Abstract
We look into the problem of recognizing citation functions in scientific literature, trying to reveal authors' rationale for citing a particular article. We introduce an annotation scheme to annotate citation functions in scientific papers with coarse-to-fine-grained categories, where the coarse-grained annotation roughly corresponds to citation sentiment and the finegrained annotation reveals more about citation functions. We implement a Maximum Entropy-based system trained on annotated data under this scheme to automatically classify citation functions in scientific literature. Using combined lexical and syntactic features, our system achieves the F-measure of 67%.
| Original language | English (US) |
|---|---|
| Title of host publication | International Conference Recent Advances in Natural Language Processing, RANLP |
| Pages | 402-407 |
| Number of pages | 6 |
| State | Published - 2013 |
| Event | 9th International Conference on Recent Advances in Natural Language Processing, RANLP 2013 - Hissar, Bulgaria Duration: Sep 9 2013 → Sep 11 2013 |
Other
| Other | 9th International Conference on Recent Advances in Natural Language Processing, RANLP 2013 |
|---|---|
| Country/Territory | Bulgaria |
| City | Hissar |
| Period | 9/9/13 → 9/11/13 |
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Software
- Electrical and Electronic Engineering