Reranking an n-gram supertagger
John Chen, Srinivas Bangalore, Michael J. Collins, Owen Rambow · 2002
As shown by Srinivas (1997), standard n-gram modeling may be used to perform supertag disambiguation with accuracy that is adequate for partial parsing, but in general not sufficient for full parsing. A serious problem is that n-gram modeling usually considers a very small, fixed context and does not perform well with large tag sets, such as those generated by automatic grammar extraction (Xia, 1999; Chen and Vijay-Shanker, 2000; Chiang, 2000).