|
a |
|
b/test-resources/integration/parse.txt |
|
|
1 |
John Smith was diagnosed with liver disease while in Chicago. |
|
|
2 |
John: |
|
|
3 |
children=[] (list) |
|
|
4 |
context_similarity=-1 |
|
|
5 |
cui=-1 |
|
|
6 |
cui_=-<N>- |
|
|
7 |
definition_=-<N>- |
|
|
8 |
dep=7037928807040764755 (int) |
|
|
9 |
dep_=compound (str) |
|
|
10 |
detected_name_=-<N>- |
|
|
11 |
ent=380 (int) |
|
|
12 |
ent_=PERSON (str) |
|
|
13 |
ent_iob=3 (int) |
|
|
14 |
ent_iob_=B (str) |
|
|
15 |
i=0 (int) |
|
|
16 |
i_sent=0 (int) |
|
|
17 |
idx=0 (int) |
|
|
18 |
is_concept=False |
|
|
19 |
is_contraction=False (bool) |
|
|
20 |
is_ent=True (bool) |
|
|
21 |
is_pronoun=False (bool) |
|
|
22 |
is_punctuation=False (int) |
|
|
23 |
is_space=False (bool) |
|
|
24 |
is_stop=False (bool) |
|
|
25 |
is_superlative=False (bool) |
|
|
26 |
is_wh=False (bool) |
|
|
27 |
lemma_=John (str) |
|
|
28 |
lexspan=(0, 4) (object) |
|
|
29 |
norm=John (str) |
|
|
30 |
norm_len=4 (int) |
|
|
31 |
pos_=PROPN (str) |
|
|
32 |
pref_name_=-<N>- |
|
|
33 |
sent_i=0 (int) |
|
|
34 |
shape=10887629174180191697 (int) |
|
|
35 |
shape_=Xxxx (str) |
|
|
36 |
sub_names=[] |
|
|
37 |
tag=15794550382381185553 (int) |
|
|
38 |
tag_=NNP (str) |
|
|
39 |
tui_descs_= |
|
|
40 |
tuis=frozenset() |
|
|
41 |
tuis_= |
|
|
42 |
Smith: |
|
|
43 |
children=[0] (list) |
|
|
44 |
context_similarity=1 |
|
|
45 |
cui=86418 |
|
|
46 |
cui_=C0086418 |
|
|
47 |
definition_=-<N>- |
|
|
48 |
dep=430 (int) |
|
|
49 |
dep_=nsubjpass (str) |
|
|
50 |
detected_name_=smith |
|
|
51 |
ent=380 (int) |
|
|
52 |
ent_=PERSON (str) |
|
|
53 |
ent_iob=1 (int) |
|
|
54 |
ent_iob_=I (str) |
|
|
55 |
i=1 (int) |
|
|
56 |
i_sent=1 (int) |
|
|
57 |
idx=5 (int) |
|
|
58 |
is_concept=True |
|
|
59 |
is_contraction=False (bool) |
|
|
60 |
is_ent=True (bool) |
|
|
61 |
is_pronoun=False (bool) |
|
|
62 |
is_punctuation=False (int) |
|
|
63 |
is_space=False (bool) |
|
|
64 |
is_stop=False (bool) |
|
|
65 |
is_superlative=False (bool) |
|
|
66 |
is_wh=False (bool) |
|
|
67 |
lemma_=Smith (str) |
|
|
68 |
lexspan=(5, 10) (object) |
|
|
69 |
norm=Smith (str) |
|
|
70 |
norm_len=5 (int) |
|
|
71 |
pos_=PROPN (str) |
|
|
72 |
pref_name_=Homo sapiens |
|
|
73 |
sent_i=0 (int) |
|
|
74 |
shape=16072095006890171862 (int) |
|
|
75 |
shape_=Xxxxx (str) |
|
|
76 |
sub_names=('allen~james~wilcox', 'allen~j~.~wilcox', 'amar~angela~f', 'baity', 'bandoh', 'bostroem', 'carlos~arvelo', 'cotard', 'danlos', 'dr~parkes~weber', 'ehlers', 'foucauldian', 'francisco~herrera~luque', 'george~bernard~shaw', 'giuseppe~paravicini', 'hahn', 'harris', 'hilsenroth', 'homo~sapien', 'homo~sapiens', 'human', 'humanized~version', 'humans', 'human~being', 'human~beings', 'human~origin', 'human~population', 'jose~luis~vethencourt', 'jose~solane', 'jose~solanes', 'jules~cotard', 'knowles', 'lisandro~alvarado', 'max~clara', 'mmy', 'mmy~s', 'parkes~weber', 'pinel~s', 'schwartz', 'sekula~l~kathleen', 'seligman~and~maier', 'shimokawa', 'single~human~host', 'single~human~hosts', 'smith', 'stiles', 'tchernabogov', 'trump', 'trump~s') |
