semantic-compressor 2.1__py3-none-any.whl → 2.3__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 +37 -3
  80. {semantic_compressor-2.1.dist-info → semantic_compressor-2.3.dist-info}/METADATA +1 -1
  81. {semantic_compressor-2.1.dist-info → semantic_compressor-2.3.dist-info}/RECORD +84 -6
  82. {semantic_compressor-2.1.dist-info → semantic_compressor-2.3.dist-info}/LICENSE +0 -0
  83. {semantic_compressor-2.1.dist-info → semantic_compressor-2.3.dist-info}/WHEEL +0 -0
  84. {semantic_compressor-2.1.dist-info → semantic_compressor-2.3.dist-info}/top_level.txt +0 -0
compressor/resources/nltk_data/tokenizers/punkt_tab/polish/sent_starters.txt ADDED
@@ -0,0 +1,71 @@
1
+ okazało
2
+ podobno
3
+ natomiast
4
+ niestety
5
+ mimo
6
+ policja
7
+ chłopiec
8
+ najwięcej
9
+ gdy
10
+ nikt
11
+ policjanci
12
+ według
13
+ obecnie
14
+ wczoraj
15
+ włodek
16
+ zanim
17
+ ponieważ
18
+ po
19
+ gdyby
20
+ dlatego
21
+ starzec
22
+ prezes
23
+ dopiero
24
+ podobnie
25
+ kobieta
26
+ otóż
27
+ potem
28
+ przypomnijmy
29
+ teraz
30
+ anka
31
+ no
32
+ jak
33
+ następnie
34
+ ponadto
35
+ wystarczy
36
+ wśród
37
+ każdy
38
+ zdaniem
39
+ cosmo
40
+ trudno
41
+ dodajmy
42
+ kościół
43
+ jeżeli
44
+ monika
45
+ pozdrawiam
46
+ kiedy
47
+ druga
48
+ ale
49
+ oprócz
50
+ poza
51
+ helenka
52
+ nie
53
+ dziś
54
+ podczas
55
+ wtedy
56
+ a
57
+ tymczasem
58
+ tranzyt
59
+ ja
60
+ zresztą
61
+ oto
62
+ oczywiście
63
+ dlaczego
64
+ dzięki
65
+ najpierw
66
+ myślę
67
+ poprawka
68
+ w
69
+ czy
70
+ jeśli
71
+ obie
compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/abbrev_types.txt ADDED
@@ -0,0 +1,72 @@
1
+ mpb
2
+ a.c
3
+ s.p
4
+ pen
5
+ itr
6
+ fund
7
+ 1.6r
8
+ ltda
9
+ dr
10
+ r
11
+ ed
12
+ f.c
13
+ jor
14
+ m.c.a
15
+ prof
16
+ uó
17
+ jr
18
+ a.s.s.j
19
+ p
20
+ op
21
+ v.excia
22
+ q1
23
+ g.r.e.s
24
+ a.a
25
+ g
26
+ fbf
27
+ tel
28
+ a.l.f
29
+ av
30
+ bms
31
+ cnt
32
+ 13º
33
+ 11s
34
+ qsp
35
+ fut
36
+ cf
37
+ 16o
38
+ sra
39
+ s.a
40
+ j.j
41
+ j.b
42
+ sós
43
+ hui
44
+ cip
45
+ s
46
+ nl
47
+ inc
48
+ vs
49
+ pág
50
+ mr
51
+ job
52
+ o.j
53
+ 1o
54
+ j.c
55
+ zoe
56
+ págs
57
+ h
58
+ sr
59
+ v.b
60
+ mens
61
+ a.p.s
62
+ r.e.m
63
+ s.p.r
64
+ mrs
65
+ alt
66
+ p.j
67
+ t.j
68
+ s.o.s
69
+ ap
70
+ 14º
71
+ a.c.j
72
+ ipm
compressor/resources/nltk_data/tokenizers/punkt_tab/portuguese/collocations.tab ADDED
@@ -0,0 +1,5 @@
1
+ t jones
2
+ ##number## loção
3
+ b justo
4
+ d luciano
5
+ ##number## nov.1902