoh at ntcir-3 web retrieval task

by Masashi Toyoda, Masaru Kitsuregawa, Hiroko Mano, Hideo Itoh, Yasushi Ogawa - In Proceedings of the Third NTCIR Workshop on research in information Retrieval, Automatic Text Summarization and Question Answering. http://research.nii.ac.jp/ntcir/workshop/OnlineProceedings3/NTCIR3-WEB-ToyodaM.pdf , 2002
"... In NTCIR-3 Web Task, we introduced new approaches in (1) similarity retrieval using one known relevant document and pseudo-relevance feedback and (2) topic and target retrieval incorporating link analysis. The experiments showed that both approaches werepromising. ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
In NTCIR-3 Web Task, we introduced new approaches in (1) similarity retrieval using one known relevant document and pseudo-relevance feedback and (2) topic and target retrieval incorporating link analysis. The experiments showed that both approaches werepromising.

Building a test collection for speech-driven Web retrieval

by Atsushi Fujii, Katunobu Itou - In Proc. EUROSPEECH , 2003
"... This paper describes a test collection (benchmark data) for retrieval systems driven by spoken queries. This collection was produced in the subtask of the NTCIR-3 Web retrieval task, which was performed in a TREC-style evaluation workshop. The search topics and document collection for the Web retrie ..."
Abstract - Cited by 11 (2 self) - Add to MetaCart
This paper describes a test collection (benchmark data) for retrieval systems driven by spoken queries. This collection was produced in the subtask of the NTCIR-3 Web retrieval task, which was performed in a TREC-style evaluation workshop. The search topics and document collection for the Web

Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product Reviews

by Kushal Dave, Steve Lawrence, David M. Pennock , 2003
"... The web contains a wealth of product reviews, but sifting through them is a daunting task. Ideally, an opinion mining tool would process a set of search results for a given item, generating a list of product attributes (quality, features, etc.) and aggregating opinions about each of them (poor, mixe ..."
Abstract - Cited by 453 (0 self) - Add to MetaCart
The web contains a wealth of product reviews, but sifting through them is a daunting task. Ideally, an opinion mining tool would process a set of search results for a given item, generating a list of product attributes (quality, features, etc.) and aggregating opinions about each of them (poor

Syskill & Webert: Identifying interesting web sites

by Michael Pazzani, Jack Muramatsu, Daniel Billsus - In Proc. 13th Natl. Conf. on Artificial Intelligence , 1998
"... We describe Syskill & Webert, a software agent that learns to rate pages on the World Wide Web (WWW), deciding what pages might interest a user. The user rates explored pages on a three point scale, and Syskill & Webert learns a user profile by analyzing the information on a page. The user p ..."
Abstract - Cited by 353 (5 self) - Add to MetaCart
algorithm on this task. . 1 Introduction There is a vast amount of information on the World Wide Web (WWW) and more is becoming available daily. How can a user locate information that might be useful to that user? In this paper, we discuss Syskill & Webert, a software agent that learns a profile of a

Evaluating speech-driven web retrieval in the third NTCIR workshop

by Atsushi Fujii, Katunobu Itou - in Proc. AAAI Spring Symposium: Intelligent Multimedia Knowledge Management , 2003
"... Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates re-trieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web retriev ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
Speech recognition has of late become a practical technology for real world applications. For the purpose of research and development in speech-driven retrieval, which facilitates re-trieving information with spoken queries, we organized the speech-driven retrieval subtask in the NTCIR-3 Web

Evaluating Multiple LVCSR Model Combination

by In Ntcir- Speech-Driven
"... This paper studies speech-driven Web retrieval models which accepts spoken search topics (queries) in the NTCIR-3 Web retrieval task. The major focus of this paper is on improving speech recognition accuracy of spoken queries and then improving retrieval accuracy in speech-driven Web retrieval. We e ..."
Abstract - Add to MetaCart
This paper studies speech-driven Web retrieval models which accepts spoken search topics (queries) in the NTCIR-3 Web retrieval task. The major focus of this paper is on improving speech recognition accuracy of spoken queries and then improving retrieval accuracy in speech-driven Web retrieval. We

NTCIR-3 WEB Experiments at Osaka Kyoiku University — Towards Index Partitioning and Parallel Retrieval —

by Takashi Sato, Yukikazu Kyo, Kihei Kobata
"... Long gram-based indices are experimented at NTCIR-3 WEB task . To make gram-based indices, no analyses such as morphological ones are required. 2 byte characters extracted from NTCIR-3 `cooked' version of WEB task corpus. The total index size is 26 Gbyte and time to make indices is about 18 ho ..."
Abstract - Add to MetaCart
Long gram-based indices are experimented at NTCIR-3 WEB task . To make gram-based indices, no analyses such as morphological ones are required. 2 byte characters extracted from NTCIR-3 `cooked' version of WEB task corpus. The total index size is 26 Gbyte and time to make indices is about 18

CMU in Cross-Language Information Retrieval at NTCIR-3

by Yiming Yang, Nianli Ma
"... We participated in the Cross-Language Information Retrieval evaluation at NTCIR-3 for the English-Chinese and English-Japanese tasks. We examined several approaches to query translation, including the use of a commercial machine translation system, a thesaurus that is automatically extracted from a ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
We participated in the Cross-Language Information Retrieval evaluation at NTCIR-3 for the English-Chinese and English-Japanese tasks. We examined several approaches to query translation, including the use of a commercial machine translation system, a thesaurus that is automatically extracted from a

Cross-Lingual Information Retrieval (CLIR) Task at the NTCIR Workshop 3

by Kazuaki Kishida, Kuang-hua Chen, Sukhoon Lee, Hsin-hsi Chen, Sung Hyon Myaeng, Noriko Kando, Koji Eguchi, Kazuko Kuriyama
"... Information and Communications University ..."
Abstract - Add to MetaCart
Information and Communications University
Results 1 - 10 of 1,803