|
|
77 |
tag=15794550382381185553 (int) |
|
|
78 |
tag_=NNP (str) |
|
|
79 |
tui_descs_=Human |
|
|
80 |
tuis=('T016',) |
|
|
81 |
tuis_=T016 |
|
|
82 |
was: |
|
|
83 |
children=[] (list) |
|
|
84 |
context_similarity=-1 |
|
|
85 |
cui=-1 |
|
|
86 |
cui_=-<N>- |
|
|
87 |
definition_=-<N>- |
|
|
88 |
dep=406 (int) |
|
|
89 |
dep_=auxpass (str) |
|
|
90 |
detected_name_=-<N>- |
|
|
91 |
ent=0 (int) |
|
|
92 |
ent_=-<N>- (str) |
|
|
93 |
ent_iob=0 (int) |
|
|
94 |
ent_iob_=O (str) |
|
|
95 |
i=2 (int) |
|
|
96 |
i_sent=2 (int) |
|
|
97 |
idx=11 (int) |
|
|
98 |
is_concept=False |
|
|
99 |
is_contraction=False (bool) |
|
|
100 |
is_ent=False (bool) |
|
|
101 |
is_pronoun=False (bool) |
|
|
102 |
is_punctuation=False (int) |
|
|
103 |
is_space=False (bool) |
|
|
104 |
is_stop=True (bool) |
|
|
105 |
is_superlative=False (bool) |
|
|
106 |
is_wh=False (bool) |
|
|
107 |
lemma_=be (str) |
|
|
108 |
lexspan=(11, 14) (object) |
|
|
109 |
norm=was (str) |
|
|
110 |
norm_len=3 (int) |
|
|
111 |
pos_=AUX (str) |
|
|
112 |
pref_name_=-<N>- |
|
|
113 |
sent_i=0 (int) |
|
|
114 |
shape=4088098365541558500 (int) |
|
|
115 |
shape_=xxx (str) |
|
|
116 |
sub_names=[] |
|
|
117 |
tag=17109001835818727656 (int) |
|
|
118 |
tag_=VBD (str) |
|
|
119 |
tui_descs_= |
|
|
120 |
tuis=frozenset() |
|
|
121 |
tuis_= |
|
|
122 |
diagnosed: |
|
|
123 |
children=[1, 2, 4, 7, 10] (list) |
|
|
124 |
context_similarity=-1 |
|
|
125 |
cui=-1 |
|
|
126 |
cui_=-<N>- |
|
|
127 |
definition_=-<N>- |
|
|
128 |
dep=8206900633647566924 (int) |
|
|
129 |
dep_=ROOT (str) |
|
|
130 |
detected_name_=-<N>- |
|
|
131 |
ent=0 (int) |
|
|
132 |
ent_=-<N>- (str) |
|
|
133 |
ent_iob=0 (int) |
|
|
134 |
ent_iob_=O (str) |
|
|
135 |
i=3 (int) |
|
|
136 |
i_sent=3 (int) |
|
|
137 |
idx=15 (int) |
|
|
138 |
is_concept=False |
|
|
139 |
is_contraction=False (bool) |
|
|
140 |
is_ent=False (bool) |
|
|
141 |
is_pronoun=False (bool) |
|
|
142 |
is_punctuation=False (int) |
|
|
143 |
is_space=False (bool) |
|
|
144 |
is_stop=False (bool) |
|
|
145 |
is_superlative=False (bool) |
|
|
146 |
is_wh=False (bool) |
|
|
147 |
lemma_=diagnose (str) |
|
|
148 |
lexspan=(15, 24) (object) |
|
|
149 |
norm=diagnosed (str) |
|
|
150 |
norm_len=9 (int) |
|
|
151 |
pos_=VERB (str) |
|
|
152 |
pref_name_=-<N>- |
|
|
153 |
sent_i=0 (int) |
|
|
154 |
shape=13110060611322374290 (int) |
|
|
155 |
shape_=xxxx (str) |
|
|
156 |
sub_names=[] |
|
|
157 |
tag=3822385049556375858 (int) |
|
|
158 |
tag_=VBN (str) |
|
|
159 |
tui_descs_= |
|
|
160 |
tuis=frozenset() |
|
|
161 |
tuis_= |
|
|
162 |
with: |
|
|
163 |
