Abstract | ||
---|---|---|
Research into the automatic acquisition of subcategorization frames (SCFs) from corpora is starting to produce large-scale computational lexicons which include valuable frequency information. However, the accuracy of the resulting lexicons shows room for improvement. One significant source of error lies in the statistical filtering used by some researchers to remove noise from automatically acquired subcategorization frames. In this paper, we compare three different approaches to filtering out spurious hypotheses. Two hypothesis tests perform poorly, compared to filtering frames on the basis of relative frequency. We discuss reasons for this and consider directions for future research. |
Year | DOI | Venue |
---|---|---|
2000 | 10.3115/1117794.1117819 | EMNLP |
Keywords | Field | DocType |
automatic acquisition,significant source,relative frequency,hypothesis test,spurious hypothesis,valuable frequency information,large-scale computational lexicon,different approach,subcategorization frame,subcategorization frame acquisition | Subcategorization,Computer science,Filter (signal processing),Frequency,Speech recognition,Natural language processing,Artificial intelligence,Spurious relationship,Statistical hypothesis testing | Conference |
Volume | Citations | PageRank |
W00-13 | 22 | 1.16 |
References | Authors | |
13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anna Korhonen | 1 | 1336 | 92.50 |
Genevieve Gorrell | 2 | 266 | 22.00 |
Diana McCarthy | 3 | 1020 | 73.34 |