semantic-compressor 2.0__py3-none-any.whl → 2.2__py3-none-any.whl

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 (84) hide show
  1. compressor/resources/nltk_data/tokenizers/punkt_tab/README +98 -0
  2. compressor/resources/nltk_data/tokenizers/punkt_tab/czech/abbrev_types.txt +118 -0
  3. compressor/resources/nltk_data/tokenizers/punkt_tab/czech/collocations.tab +96 -0
  4. compressor/resources/nltk_data/tokenizers/punkt_tab/czech/ortho_context.tab +52789 -0
  5. compressor/resources/nltk_data/tokenizers/punkt_tab/czech/sent_starters.txt +54 -0
  6. compressor/resources/nltk_data/tokenizers/punkt_tab/danish/abbrev_types.txt +211 -0
  7. compressor/resources/nltk_data/tokenizers/punkt_tab/danish/collocations.tab +101 -0
  8. compressor/resources/nltk_data/tokenizers/punkt_tab/danish/ortho_context.tab +53913 -0
  9. compressor/resources/nltk_data/tokenizers/punkt_tab/danish/sent_starters.txt +64 -0
  10. compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/abbrev_types.txt +99 -0
  11. compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/collocations.tab +37 -0
  12. compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/ortho_context.tab +32208 -0
  13. compressor/resources/nltk_data/tokenizers/punkt_tab/dutch/sent_starters.txt +54 -0
  14. compressor/resources/nltk_data/tokenizers/punkt_tab/english/abbrev_types.txt +156 -0
  15. compressor/resources/nltk_data/tokenizers/punkt_tab/english/collocations.tab +37 -0
  16. compressor/resources/nltk_data/tokenizers/punkt_tab/english/ortho_context.tab +20366 -0
  17. compressor/resources/nltk_data/tokenizers/punkt_tab/english/sent_starters.txt +39 -0
  18. compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/abbrev_types.txt +48 -0
  19. compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/collocations.tab +100 -0
  20. compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/ortho_context.tab +68544 -0
  21. compressor/resources/nltk_data/tokenizers/punkt_tab/estonian/sent_starters.txt +89 -0
  22. compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/abbrev_types.txt +81 -0
  23. compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/collocations.tab +167 -0
  24. compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/ortho_context.tab +79765 -0
  25. compressor/resources/nltk_data/tokenizers/punkt_tab/finnish/sent_starters.txt +86 -0
  26. compressor/resources/nltk_data/tokenizers/punkt_tab/french/abbrev_types.txt +61 -0
  27. compressor/resources/nltk_data/tokenizers/punkt_tab/french/collocations.tab +18 -0
  28. compressor/resources/nltk_data/tokenizers/punkt_tab/french/ortho_context.tab +26726 -0
  29. compressor/resources/nltk_data/tokenizers/punkt_tab/french/sent_starters.txt +48 -0
  30. compressor/resources/nltk_data/tokenizers/punkt_tab/german/abbrev_types.txt +71 -0
  31. compressor/resources/nltk_data/tokenizers/punkt_tab/german/collocations.tab +28 -0
  32. compressor/resources/nltk_data/tokenizers/punkt_tab/german/ortho_context.tab +60260 -0
  33. compressor/resources/nltk_data/tokenizers/punkt_tab/german/sent_starters.txt +107 -0
  34. compressor/resources/nltk_data/tokenizers/punkt_tab/greek/abbrev_types.txt +100 -0
  35. compressor/resources/nltk_data/tokenizers/punkt_tab/greek/collocations.tab +7 -0
  36. compressor/resources/nltk_data/tokenizers/punkt_tab/greek/ortho_context.tab +29624 -0
  37. compressor/resources/nltk_data/tokenizers/punkt_tab/greek/sent_starters.txt +54 -0
  38. compressor/resources/nltk_data/tokenizers/punkt_tab/italian/abbrev_types.txt +125 -0
  39. compressor/resources/nltk_data/tokenizers/punkt_tab/italian/collocations.tab +6 -0
  40. compressor/resources/nltk_data/tokenizers/punkt_tab/italian/ortho_context.tab +29929 -0
  41. compressor/resources/nltk_data/tokenizers/punkt_tab/italian/sent_starters.txt +40 -0
  42. compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/abbrev_types.txt +285 -0
  43. compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/collocations.tab +153 -0
  44. compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/ortho_context.tab +10520 -0
  45. compressor/resources/nltk_data/tokenizers/punkt_tab/malayalam/sent_starters.txt +14 -0
  46. compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/abbrev_types.txt +106 -0
  47. compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/collocations.tab +54 -0
  48. compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/ortho_context.tab +54125 -0