children=[6] (list) |
|
|
164 |
context_similarity=-1 |
|
|
165 |
cui=-1 |
|
|
166 |
cui_=-<N>- |
|
|
167 |
definition_=-<N>- |
|
|
168 |
dep=443 (int) |
|
|
169 |
dep_=prep (str) |
|
|
170 |
detected_name_=-<N>- |
|
|
171 |
ent=0 (int) |
|
|
172 |
ent_=-<N>- (str) |
|
|
173 |
ent_iob=0 (int) |
|
|
174 |
ent_iob_=O (str) |
|
|
175 |
i=4 (int) |
|
|
176 |
i_sent=4 (int) |
|
|
177 |
idx=25 (int) |
|
|
178 |
is_concept=False |
|
|
179 |
is_contraction=False (bool) |
|
|
180 |
is_ent=False (bool) |
|
|
181 |
is_pronoun=False (bool) |
|
|
182 |
is_punctuation=False (int) |
|
|
183 |
is_space=False (bool) |
|
|
184 |
is_stop=True (bool) |
|
|
185 |
is_superlative=False (bool) |
|
|
186 |
is_wh=False (bool) |
|
|
187 |
lemma_=with (str) |
|
|
188 |
lexspan=(25, 29) (object) |
|
|
189 |
norm=with (str) |
|
|
190 |
norm_len=4 (int) |
|
|
191 |
pos_=ADP (str) |
|
|
192 |
pref_name_=-<N>- |
|
|
193 |
sent_i=0 (int) |
|
|
194 |
shape=13110060611322374290 (int) |
|
|
195 |
shape_=xxxx (str) |
|
|
196 |
sub_names=[] |
|
|
197 |
tag=1292078113972184607 (int) |
|
|
198 |
tag_=IN (str) |
|
|
199 |
tui_descs_= |
|
|
200 |
tuis=frozenset() |
|
|
201 |
tuis_= |
|
|
202 |
liver: |
|
|
203 |
children=[] (list) |
|
|
204 |
context_similarity=-1 |
|
|
205 |
cui=-1 |
|
|
206 |
cui_=-<N>- |
|
|
207 |
definition_=-<N>- |
|
|
208 |
dep=7037928807040764755 (int) |
|
|
209 |
dep_=compound (str) |
|
|
210 |
detected_name_=-<N>- |
|
|
211 |
ent=0 (int) |
|
|
212 |
ent_=-<N>- (str) |
|
|
213 |
ent_iob=0 (int) |
|
|
214 |
ent_iob_=O (str) |
|
|
215 |
i=5 (int) |
|
|
216 |
i_sent=5 (int) |
|
|
217 |
idx=30 (int) |
|
|
218 |
is_concept=False |
|
|
219 |
is_contraction=False (bool) |
|
|
220 |
is_ent=False (bool) |
|
|
221 |
is_pronoun=False (bool) |
|
|
222 |
is_punctuation=False (int) |
|
|
223 |
is_space=False (bool) |
|
|
224 |
is_stop=False (bool) |
|
|
225 |
is_superlative=False (bool) |
|
|
226 |
is_wh=False (bool) |
|
|
227 |
lemma_=liver (str) |
|
|
228 |
lexspan=(30, 35) (object) |
|
|
229 |
norm=liver (str) |
|
|
230 |
norm_len=5 (int) |
|
|
231 |
pos_=NOUN (str) |
|
|
232 |
pref_name_=-<N>- |
|
|
233 |
sent_i=0 (int) |
|
|
234 |
shape=13110060611322374290 (int) |
|
|
235 |
shape_=xxxx (str) |
|
|
236 |
sub_names=[] |
|
|
237 |
tag=15308085513773655218 (int) |
|
|
238 |
tag_=NN (str) |
|
|
239 |
tui_descs_= |
|
|
240 |
tuis=frozenset() |
|
|
241 |
tuis_= |
|
|
242 |
disease: |
|
|
243 |
children=[5] (list) |
|
|
244 |
context_similarity=-1 |
|
|
245 |
cui=-1 |
|
|
246 |
cui_=-<N>- |
|
|
247 |
definition_=-<N>- |
|
|
248 |
dep=439 (int) |
|
|
249 |
dep_=pobj (str) |
|
|
250 |
detected_name_=-<N>- |
|
|
251 |
ent=0 (int) |
|
|
252 |
ent_=-<N>- (str) |
|
|
253 |
ent_iob=0 (int) |
|
|
254 |
ent_iob_=O (str) |
|
|
255 |
i=6 (int) |
|
|
256 |
i_sent=6 (int) |
|
|
257 |
idx=36 (int) |
|
|
258 |
