Abstract | ||
---|---|---|
We investigate a series of targeted modifications to a data-driven dependency parser of German and show that these can be highly effective even for a relatively well studied language like German if they are made on a (linguistically and methodologically) informed basis and with a parser implementation that allows for fast and robust training and application. Making relatively small changes to a range of very different system components, we were able to increase labeled accuracy on a standard test set (from the CoNLL 2009 shared task), ignoring gold standard part-of-speech tags, from 87.64% to 89.40%. The study was conducted in less than five weeks and as a secondary project of all four authors. Effective modifications include the quality and combination of auto-assigned morphosyntactic features entering machine learning, the internal feature handling as well as the inclusion of global constraints and a combination of different parsing strategies. |
Year | Venue | Keywords |
---|---|---|
2010 | COLING (Posters) | standard test set,global constraint,auto-assigned morphosyntactic,effective modification,informed way,gold standard part-of-speech tag,data-driven dependency parser,different parsing strategy,different system component,parser implementation,informed basis,dependency parsing |
Field | DocType | Volume |
Data-driven,Computer science,Dependency grammar,Bottom-up parsing,Natural language processing,Artificial intelligence,Parsing,Test set,German | Conference | C10-2 |
Citations | PageRank | References |
6 | 0.60 | 23 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
wolfgang seeker | 1 | 121 | 10.56 |
Bernd Bohnet | 2 | 524 | 38.19 |
Lilja Øvrelid | 3 | 187 | 27.28 |
Jonas Kuhn | 4 | 115 | 13.05 |