excite 2.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. data/.gitignore +11 -0
  2. data/.rspec +1 -0
  3. data/Gemfile +8 -0
  4. data/Gemfile.lock +69 -0
  5. data/LICENSE +22 -0
  6. data/README.md +46 -0
  7. data/Rakefile +24 -0
  8. data/config/citation_cleanup_rules.yml +68 -0
  9. data/config/parscit_features.yml +55 -0
  10. data/excite.gemspec +30 -0
  11. data/lib/excite/array_helpers.rb +27 -0
  12. data/lib/excite/citation.rb +48 -0
  13. data/lib/excite/crfparser.rb +322 -0
  14. data/lib/excite/postprocessor.rb +252 -0
  15. data/lib/excite/preprocessor.rb +107 -0
  16. data/lib/excite/resources/dicts/female-names +4954 -0
  17. data/lib/excite/resources/dicts/first-names +27926 -0
  18. data/lib/excite/resources/dicts/male-names +3901 -0
  19. data/lib/excite/resources/dicts/months +24 -0
  20. data/lib/excite/resources/dicts/places +43109 -0
  21. data/lib/excite/resources/dicts/publishers +654 -0
  22. data/lib/excite/resources/dicts/surnames +146259 -0
  23. data/lib/excite/resources/html.template +84 -0
  24. data/lib/excite/resources/html_model +0 -0
  25. data/lib/excite/resources/model +0 -0
  26. data/lib/excite/resources/parsCit.template +76 -0
  27. data/lib/excite/resources/trainingdata/tagged_html_references.txt +500 -0
  28. data/lib/excite/resources/trainingdata/tagged_references.txt +500 -0
  29. data/lib/excite/resources/trainingdata/verify.rb +97 -0
  30. data/lib/excite/token_features.rb +313 -0
  31. data/lib/excite/version.rb +7 -0
  32. data/lib/excite.rb +13 -0
  33. data/model/test/analysis.csv +54 -0
  34. data/model/test/array_helpers.rb +30 -0
  35. data/model/test/html-analysis.csv +60 -0
  36. data/model/test/html-output.txt +19893 -0
  37. data/model/test/model_test.rb +306 -0
  38. data/model/test/output.txt +16742 -0
  39. data/spec/excite/citation_spec.rb +128 -0
  40. data/spec/excite/crfparser_spec.rb +118 -0
  41. data/spec/excite/postprocessor_spec.rb +68 -0
  42. data/spec/excite/token_features_spec.rb +641 -0
  43. data/spec/spec_helper.rb +4 -0
  44. metadata +222 -0
data/lib/excite/resources/html.template ADDED
@@ -0,0 +1,84 @@
1
+ # See config/parscit_features.yml for function-to-number correlation
2
+
3
+ b# Unigram
4
+ U00:%x[-3,0]
5
+ U01:%x[-2,0]
6
+ U02:%x[-1,0]
7
+ U03:%x[0,0]
8
+ U04:%x[1,0]
9
+ U05:%x[2,0]
10
+ U06:%x[3,0]
11
+ U07:%x[-1,0]/%x[0,0]
12
+ U08:%x[0,0]/%x[1,0]
13
+
14
+ # last Char
15
+ U10:%x[0,1]
16
+ U11:%x[-1,1]
17
+
18
+ # first 1-4
19
+ U20:%x[0,2]
20
+ U21:%x[0,3]
21
+ U22:%x[0,4]
22
+ U23:%x[0,5]
23
+
24
+ # last 1-4
25
+ U30:%x[0,6]
26
+ U31:%x[0,7]
27
+ U32:%x[0,8]
28
+ U33:%x[0,9]
29
+
30
+ # Lowercased, no punct
31
+ U40:%x[-2,10]
32
+ U41:%x[-1,10]
33
+ U42:%x[0,10]
34
+ U43:%x[1,10]
35
+ U44:%x[2,10]
36
+
37
+ # Capitalization
38
+ U50:%x[0,11]
39
+
40
+ # Numbers
41
+ U60:%x[-1,12]
42
+ U61:%x[0,12]
43
+ U62:%x[1,12]
44
+ U63:%x[-1,12]/%x[0,12]
45
+ U63:%x[0,12]/%x[1,12]
46
+
47
+ # Dict info
48
+ U70:%x[0,13]
49
+ U71:%x[0,14]
50
+ U72:%x[0,15]
51
+ U73:%x[0,16]
52
+ U74:%x[0,17]
53
+ U75:%x[0,18]
54
+
55
+ # Possible editor?
56
+ U80:%x[0,19]
57
+
58
+ # Position
59
+ U90:%x[0,20]
60
+
61
+ # Punctuation
62
+ UA0:%x[0,21]
63
+
64
+ # possible chapter?
65
+ U90:%x[-1,25]/%x[0,22]/%x[0,19]
66
+ U91:%x[-1,25]/%x[0,22]/%x[1,11]
67
+
68
+ # html tag
69
+ UH2:%x[0,23]
70
+ UH3:%x[1,23]
71
+ UH4:%x[-1,23]
72
+ UH5:%x[-1,23]/%x[0,23]
73
+ UH6:%x[0,23]/%x[1,23]
74
+ UH7:%x[0,24]
75
+
76
+ # part of speech
77
+ UP0:%x[0,25]
78
+ UP1:%x[-1,25]
79
+ UP2:%x[1,25]
80
+ UP3:%x[-1,25]/%x[0,25]
81
+ UP4:%x[0,25]/%x[1,25]
82
+
83
+ # Bigram
84
+ B
data/lib/excite/resources/html_model ADDED
Binary file
data/lib/excite/resources/model ADDED
Binary file
data/lib/excite/resources/parsCit.template ADDED
@@ -0,0 +1,76 @@
1
+ # See config/parscit_features.yml for function-to-number correlation
2
+
3
+ # Unigram
4
+ U00:%x[-3,0]
5
+ U01:%x[-2,0]
6
+ U02:%x[-1,0]
7
+ U03:%x[0,0]
8
+ U04:%x[1,0]
9
+ U05:%x[2,0]
10
+ U06:%x[3,0]
11
+ U07:%x[-1,0]/%x[0,0]
12
+ U08:%x[0,0]/%x[1,0]
13
+
14
+ # last Char
15
+ U10:%x[0,1]
16
+ U11:%x[-1,1]
17
+
18
+ # first 1-4
19
+ U20:%x[0,2]
20
+ U21:%x[0,3]
21
+ U22:%x[0,4]
22
+ U23:%x[0,5]
23
+
24
+ # last 1-4
25
+ U30:%x[0,6]
26
+ U31:%x[0,7]
27
+ U32:%x[0,8]
28
+ U33:%x[0,9]
29
+
30
+ # Lowercased, no punct
31
+ U40:%x[-2,10]
32
+ U41:%x[-1,10]
33
+ U42:%x[0,10]
34
+ U43:%x[1,10]
35
+ U44:%x[2,10]
36
+
37
+ # Capitalization
38
+ U50:%x[0,11]
39
+
40
+ # Numbers
41
+ U60:%x[-1,12]
42
+ U61:%x[0,12]
43
+ U62:%x[1,12]
44
+ U63:%x[-1,12]/%x[0,12]
45
+ U63:%x[0,12]/%x[1,12]
46
+
47
+ # Dict info
48
+ U70:%x[0,13]
49
+ U71:%x[0,14]
50
+ U72:%x[0,15]
51
+ U73:%x[0,16]
52
+ U74:%x[0,17]
53
+ U75:%x[0,18]
54
+
55
+ # Possible editor?
56
+ U80:%x[0,19]
57
+
58
+ # Position
59
+ U90:%x[0,20]
60
+
61
+ # Punctuation
62
+ UA0:%x[0,21]
63
+
64
+ # possible chapter?
65
+ U90:%x[-1,23]/%x[0,22]/%x[0,19]
66
+ U91:%x[-1,23]/%x[0,22]/%x[1,11]
67
+
68
+ # part of speech
69
+ UP0:%x[0,23]
70
+ UP1:%x[-1,23]
71
+ UP2:%x[1,23]
72
+ UP3:%x[-1,23]/%x[0,23]
73
+ UP4:%x[0,23]/%x[1,23]
74
+
75
+ # Bigram
76
+ B