is_concept=False |
|
|
259 |
is_contraction=False (bool) |
|
|
260 |
is_ent=False (bool) |
|
|
261 |
is_pronoun=False (bool) |
|
|
262 |
is_punctuation=False (int) |
|
|
263 |
is_space=False (bool) |
|
|
264 |
is_stop=False (bool) |
|
|
265 |
is_superlative=False (bool) |
|
|
266 |
is_wh=False (bool) |
|
|
267 |
lemma_=disease (str) |
|
|
268 |
lexspan=(36, 43) (object) |
|
|
269 |
norm=disease (str) |
|
|
270 |
norm_len=7 (int) |
|
|
271 |
pos_=NOUN (str) |
|
|
272 |
pref_name_=-<N>- |
|
|
273 |
sent_i=0 (int) |
|
|
274 |
shape=13110060611322374290 (int) |
|
|
275 |
shape_=xxxx (str) |
|
|
276 |
sub_names=[] |
|
|
277 |
tag=15308085513773655218 (int) |
|
|
278 |
tag_=NN (str) |
|
|
279 |
tui_descs_= |
|
|
280 |
tuis=frozenset() |
|
|
281 |
tuis_= |
|
|
282 |
while: |
|
|
283 |
children=[8] (list) |
|
|
284 |
context_similarity=-1 |
|
|
285 |
cui=-1 |
|
|
286 |
cui_=-<N>- |
|
|
287 |
definition_=-<N>- |
|
|
288 |
dep=443 (int) |
|
|
289 |
dep_=prep (str) |
|
|
290 |
detected_name_=-<N>- |
|
|
291 |
ent=0 (int) |
|
|
292 |
ent_=-<N>- (str) |
|
|
293 |
ent_iob=0 (int) |
|
|
294 |
ent_iob_=O (str) |
|
|
295 |
i=7 (int) |
|
|
296 |
i_sent=7 (int) |
|
|
297 |
idx=44 (int) |
|
|
298 |
is_concept=False |
|
|
299 |
is_contraction=False (bool) |
|
|
300 |
is_ent=False (bool) |
|
|
301 |
is_pronoun=False (bool) |
|
|
302 |
is_punctuation=False (int) |
|
|
303 |
is_space=False (bool) |
|
|
304 |
is_stop=True (bool) |
|
|
305 |
is_superlative=False (bool) |
|
|
306 |
is_wh=False (bool) |
|
|
307 |
lemma_=while (str) |
|
|
308 |
lexspan=(44, 49) (object) |
|
|
309 |
norm=while (str) |
|
|
310 |
norm_len=5 (int) |
|
|
311 |
pos_=SCONJ (str) |
|
|
312 |
pref_name_=-<N>- |
|
|
313 |
sent_i=0 (int) |
|
|
314 |
shape=13110060611322374290 (int) |
|
|
315 |
shape_=xxxx (str) |
|
|
316 |
sub_names=[] |
|
|
317 |
tag=1292078113972184607 (int) |
|
|
318 |
tag_=IN (str) |
|
|
319 |
tui_descs_= |
|
|
320 |
tuis=frozenset() |
|
|
321 |
tuis_= |
|
|
322 |
in: |
|
|
323 |
children=[9] (list) |
|
|
324 |
context_similarity=-1 |
|
|
325 |
cui=-1 |
|
|
326 |
cui_=-<N>- |
|
|
327 |
definition_=-<N>- |
|
|
328 |
dep=443 (int) |
|
|
329 |
dep_=prep (str) |
|
|
330 |
detected_name_=-<N>- |
|
|
331 |
ent=0 (int) |
|
|
332 |
ent_=-<N>- (str) |
|
|
333 |
ent_iob=0 (int) |
|
|
334 |
ent_iob_=O (str) |
|
|
335 |
i=8 (int) |
|
|
336 |
i_sent=8 (int) |
|
|
337 |
idx=50 (int) |
|
|
338 |
is_concept=False |
|
|
339 |
is_contraction=False (bool) |
|
|
340 |
is_ent=False (bool) |
|
|
341 |
is_pronoun=False (bool) |
|
|
342 |
is_punctuation=False (int) |
|
|
343 |
is_space=False (bool) |
|
|
344 |
is_stop=True (bool) |
|
|
345 |
is_superlative=False (bool) |
|
|
346 |
is_wh=False (bool) |
|
|
347 |
lemma_=in (str) |
|
|
348 |
lexspan=(50, 52) (object) |
|
|
349 |
norm=in (str) |
|
|
350 |
norm_len=2 (int) |
|