  49. compressor/resources/nltk_data/tokenizers/punkt_tab/norwegian/sent_starters.txt +63 -0
  50. compressor/resources/nltk_data/tokenizers/punkt_tab/polish/abbrev_types.txt +225 -0
  51. compressor/resources/nltk_data/tokenizers/punkt_tab/polish/collocations.tab +57 -0
  52. compressor/resources/nltk_data/tokenizers/punkt_tab/polish/ortho_context.tab +81425 -0
  53. compressor/resources/nltk_data/tokenizers/punkt_tab/polish/sent_starters.txt +71 -0
  54. compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/abbrev_types.txt +72 -0
  55. compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/collocations.tab +5 -0
  56. compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/ortho_context.tab +30167 -0
  57. compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/sent_starters.txt +40 -0
  58. compressor/resources/nltk_data/tokenizers/punkt_tab/russian/abbrev_types.txt +1989 -0
  59. compressor/resources/nltk_data/tokenizers/punkt_tab/russian/collocations.tab +0 -0
  60. compressor/resources/nltk_data/tokenizers/punkt_tab/russian/ortho_context.tab +1 -0
  61. compressor/resources/nltk_data/tokenizers/punkt_tab/russian/sent_starters.txt +0 -0
  62. compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/abbrev_types.txt +73 -0
  63. compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/collocations.tab +74 -0
  64. compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/ortho_context.tab +35434 -0
  65. compressor/resources/nltk_data/tokenizers/punkt_tab/slovene/sent_starters.txt +58 -0
  66. compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/abbrev_types.txt +66 -0
  67. compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/collocations.tab +7 -0
  68. compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/ortho_context.tab +27443 -0
  69. compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/sent_starters.txt +46 -0
  70. compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/abbrev_types.txt +39 -0
  71. compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/collocations.tab +8 -0
  72. compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/ortho_context.tab +44485 -0
  73. compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/sent_starters.txt +49 -0
  74. compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/abbrev_types.txt +67 -0
  75. compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/collocations.tab +14 -0
  76. compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/ortho_context.tab +45926 -0
  77. compressor/resources/nltk_data/tokenizers/punkt_tab/turkish/sent_starters.txt +87 -0
  78. compressor/resources/nltk_data/tokenizers/punkt_tab.zip +0 -0
  79. compressor/semantic.py +1 -1
  80. {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/METADATA +1 -1
  81. {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/RECORD +84 -6
  82. {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/LICENSE +0 -0
  83. {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/WHEEL +0 -0
  84. {semantic_compressor-2.0.dist-info → semantic_compressor-2.2.dist-info}/top_level.txt +0 -0
compressor/resources/nltk_data/tokenizers/punkt_tab/spanish/sent_starters.txt ADDED
@@ -0,0 +1,46 @@
1
+ francisco
2
+ la
3
+ el
4
+ mayoral
5
+ tras
6
+ durante
7
+ yo
8
+ ben
9
+ aunque
10
+ foto
11
+ esto
12
+ arbitro
13
+ hoy
14
+ los
15
+ posteriormente
16
+ así
17
+ josé
18
+ por
19
+ no
20
+ _pero
21
+ pero
22
+ arbitros
23
+ estos
24
+ además
25
+ este
26
+ también
27
+ estas
28
+ pese
29
+ si
30
+ ahora
31
+ fuentes
32
+ en
33
+ esta
34
+ recibimos
35
+ igualmente
36
+ incidencias
37
+ asimismo
38
+ sin
39
+ las
40
+ silvema
41
+ juan
42
+ _toros
43
+ según
44
+ pepe
45
+ _novillos
46
+ fax
compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/abbrev_types.txt ADDED
@@ -0,0 +1,39 @@
1
+ f.m
2
+ p.g.a
3
+ t.ex
4
+ ppm
5
+ e.m
6
+ t.o.m
7
+ dir
8
+ m.m
9
+ o.d
10
+ ordf
11
+ p
12
+ prop
13
+ ex
14
+ postst
15
+ jaha
16
+ kap
17
+ m.fl
18
+ landtm.-förb
19
+ f.n
20
+ o.s.v
21
+ osv
22
+ z.b
23
+ mom
24
+ ital
25
+ rskr
26
+ resp
27
+ rif
28
+ f.d
29
+ fig
30
+ s.k
31
+ hrm
32
+ hushålln.-sällsk
33
+ bl.a
34
+ föreläsn.-fören
35
+ dna
36
+ åk
37
+ mm
38
+ bf
39
+ aig
compressor/resources/nltk_data/tokenizers/punkt_tab/swedish/collocations.tab ADDED
@@ -0,0 +1,8 @@
1
+ ##number## uppgifter
2
+ s översättning
3
+ j r
4
+ s ##number##
5
+ ##number## rättens
6
+ ##number## dragen
7
+ r broline
8
+ ##number## civilförsvarspliktiga