excite 2.1.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +11 -0
- data/.rspec +1 -0
- data/Gemfile +8 -0
- data/Gemfile.lock +69 -0
- data/LICENSE +22 -0
- data/README.md +46 -0
- data/Rakefile +24 -0
- data/config/citation_cleanup_rules.yml +68 -0
- data/config/parscit_features.yml +55 -0
- data/excite.gemspec +30 -0
- data/lib/excite/array_helpers.rb +27 -0
- data/lib/excite/citation.rb +48 -0
- data/lib/excite/crfparser.rb +322 -0
- data/lib/excite/postprocessor.rb +252 -0
- data/lib/excite/preprocessor.rb +107 -0
- data/lib/excite/resources/dicts/female-names +4954 -0
- data/lib/excite/resources/dicts/first-names +27926 -0
- data/lib/excite/resources/dicts/male-names +3901 -0
- data/lib/excite/resources/dicts/months +24 -0
- data/lib/excite/resources/dicts/places +43109 -0
- data/lib/excite/resources/dicts/publishers +654 -0
- data/lib/excite/resources/dicts/surnames +146259 -0
- data/lib/excite/resources/html.template +84 -0
- data/lib/excite/resources/html_model +0 -0
- data/lib/excite/resources/model +0 -0
- data/lib/excite/resources/parsCit.template +76 -0
- data/lib/excite/resources/trainingdata/tagged_html_references.txt +500 -0
- data/lib/excite/resources/trainingdata/tagged_references.txt +500 -0
- data/lib/excite/resources/trainingdata/verify.rb +97 -0
- data/lib/excite/token_features.rb +313 -0
- data/lib/excite/version.rb +7 -0
- data/lib/excite.rb +13 -0
- data/model/test/analysis.csv +54 -0
- data/model/test/array_helpers.rb +30 -0
- data/model/test/html-analysis.csv +60 -0
- data/model/test/html-output.txt +19893 -0
- data/model/test/model_test.rb +306 -0
- data/model/test/output.txt +16742 -0
- data/spec/excite/citation_spec.rb +128 -0
- data/spec/excite/crfparser_spec.rb +118 -0
- data/spec/excite/postprocessor_spec.rb +68 -0
- data/spec/excite/token_features_spec.rb +641 -0
- data/spec/spec_helper.rb +4 -0
- metadata +222 -0
@@ -0,0 +1,654 @@
|
|
1
|
+
addison
|
2
|
+
alexander
|
3
|
+
alfred
|
4
|
+
allan
|
5
|
+
allen
|
6
|
+
allyn
|
7
|
+
andre
|
8
|
+
angus
|
9
|
+
berkley
|
10
|
+
blake
|
11
|
+
boyd
|
12
|
+
brooks
|
13
|
+
carroll
|
14
|
+
charles
|
15
|
+
chick
|
16
|
+
clark
|
17
|
+
cole
|
18
|
+
court
|
19
|
+
del
|
20
|
+
delmar
|
21
|
+
dick
|
22
|
+
faber
|
23
|
+
fitzgerald
|
24
|
+
francis
|
25
|
+
franklin
|
26
|
+
fraser
|
27
|
+
george
|
28
|
+
gordon
|
29
|
+
gregg
|
30
|
+
grove
|
31
|
+
hale
|
32
|
+
hall
|
33
|
+
hamilton
|
34
|
+
hamish
|
35
|
+
harcourt
|
36
|
+
harry
|
37
|
+
hill
|
38
|
+
holt
|
39
|
+
ian
|
40
|
+
ivan
|
41
|
+
james
|
42
|
+
john
|
43
|
+
joseph
|
44
|
+
kelly
|
45
|
+
lane
|
46
|
+
law
|
47
|
+
lion
|
48
|
+
lock
|
49
|
+
marcel
|
50
|
+
marion
|
51
|
+
marshall
|
52
|
+
matthias
