Uses 6125K of libraries. Click here for Pure Java version (438L/4K/13K).
1 | !7 |
2 | |
3 | lib 1008485 // stanford parser |
4 | lib 1008486 // english model |
5 | |
6 | import edu.stanford.nlp.ling.CoreLabel; |
7 | import edu.stanford.nlp.process.TokenizerFactory; |
8 | import edu.stanford.nlp.parser.lexparser.LexicalizedParser; |
9 | import edu.stanford.nlp.process.CoreLabelTokenFactory; |
10 | import edu.stanford.nlp.process.PTBTokenizer; |
11 | import edu.stanford.nlp.process.Tokenizer; |
12 | import edu.stanford.nlp.trees.Tree; |
13 | |
14 | sS PCG_MODEL = "edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz"; |
15 | static TokenizerFactory<CoreLabel> tokenizerFactory; |
16 | static LexicalizedParser parser; |
17 | |
18 | static Tree parse(S str) { |
19 | List<CoreLabel> tokens = tokenize(str); |
20 | ret parser.apply(tokens); |
21 | } |
22 | |
23 | static L<CoreLabel> tokenize(String str) { |
24 | Tokenizer<CoreLabel> tokenizer = tokenizerFactory.getTokenizer( |
25 | new StringReader(str)); |
26 | ret tokenizer.tokenize(); |
27 | } |
28 | |
29 | p { |
30 | tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "invertible=true"); |
31 | parser = LexicalizedParser.loadModel(PCG_MODEL); |
32 | S str = "My dog also likes eating sausage."; |
33 | Tree tree = parse(str); |
34 | |
35 | L<Tree> leaves = tree.getLeaves(); |
36 | // Print words and Pos Tags |
37 | for (Tree leaf : leaves) { |
38 | Tree parent = leaf.parent(tree); |
39 | print(" " + leaf.label().value() + " [" + parent.label().value() + "]"); |
40 | } |
41 | print(); |
42 | printTree(tree); |
43 | } |
44 | |
45 | svoid printTree(Tree tree) { |
46 | printTree("", tree); |
47 | } |
48 | |
49 | svoid printTree(S indent, Tree tree) { |
50 | //if (l(indent) > 4) ret; |
51 | print(indent + tree.label().value()); |
52 | for (Tree child : tree.getChildrenAsList()) |
53 | printTree(indent + " ", child); |
54 | } |
download show line numbers debug dex old transpilations
Travelled to 13 computer(s): aoiabmzegqzx, bhatertpkbcr, cbybwowwnfue, cfunsshuasjs, gwrvuhgaqvyk, ishqpsrjomds, lpdgvwnxivlt, mqqgnosmbjvj, pyentgdyhuwx, pzhvpgtvlbxg, tslmcundralx, tvejysmllsmz, vouqrxazstgt
No comments. add comment
Snippet ID: | #1008487 |
Snippet name: | Stanford Parser Test [WORKS] |
Eternal ID of this version: | #1008487/7 |
Text MD5: | 165c55ac305a3dfc53f2ee1a476f5fa3 |
Transpilation MD5: | 260168e69f45a65543a4225fdc150f6d |
Author: | stefan |
Category: | javax / a.i. parsing |
Type: | JavaX source code |
Public (visible to everyone): | Yes |
Archived (hidden from active list): | No |
Created/modified: | 2017-05-17 17:30:56 |
Source code size: | 1589 bytes / 54 lines |
Pitched / IR pitched: | No / No |
Views / Downloads: | 389 / 1301 |
Version history: | 6 change(s) |
Referenced in: | [show references] |