| C90-3038 | sparse trigram training data using | bigram training | memory . 6 . Conclusion In this |
| P96-1041 | performs poorly except on large | bigram training | sets , where it performs the |
| P96-1042 | inde - pendent . 4.2 Examples in | bigram training | Typically , concept learning |
| C02-1096 | three terms : the unigram and | bigram training | corpus frequency of nominal wordforms |
| H01-1035 | .94 .91 ( e ) Fully supervised | bigram training | ( on goldstandard ) .97 .96 .98 |