|
53
|
+
mead
|
54
|
+
merrill
|
55
|
+
michael
|
56
|
+
miles
|
57
|
+
morgan
|
58
|
+
murray
|
59
|
+
nelson
|
60
|
+
north
|
61
|
+
orion
|
62
|
+
owen
|
63
|
+
pascal
|
64
|
+
patrick
|
65
|
+
paul
|
66
|
+
peter
|
67
|
+
prentice
|
68
|
+
putnam
|
69
|
+
ray
|
70
|
+
reed
|
71
|
+
robert
|
72
|
+
saunders
|
73
|
+
simon
|
74
|
+
smith
|
75
|
+
stanford
|
76
|
+
taylor
|
77
|
+
thomas
|
78
|
+
victor
|
79
|
+
wadsworth
|
80
|
+
walker
|
81
|
+
ward
|
82
|
+
warner
|
83
|
+
wesley
|
84
|
+
west
|
85
|
+
wiley
|
86
|
+
winston
|
87
|
+
xavier
|
88
|
+
yale
|
89
|
+
ardis
|
90
|
+
concordia
|
91
|
+
dee
|
92
|
+
garland
|
93
|
+
jada
|
94
|
+
lucie
|
95
|
+
minerva
|
96
|
+
sophia
|
97
|
+
star
|
98
|
+
williams
|
99
|
+
brown
|
100
|
+
lewis
|
101
|
+
baker
|
102
|
+
collins
|
103
|
+
barnes
|
104
|
+
long
|
105
|
+
black
|
106
|
+
mills
|
107
|
+
stone
|
108
|
+
hudson
|
109
|
+
stephens
|
110
|
+
andrews
|
111
|
+
chapman
|
112
|
+
little
|
113
|
+
pearson
|
114
|
+
holland
|
115
|
+
hopkins
|
116
|
+
watts
|
117
|
+
haynes
|
118
|
+
bass
|
119
|
+
wilkins
|
120
|
+
collier
|
121
|
+
hutchinson
|
122
|
+
blackwell
|
123
|
+
johns
|
124
|
+
golden
|
125
|
+
english
|
126
|
+
house
|
127
|
+
petty
|
128
|
+
good
|
129
|
+
workman
|
130
|
+
andersen
|
131
|
+
dodd
|
132
|
+
springer
|
133
|
+
blue
|
134
|
+
tuttle
|
135
|
+
dunham
|
136
|
+
abrams
|
137
|
+
mcgraw
|
138
|
+
thomson
|
139
|
+
street
|
140
|
+
crowell
|
141
|
+
hackett
|
142
|
+
london
|
143
|
+
dutton
|
144
|
+
boston
|
145
|
+
sams
|
146
|
+
schuster
|
147
|
+
duckworth
|
148
|
+
brunner
|
149
|
+
pickering
|
150
|
+
rinehart
|
151
|
+
graf
|
152
|
+
kraus
|
153
|
+
south
|
154
|
+
churchill
|
155
|
+
box
|
156
|
+
falcon
|
157
|
+
new
|
158
|
+
houghton
|
159
|
+
cave
|
160
|
+
canada
|
161
|
+
council
|
162
|
+
dover
|
163
|
+
mosby
|
164
|
+
manson
|
165
|
+
sparrow
|
166
|
+
peace
|
167
|
+
harwood
|
168
|
+
spring
|
169
|
+
robson
|
170
|
+
brill
|
171
|
+
apple
|
172
|
+
scribner
|
173
|
+
pitman
|
174
|
+
cassell
|
175
|
+
book
|
176
|
+
macmillan
|
177
|
+
deutsch
|
178
|
+
bridge
|
179
|
+
wales
|
180
|
+
oxford
|
181
|
+
wisdom
|
182
|
+
calder
|
183
|
+
dryden
|
184
|
+
copper
|
185
|
+
mcclurg
|
186
|
+
kaufmann
|
187
|
+
rager
|
188
|
+
reader
|
189
|
+
manchester
|
190
|
+
wine
|
191
|
+
to
|
192
|
+
kessinger
|
193
|
+
creek
|
194
|
+
telford
|
195
|
+
phoenix
|
196
|
+
sohn
|
197
|
+
belknap
|
198
|
+
grafton
|
199
|
+
spoon
|
200
|
+
heinemann
|
201
|
+
pan
|
202
|
+
sons
|
203
|
+
press
|
204
|
+
touchstone
|
205
|
+
dublin
|
206
|
+
orchard
|
207
|
+
capo
|
208
|
+
cambridge
|
209
|
+
auerbach
|
210
|
+
knopf
|
211
|
+
dekker
|
212
|
+
virgin
|
213
|
+
livingstone
