| Presentation | 2005/7/15 Feature Analysis of Explanatory Documents for How-to Type Question Answering Naoki ASANOMA, Osamu FURUSE, Ryoji KATAOKA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We are investigating a retrieval mechanism that provides adequate explanations to how-to type questions more efficiently than conventional web searches. Because explanatory documents have various document styles, we defined two measures for evaluating the probable likelihood of answer to how-to type questions. We examined the features of documents with high values of each measure, and the feasibility to estimate the measured values based on the document features. The experimental results showed a positive correlation between the presence of itemization and each measure. Regression analysis showed the possibilities for estimating the accordance value as one of two measures. Although the analysis of the cases in which the documents with low accordance values was assigned a high estimation value, deep natural language analysis is necessary to improve the estimation accuracy. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Explanatory procedure retrieval / How-to type question answering / Answer likelihood / Document style / Itemization |
| Paper # | NLC2005-9 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2005/7/15(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 | 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) | Feature Analysis of Explanatory Documents for How-to Type Question Answering |
| Sub Title (in English) | |
| Keyword(1) | Explanatory procedure retrieval |
| Keyword(2) | How-to type question answering |
| Keyword(3) | Answer likelihood |
| Keyword(4) | Document style |
| Keyword(5) | Itemization |
| 1st Author's Name | Naoki ASANOMA |
| 1st Author's Affiliation | NTT Cyber Solutions Laboratories, NTT Corporation() |
| 2nd Author's Name | Osamu FURUSE |
| 2nd Author's Affiliation | NTT Cyber Solutions Laboratories, NTT Corporation |
| 3rd Author's Name | Ryoji KATAOKA |
| 3rd Author's Affiliation | NTT Cyber Solutions Laboratories, NTT Corporation |
| Date | 2005/7/15 |
| Paper # | NLC2005-9 |
| Volume (vol) | vol.105 |
| Number (no) | 203 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |