Abstract | ||
---|---|---|
We present an experiment for finding semantically similar words on the ba- sis of a parsed corpus of Dutch text and show that the acquired informa- tion correlates with relations found in Dutch EuroWordNet. Next, we demon- strate how the acquired knowledge can be used to boost the performance of an open-domain question answering sys- tem for Dutch. Automatically acquired lexico-semantic information is used to improve the recall of a method for ex- tracting function relations (such as Wim Kok is the prime minister of the Nether- lands) from corpora, and to improve the precision of our QA system on general WH-questions and definition questions. |
Year | Venue | Keywords |
---|---|---|
2005 | OntoLex@IJCNLP | semantic similarity,question answering |
Field | DocType | Citations |
Semantic similarity,Semantic integration,Question answering,Information retrieval,Computer science,Explicit semantic analysis,Semantic interoperability,Lexico,Natural language processing,Artificial intelligence,EuroWordNet,Semantic computing | Conference | 2 |
PageRank | References | Authors |
0.49 | 10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lonneke Van Der Plas | 1 | 192 | 17.18 |
Gosse Bouma | 2 | 483 | 70.88 |