| Presentation | 2005-09-21 Automatic Annotation and its Features of Japanese and English Sentence Types Yohei SEKI, Noriko KANDO, Masaki AONO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The purpose of thie study it to testing for using contextual information as a subjective feature, which is not focused on in other related works for annotating subjectivity. Subjectivity usually refers to aspects of language used to express author's or autority's opinions, evaluations, and speculations. Subjectivity analysis was mainly applied to measure the perceptions of Web site reputation, which did not contain complex text structure, but did contain some key extraction patterns. On the other hand, subjectivity analysis on newspaper articles for information analysis in political domains, text structure also performs as a good clue. We evaluated the effectiveness of contextual information with two datasets, which containing English and Japanese newspaper articles with manually annotated opinion information. We found significant improvements for accuracy, precision, and recall for automatic annotation by using contextual information as a feature. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Sentence-type Annotation / Subjectivity Analysis / Context |
| Paper # | NLC2005-28,PRMU2005-55 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2005/9/14(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) | Automatic Annotation and its Features of Japanese and English Sentence Types |
| Sub Title (in English) | |
| Keyword(1) | Sentence-type Annotation |
| Keyword(2) | Subjectivity Analysis |
| Keyword(3) | Context |
| 1st Author's Name | Yohei SEKI |
| 1st Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology() |
| 2nd Author's Name | Noriko KANDO |
| 2nd Author's Affiliation | National Institute of Informatics |
| 3rd Author's Name | Masaki AONO |
| 3rd Author's Affiliation | Department of Information and Computer Sciences, Toyohashi University of Technology |
| Date | 2005-09-21 |
| Paper # | NLC2005-28,PRMU2005-55 |
| Volume (vol) | vol.105 |
| Number (no) | 299 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |