Presentation | 2009-05-22 Unsupervised extraction of content-related annotations Tomoharu IWATA, Takeshi YAMADA, Naonori UEDA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a topic model for extracting content-related annotations. In social annotation services, some annotations do not relate to their contents since users can attach annotations freely. The extraction of content-related annotations can improve the information retrieval performance or can be used as a preprocessing step in machine learning tasks such as text classification and image recognition. The proposed model is a generative model for content and annotations, and the inference and parameter estimation are carried out based on a stochastic EM algorithm. We demonstrate the effectiveness of the proposed method by using synthetic data and real social annotation data for text and images. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Topic model / Social annotation / Folksonomy |
Paper # | AI2009-3 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2009/5/15(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Unsupervised extraction of content-related annotations |
Sub Title (in English) | |
Keyword(1) | Topic model |
Keyword(2) | Social annotation |
Keyword(3) | Folksonomy |
1st Author's Name | Tomoharu IWATA |
1st Author's Affiliation | NTT Communication Science Laboratories() |
2nd Author's Name | Takeshi YAMADA |
2nd Author's Affiliation | NTT Communication Science Laboratories |
3rd Author's Name | Naonori UEDA |
3rd Author's Affiliation | NTT Communication Science Laboratories |
Date | 2009-05-22 |
Paper # | AI2009-3 |
Volume (vol) | vol.109 |
Number (no) | 51 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |