Abstract | ||
---|---|---|
Developing a full coreference system able to run all the way from raw text to seman- tic interpretation is a considerable engineer- ing effort, yet there is very limited avail- ability of off-the shelf tools for researchers whose interests are not in coreference, or for researchers who want to concentrate on a specific aspect of the problem. We present BART, a highly modular toolkit for de- veloping coreference applications. In the Johns Hopkins workshop on using lexical and encyclopedic knowledge for entity dis- ambiguation, the toolkit was used to ex- tend a reimplementation of the Soon et al. (2001) proposal with a variety of additional syntactic and knowledge-based features, and experiment with alternative resolution pro- cesses, preprocessing tools, and classifiers. |
Year | Venue | Keywords |
---|---|---|
2008 | LREC | full coreference system,knowledge-based feature,encyclopedic knowledge,considerable engineering effort,modular toolkit,alternative resolution process,coreference resolution,johns hopkins workshop,coreference application,entity disambiguation,additional syntactic,knowledge base |
Field | DocType | Volume |
Coreference,Computer science,Semantic interpretation,Preprocessor,Natural language processing,Artificial intelligence,Modular design,Syntax | Conference | P08-4 |
Citations | PageRank | References |
79 | 3.14 | 20 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yannick Versley | 1 | 281 | 19.36 |
Simone Paolo Ponzetto | 2 | 2280 | 129.35 |
Massimo Poesio | 3 | 1869 | 170.68 |
Vladimir Eidelman | 4 | 323 | 17.61 |
Jern, Alan | 5 | 94 | 8.15 |
Jason Smith | 6 | 79 | 3.14 |
Xiaofeng Yang | 7 | 437 | 21.44 |
Alessandro Moschitti | 8 | 3262 | 177.68 |