| Description: | This paper presents a method for automatic topic identification using an encyclopedic graph derived from Wikipedia. The system is found to exceed the performance of previously proposed machine learning algorithms for topic identification, with an annotation consistency comparable to human annotations. |
|---|---|
| Creator(s): | |
| Creation Date: | May 2009 |
| Partner(s): |
UNT College of Engineering
|
| Collection(s): |
UNT Scholarly Works
|
| Usage: |
Total Uses: 24
Past 30 days: 0
Yesterday: 0
|
| Creator (Author): |
Coursey, Kino High
University of North Texas |
|
|---|---|---|
| Creator (Author): |
Mihalcea, Rada
University of North Texas |
|
| Creator : |
Moen, William E.
University of North Texas |
|
| Publisher Info: |
Publisher Name: Association for Computational Linguistics (ACL)
Place of Publication: [Stroudsburg, Pennsylvania]
|
|
| Original Creation Date: | May 2009 | |
| Description: | This paper presents a method for automatic topic identification using an encyclopedic graph derived from Wikipedia. The system is found to exceed the performance of previously proposed machine learning algorithms for topic identification, with an annotation consistency comparable to human annotations. |
|
| Degree: |
Department:
Computer Science and Engineering
Department:
Library and Information Science
|
|
| Physical Description: |
9 p. |
|
| Language(s): | ||
| Subject(s): |
|
|
| Keyword(s): | topic identifications | information retrieval | dynamic ranking | |
| Source: | Thirteenth Annual Conference on Natural Language Learning (CoNLL), 2009, Boulder, Colorado, United States | |
| Contributor(s): |
|
|
| Partner: |
UNT College of Engineering
|
|
| Collection: |
UNT Scholarly Works
|
|
| Identifier: |
|
|
| Resource Type: | Paper | |
| Format: | Text | |
| Rights: |
Access:
Public
|
|