|
351 |
pos_=ADP (str) |
|
|
352 |
pref_name_=-<N>- |
|
|
353 |
sent_i=0 (int) |
|
|
354 |
shape=4370460163704169311 (int) |
|
|
355 |
shape_=xx (str) |
|
|
356 |
sub_names=[] |
|
|
357 |
tag=1292078113972184607 (int) |
|
|
358 |
tag_=IN (str) |
|
|
359 |
tui_descs_= |
|
|
360 |
tuis=frozenset() |
|
|
361 |
tuis_= |
|
|
362 |
Chicago: |
|
|
363 |
children=[] (list) |
|
|
364 |
context_similarity=1 |
|
|
365 |
cui=8044 |
|
|
366 |
cui_=C0008044 |
|
|
367 |
definition_=-<N>- |
|
|
368 |
dep=439 (int) |
|
|
369 |
dep_=pobj (str) |
|
|
370 |
detected_name_=chicago |
|
|
371 |
ent=384 (int) |
|
|
372 |
ent_=GPE (str) |
|
|
373 |
ent_iob=3 (int) |
|
|
374 |
ent_iob_=B (str) |
|
|
375 |
i=9 (int) |
|
|
376 |
i_sent=9 (int) |
|
|
377 |
idx=53 (int) |
|
|
378 |
is_concept=True |
|
|
379 |
is_contraction=False (bool) |
|
|
380 |
is_ent=True (bool) |
|
|
381 |
is_pronoun=False (bool) |
|
|
382 |
is_punctuation=False (int) |
|
|
383 |
is_space=False (bool) |
|
|
384 |
is_stop=False (bool) |
|
|
385 |
is_superlative=False (bool) |
|
|
386 |
is_wh=False (bool) |
|
|
387 |
lemma_=Chicago (str) |
|
|
388 |
lexspan=(53, 60) (object) |
|
|
389 |
norm=Chicago (str) |
|
|
390 |
norm_len=7 (int) |
|
|
391 |
pos_=PROPN (str) |
|
|
392 |
pref_name_=chicago |
|
|
393 |
sent_i=0 (int) |
|
|
394 |
shape=16072095006890171862 (int) |
|
|
395 |
shape_=Xxxxx (str) |
|
|
396 |
sub_names=('chicago',) |
|
|
397 |
tag=15794550382381185553 (int) |
|
|
398 |
tag_=NNP (str) |
|
|
399 |
tui_descs_=Geographic Area |
|
|
400 |
tuis=('T083',) |
|
|
401 |
tuis_=T083 |
|
|
402 |
.: |
|
|
403 |
children=[] (list) |
|
|
404 |
context_similarity=-1 |
|
|
405 |
cui=-1 |
|
|
406 |
cui_=-<N>- |
|
|
407 |
definition_=-<N>- |
|
|
408 |
dep=445 (int) |
|
|
409 |
dep_=punct (str) |
|
|
410 |
detected_name_=-<N>- |
|
|
411 |
ent=0 (int) |
|
|
412 |
ent_=-<N>- (str) |
|
|
413 |
ent_iob=0 (int) |
|
|
414 |
ent_iob_=O (str) |
|
|
415 |
i=10 (int) |
|
|
416 |
i_sent=10 (int) |
|
|
417 |
idx=60 (int) |
|
|
418 |
is_concept=False |
|
|
419 |
is_contraction=False (bool) |
|
|
420 |
is_ent=False (bool) |
|
|
421 |
is_pronoun=False (bool) |
|
|
422 |
is_punctuation=True (int) |
|
|
423 |
is_space=False (bool) |
|
|
424 |
is_stop=False (bool) |
|
|
425 |
is_superlative=False (bool) |
|
|
426 |
is_wh=False (bool) |
|
|
427 |
lemma_=. (str) |
|
|
428 |
lexspan=(60, 61) (object) |
|
|
429 |
norm=. (str) |
|
|
430 |
norm_len=1 (int) |
|
|
431 |
pos_=PUNCT (str) |
|
|
432 |
pref_name_=-<N>- |
|
|
433 |
sent_i=0 (int) |
|
|
434 |
shape=12646065887601541794 (int) |
|
|
435 |
shape_=. (str) |
|
|
436 |
sub_names=[] |
|
|
437 |
tag=12646065887601541794 (int) |
|
|
438 |
tag_=. (str) |
|
|
439 |
tui_descs_= |
|
|
440 |
tuis=frozenset() |
|
|
441 |
tuis_= |
|
|
442 |
entities: |
|
|
443 |
John Smith |
|
|
444 |
Smith |
|
|
445 |
Chicago |