Berkeley parser初探

對應的目錄

http://code.google.com/p/berkeleyparser/downloads/list

把這些檔案抓下來，放在同一個工作目錄中，以要分析的檔案名叫mumbai.txt為例，鍵入


java -Xms64m -Xmx512m -jar berkeleyParser.jar -gr eng_sm6.gr.gz -inputFile mumbai.txt

它的說明檔範例中沒有參數-Xms64m -Xmx512m，對於使用者來說可能會得到空間不夠的錯誤訊息；其它可用參數如下


-render                       Write rendered tree to image file. (Default: false)
-inputFile                    Read input from this file instead of reading it from STDIN.
-substates                    Output subcategories (only for binarized viterbi trees). (Default: false)
-gr                           Grammarfile (Required) [required]
-binarize                     Output binarized trees. (Default: false)
-likelihood                   Output sentence likelihood, i.e. summing out all parse trees: P(w) (Default: false)
-confidence                   Output confidence measure, i.e. tree likelihood: P(T|w) (Default: false)
-tokenize                     Tokenize input first. (Default: false=text is already tokenized)
-scores                       Output inside scores (only for binarized viterbi trees). (Default: false)
-viterbi                      Compute viterbi derivation instead of max-rule tree (Default: max-rule)
-chinese                      Enable some Chinese specific features in the lexicon.
-accurate                     Set thresholds for accuracy. (Default: set thresholds for efficiency)