|
214
|
+
atlas
|
215
|
+
daw
|
216
|
+
harvill
|
217
|
+
river
|
218
|
+
maclennan
|
219
|
+
books
|
220
|
+
mifflin
|
221
|
+
newbury
|
222
|
+
an
|
223
|
+
harvard
|
224
|
+
stackpole
|
225
|
+
harbor
|
226
|
+
hodder
|
227
|
+
doubleday
|
228
|
+
columbia
|
229
|
+
ballantine
|
230
|
+
student
|
231
|
+
world
|
232
|
+
imperial
|
233
|
+
vent
|
234
|
+
quay
|
235
|
+
hogarth
|
236
|
+
routledge
|
237
|
+
melbourne
|
238
|
+
arts
|
239
|
+
dorset
|
240
|
+
wordsworth
|
241
|
+
sovereign
|
242
|
+
heinle
|
243
|
+
cavendish
|
244
|
+
brookings
|
245
|
+
rover
|
246
|
+
glas
|
247
|
+
america
|
248
|
+
ace
|
249
|
+
thornes
|
250
|
+
russian
|
251
|
+
end
|
252
|
+
emerald
|
253
|
+
quiet
|
254
|
+
lights
|
255
|
+
city
|
256
|
+
breach
|
257
|
+
times
|
258
|
+
sadan
|
259
|
+
mcmeel
|
260
|
+
longman
|
261
|
+
harvest
|
262
|
+
college
|
263
|
+
va
|
264
|
+
godine
|
265
|
+
bison
|
266
|
+
plume
|
267
|
+
media
|
268
|
+
course
|
269
|
+
uk
|
270
|
+
tulip
|
271
|
+
oak
|
272
|
+
left
|
273
|
+
zephyr
|
274
|
+
war
|
275
|
+
verso
|
276
|
+
station
|
277
|
+
mini
|
278
|
+
duxbury
|
279
|
+
american
|
280
|
+
da
|
281
|
+
que
|
282
|
+
california
|
283
|
+
australia
|
284
|
+
michigan
|
285
|
+
chicago
|
286
|
+
central
|
287
|
+
indiana
|
288
|
+
toronto
|
289
|
+
minnesota
|
290
|
+
kentucky
|
291
|
+
iowa
|
292
|
+
nebraska
|
293
|
+
alaska
|
294
|
+
epworth
|
295
|
+
arcadia
|
296
|
+
usa
|
297
|
+
methuen
|
298
|
+
university
|
299
|
+
of
|
300
|
+
athlone
|
301
|
+
canyon
|
302
|
+
princeton
|
303
|
+
progress
|
304
|
+
prospect
|
305
|
+
lutterworth
|
306
|
+
egg
|
307
|
+
cloverdale
|
308
|
+
atlantic
|
309
|
+
triangle
|
310
|
+
kindersley
|
311
|
+
a
|
312
|
+
abode
|
313
|
+
academic
|
314
|
+
architectural
|
315
|
+
association
|
316
|
+
autodesk
|
317
|
+
b
|
318
|
+
bacan
|
319
|
+
bertelsmannspringer
|
320
|
+
birkhaeuser
|
321
|
+
business
|
322
|
+
cold
|
323
|
+
company
|
324
|
+
copernicus
|
325
|
+
corporation
|
326
|
+
crc
|
327
|
+
e
|
328
|
+
economics
|
329
|
+
editions
|
330
|
+
education
|
331
|
+
educational
|
332
|
+
ersnt
|
333
|
+
europa
|
334
|
+
f
|
335
|
+
fence
|
336
|
+
for
|
337
|
+
futura
|
338
|
+
g
|
339
|
+
gmbh
|
340
|
+
group
|
341
|
+
humana
|
342
|
+
ieee
|
343
|
+
inc
|
344
|
+
ingress
|
345
|
+
institute
|
346
|
+
international
|
347
|
+
itp
|
348
|
+
jossey
|
349
|
+
kluwer
|
350
|
+
laboratory
|
351
|
+
learning
|
352
|
+
ltd
|
353
|
+
mathematical
|
354
|
+
medical
|
355
|
+
microbiology
|
356
|
+
milady
|
357
|
+
n
|
358
|
+
narosa
|
359
|
+
neurological
|
360
|
+
onword
|
361
|
+
oultedge
|
362
|
+
peachpit
|
363
|
+
penguin
|
364
|
+
physica
|
365
|
+
physics
|
366
|
+
plenum
|
367
|
+
professional
