| Presentation | 2002/12/12 Generating Rules to Understand Spontaneous User Input to an Impression-Based Music-Retrieval System Tadahiko KUMAMOTO, Kimiko OHTA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Impression-based music retrieval is the best way to find pieces of music that suit the preferences, senses, or mental states of users. In a music-retrieval system of this kind, the system presents a relatively short set of words that denote impressions; the user selects words from this set for input to the system. With this approach, increases in the numbers of words presented lead to increase the cost to the user in terms of the time required to enter impressions. On the other hand, a set of words that is too limited will often leave users unable to accurately represent their target impressions. In order for the system to understand impression words, the system must have rules for transforming the words into a suitable form, i.e., into retrieval conditions. However, generating these rules is costly, since this process requires that many subjects listen to and evaluate many pieces of music against the target words. Increases in the numbers of words presented lead to increases in the cost of this process, such that the process is impracticable with large numbers of word. In this paper, we propose a new approach to the rule-generation process, in which the rules for use in deriving retrieval conditions from impression words are obtained by evaluating target impression words against impression scales that we have devised. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | natural language understanding / impression-based music retrieval / natural language interface |
| Paper # | NLC2002-57 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2002/12/12(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 | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Generating Rules to Understand Spontaneous User Input to an Impression-Based Music-Retrieval System |
| Sub Title (in English) | |
| Keyword(1) | natural language understanding |
| Keyword(2) | impression-based music retrieval |
| Keyword(3) | natural language interface |
| 1st Author's Name | Tadahiko KUMAMOTO |
| 1st Author's Affiliation | Keihanna Human Info-Communication Research Center, Communications Research Laboratory() |
| 2nd Author's Name | Kimiko OHTA |
| 2nd Author's Affiliation | Keihanna Human Info-Communication Research Center, Communications Research Laboratory |
| Date | 2002/12/12 |
| Paper # | NLC2002-57 |
| Volume (vol) | vol.102 |
| Number (no) | 527 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |