Abstract | ||
---|---|---|
This paper examines the portability of Stanford's multi-pass rule-based sieve coreference resolution system to inflectional language (Polish) with a different annotation scheme. The presented system is implemented in BART, a modular toolkit later adapted to the sieve architecture by Baumann et al. The sieves for Polish include processing of zero subjects and experimental knowledge-intensive sieve using the newly created database of periphrastic expressions. Evaluation shows that the results for Polish are higher than those seen on the CoNLL-2011/2012 data. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-59888-8_20 | Lecture Notes in Artificial Intelligence |
Keywords | Field | DocType |
Coreference resolution,BART,The Stanford's multi-pass sieve architecture,Polish language,Knowledge-based resources | Architecture,Coreference,Annotation,Expression (mathematics),Computer science,Polish,Software portability,Artificial intelligence,Natural language processing,Modular design,Sieve | Conference |
Volume | ISSN | Citations |
10318 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 19 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bartlomiej Niton | 1 | 2 | 1.86 |
Maciej Ogrodniczuk | 2 | 38 | 11.22 |