|
368
|
+
psychological
|
369
|
+
psychology
|
370
|
+
ptr
|
371
|
+
pty
|
372
|
+
publications
|
373
|
+
publishers
|
374
|
+
publishing
|
375
|
+
pvt
|
376
|
+
riders
|
377
|
+
routledgeflamer
|
378
|
+
s
|
379
|
+
science
|
380
|
+
singular
|
381
|
+
society
|
382
|
+
software
|
383
|
+
southwestern
|
384
|
+
spon
|
385
|
+
st
|
386
|
+
steinkopff
|
387
|
+
surgeons
|
388
|
+
technip
|
389
|
+
technology
|
390
|
+
the
|
391
|
+
verlag
|
392
|
+
vnr
|
393
|
+
w
|
394
|
+
wileyheyden
|
395
|
+
wileyliss
|
396
|
+
wileylnterscience
|
397
|
+
wileyvch
|
398
|
+
wissenschafts
|
399
|
+
abacus
|
400
|
+
ac
|
401
|
+
addison-wesley
|
402
|
+
ak
|
403
|
+
akashic
|
404
|
+
aladdin
|
405
|
+
allenunwin
|
406
|
+
and
|
407
|
+
anvil
|
408
|
+
arcade
|
409
|
+
archive
|
410
|
+
arkham
|
411
|
+
artscroll
|
412
|
+
associated
|
413
|
+
at
|
414
|
+
atheneum
|
415
|
+
atom
|
416
|
+
avari
|
417
|
+
baen
|
418
|
+
bantam
|
419
|
+
barriejenkins
|
420
|
+
basic
|
421
|
+
bbc
|
422
|
+
birkhauser
|
423
|
+
blackstaff
|
424
|
+
blackwell's
|
425
|
+
bloodaxe
|
426
|
+
blooming
|
427
|
+
bloomsbury
|
428
|
+
bobbs-merrill
|
429
|
+
booksforabuckcom
|
430
|
+
bookshops
|
431
|
+
borzoi
|
432
|
+
boyars
|
433
|
+
boydellbrewer
|
434
|
+
boyds
|
435
|
+
bswk
|
436
|
+
butterworth-heinemann
|
437
|
+
bw
|
438
|
+
c
|
439
|
+
canongate
|
440
|
+
carcanet
|
441
|
+
carrer
|
442
|
+
catalog
|
443
|
+
catbird
|
444
|
+
century
|
445
|
+
change
|
446
|
+
chicken
|
447
|
+
classics
|
448
|
+
club
|
449
|
+
cockerel
|
450
|
+
communications
|
451
|
+
companionguidescom
|
452
|
+
continuum
|
453
|
+
coronet
|
454
|
+
counterpoint
|
455
|
+
creation
|
456
|
+
crockerbrewster
|
457
|
+
daedalus
|
458
|
+
dalkey
|
459
|
+
deagostini
|
460
|
+
dedalus
|
461
|
+
delacorte
|
462
|
+
denbridge
|
463
|
+
desk
|
464
|
+
detrituscom
|
465
|
+
directions
|
466
|
+
directmedia
|
467
|
+
dorling
|
468
|
+
eburon
|
469
|
+
ecw
|
470
|
+
eerdmans
|
471
|
+
ellora's
|
472
|
+
elsevier
|
473
|
+
enterprises
|
474
|
+
equity
|
475
|
+
european
|
476
|
+
everyman's
|
477
|
+
exact
|
478
|
+
eyrespottiswoode
|
479
|
+
gk
|
480
|
+
gollancz
|
481
|
+
goose
|
482
|
+
greenery
|
483
|
+
hallcompany
|
484
|
+
harlequin
|
485
|
+
harperbrothers
|
486
|
+
harpercollins
|
487
|
+
harperprism
|
488
|
+
harperrow
|
489
|
+
harpertrophy
|
490
|
+
hbj
|
491
|
+
headline
|
492
|
+
helter
|
493
|
+
hesperus
|
494
|
+
hms
|
495
|
+
hmso
|
496
|
+
hodderstoughton
|
497
|
+
hotei
|
498
|
+
hyperion
|
499
|
+
idc
|
500
|
+
imprint
|
501
|
+
information
|
502
|
+
inpress
|
503
|
+
inscape
|
504
|
+
insomniac
|
505
|
+
institution
|
506
|
+
interlink
|
507
|
+
inter-varsity
|
508
|
+
intervarsity
|
509
|
+
ivyspring
|
510
|
+
jarrolds
|
511
|
+
kegan
|
512
|
+
kehot
|
513
|
+
kodansha
|
514
|
+
kregel
|
515
|
+
ladybird
|
516
|
+
legend
|
517
|
+
library
|
518
|
+
limited
|
519
|
+
llc
|
520
|
+
lobster
|
521
|
+
lockco
|
522
|
+
mainstream
|
523
|
+
mandrake
|
524
|
+
manuals
|
525
|
+
martin's
|
526
|
+
martinus
|
527
|
+
masquerade
|
528
|
+
mcfarlandcompany
|
529
|
+
medknow
|
530
|
+
miegunyah
|
531
|
+
millsboon
|
532
|
+
mit
|
533
|
+
mjs
|
534
|
+
mocho
|
535
|
+
modern
|
536
|
+
monthly
|
537
|
+
monument
|
538
|
+
museum
|
539
|
+
mycroftmoran
|
540
|
+
nauka
|
541
|
+
newnes
|
542
|
+
nijhoff
|
543
|
+
nonesuch
|
544
|
+
noontide
|
545
|
+
northpoint
|
546
|
+
northwestern
|
547
|
+
nortoncompany
|
548
|
+
nyrb
|
549
|
+
office
|
550
|
+
online
|
551
|
+
open
|
552
|
+
o'reilly
|
553
|
+
overlook
|
554
|
+
oxfam
|
555
|
+
p
|
556
|
+
palgrave
|
557
|
+
pantheon
|
558
|
+
paperbacks
|
559
|
+
parallax
|
560
|
+
pathfinder
|
561
|
+
paulist
|
562
|
+
pavilion
|
563
|
+
perennis
|
564
|
+
pergamon
|
565
|
+
phaidon
|
566
|
+
philtrum
|
567
|
+
picador
|
568
|
+
piccadilly
|
569
|
+
pimlico
|
570
|
+
plc
|
571
|
+
poetry
|
572
|
+
poseidon
|
573
|
+
presses
|
574
|
+
prometheus
|
575
|
+
publication
|
576
|
+
publisher
|
577
|
+
puffin
|
578
|
+
pulpnet
|
579
|
+
putnam's
|
580
|
+
quartet
|
581
|
+
quebecor
|
582
|
+
r
|
583
|
+
random
|
584
|
+
recorded
|
585
|
+
reference
|
586
|
+
rmit
|
587
|
+
rockcompany
|
588
|
+
routledgesons
|
589
|
+
rubicon
|
590
|
+
scarecrow
|
591
|
+
schocken
|
592
|
+
schofieldsims
|
593
|
+
scholars
|
594
|
+
scholastic
|
595
|
+
scientific
|
596
|
+
scm
|
597
|
+
scribner's
|
598
|
+
seckerwarburg
|
599
|
+
sensorotika
|
600
|
+
shambhala
|
601
|
+
shanti
|
602
|
+
shoemakerhoard
|
603
|
+
sidgwickjackson
|
604
|
+
signet
|
605
|
+
skelter
|
606
|
+
snake
|
607
|
+
spacepol
|
608
|
+
spck
|
609
|
+
spectra
|
610
|
+
spottiswoode
|
611
|
+
stantonlee
|
612
|
+
stationery
|
613
|
+
steerforth
|
614
|
+
stovepipe
|
615
|
+
sunmoon
|
616
|
+
suny
|
617
|
+
tachyon
|
618
|
+
tantivy
|
619
|
+
target
|
620
|
+
tartarus
|
621
|
+
taschen
|
622
|
+
taylorfrancis
|
623
|
+
tenspeed
|
624
|
+
thameshudson
|
625
|
+
third
|
626
|
+
ticonderoga
|
627
|
+
time
|
628
|
+
tor
|
629
|
+
trade
|
630
|
+
tree
|
631
|
+
tt
|
632
|
+
twisted
|
633
|
+
ucl
|
634
|
+
unfinished
|
635
|
+
usborne
|
636
|
+
vedanta
|
637
|
+
viking
|
638
|
+
vintage
|
639
|
+
virago
|
640
|
+
vision
|
641
|
+
voyager
|
642
|
+
vsp
|
643
|
+
website
|
644
|
+
weidenfeldnicolson
|
645
|
+
wesleyan
|
646
|
+
westbow
|
647
|
+
wildside
|
648
|
+
wileysons
|
649
|
+
windrush
|
650
|
+
women’s
|
651
|
+
writing
|
652
|
+
ww
|
653
|
+
yoseloff
|
654
|
+
zondervan
|