Spaces:
Sleeping
Sleeping
File size: 41,305 Bytes
0146ef9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 |
from typing import List, Sequence, Tuple, Optional, Dict, Union, Callable
import pandas as pd
import spacy
from spacy.language import Language
from skbio import diversity as dv
SPAN_ATTRS = ["text", "label_", "start", "end"]
CATEGORIES = [
"ATTRIBUTION",
"CITATION",
"COUNTER",
"DENY",
"ENDOPHORIC",
"ENTERTAIN",
"JUSTIFYING",
"MONOGLOSS",
"PROCLAIM",
"SOURCES",
]
def simple_table(
doc: Union[spacy.tokens.Doc, Dict[str, str]],
spans_key: str = "sc",
attrs: List[str] = SPAN_ATTRS,
):
columns = attrs + ["Conf. score"]
data = [
[str(getattr(span, attr)) for attr in attrs] + [score] # [f'{score:.5f}']
for span, score in zip(
doc.spans[spans_key], doc.spans[spans_key].attrs["scores"]
)
]
return data, columns
# def span_info_aggregator()
def construction_classifier(doc, span):
category = None
spanroot = span.root
## Grabbing lexico-grammatical information
span_t_dep_ = ["_".join([t.norm_, t.dep_]) for t in span]
span_dep = [t.dep_ for t in span]
span_token = [t.norm_ for t in span]
span_tag = [t.tag_ for t in span]
c = [c for c in spanroot.children]
c_t_dep_ = ["_".join([t.norm_, t.dep_]) for t in spanroot.children]
c_norm = [c.norm_ for c in spanroot.children]
c_dep = [c.dep_ for c in spanroot.children]
c_pos = [c.pos_ for c in spanroot.children]
c_tag = [c.tag_ for c in spanroot.children]
right_dep = [c.dep_ for c in spanroot.rights]
# conditionals
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
argmentless = all(
c.dep_
not in [
"nsubj",
"nsubjpass",
"csubj",
"csubjpass",
"dobj",
"ccomp",
"xcomp",
"dative",
"attr",
"oprd",
"acomp",
]
for c in spanroot.children
)
argless_span = all(
c.dep_
not in [
"nsubj",
"nsubjpass",
"csubj",
"csubjpass",
"dobj",
"ccomp",
"xcomp",
"dative",
"attr",
"oprd",
"acomp",
]
for c in span
)
## nesting classifiers
if spanroot.dep_ == "conj":
while spanroot.dep_ == "conj":
spanroot = spanroot.head
# if spanroot.dep_ == "poss":
# while spanroot.dep_ == 'poss':
# spanroot = spanroot.head
## Conjunctions
# Preconjunctions
if spanroot.dep_ in ["preconj", "cc"]:
category = "Conjunction"
## NOUN PHRASES
# adverbial phrases
if spanroot.dep_ in ["amod"]:
category = "Adjectival modifier"
# adverbial phrases
if spanroot.dep_ in ["compound"]:
category = "Compound noun"
## Nominal category
if spanroot.dep_ in ["pobj", "dobj", "obj", "iobj", "dative"]:
if "acl" in c_dep:
category = "Noun + Complement (Object)"
else:
category = "Object"
if spanroot.dep_ in ["nsubj", "nsubjpass"]:
if "acl" in c_dep:
category = "Noun + Complement (Subject)"
else:
category = "Subject"
## ADJUNCTS
# prep phrases
if spanroot.dep_ in ["prep", "agent"]:
category = "Prepositional phrase"
# adverbial phrases
if spanroot.dep_ in ["advmod", "npadvmod", "nmod", "npmod", "quantmod"]:
category = "Adverbial phrase"
## Predication patterns
if spanroot.dep_ in ["acomp", "oprd"]:
if "xcomp" in c_dep:
category = "Subject predicate to-cl"
else:
category = "Adjectival complement"
if spanroot.dep_ in ["attr"]:
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
c_head = [c.dep_ for c in spanroot.head.children]
if "expl" in c_head and "no_det" in span_t_dep_:
category = "There is/are no NOUN"
elif "expl" in c_head and spanroot.pos_ in ["NOUN"]:
category = "There is/are + Noun complement"
elif "expl" in c_head and spanroot.tag_ in ["NN", "NNS"]:
category = "There is/are + Noun complement"
elif spanroot.pos_ in ["NOUN", "PRON"]:
if "acl" in c_dep:
category = "Noun + Complement (attr)"
else:
category = "Nominal complement"
elif not subjless and spanroot.pos_ in ["VERB", "AUX"]:
category = "Main verb 4"
elif spanroot.tag_ in ["NNP"]:
category = "Nominal complement"
####################################
### clausal ####
####################################
if spanroot.dep_ in ["ROOT", "advcl", "ccomp", "acl", "pcomp", "relcl"]:
_check_to = [
c.dep_
for c in spanroot.subtree
if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"])
and c.head.dep_ == "xcomp"
]
_check_ing = [
c.dep_
for c in spanroot.subtree
if "Prog" in str(c.morph) and c.dep_ == "xcomp"
]
root_before_ccomp = [
c.i > spanroot.i for c in spanroot.children if c.dep_ == "ccomp"
]
_check_for_to = [
"_".join([c.norm_, c.dep_])
for c in spanroot.subtree
if c.head.dep_ == "advcl" and (c.dep_ == "mark" or c.dep_ == "aux")
]
entire_cl = (
spanroot.left_edge.i == span.start and spanroot.right_edge.i == span.end
)
## Start with broad category, which is then re-evaluated for specific constructions.
if spanroot.dep_ in ["advcl", "mark", "acl", "pcomp"]:
## Adverbial clauses
### Finite-adverbial clauses
### Non-finite adverbial clauses
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
entire_cl = (
spanroot.left_edge.i == span.start and spanroot.right_edge.i == span.end
)
if "mark" in span_dep and spanroot.pos_ in ["VERB", "AUX"]:
category = "Finite adverbial clause"
elif "mark" in span_dep and "aux" in span_dep:
category = "Finite adverbial clause"
elif (
"mark" in span_dep
and spanroot.pos_ in ["VERB", "AUX"]
and "expl" in c_dep
):
category = "Finite adverbial clause"
elif "advmod" in span_dep and ("WRB" in span_tag or "WDT" in span_tag):
if spanroot.pos_ in ["VERB", "AUX"]:
category = "Finite adverbial clause"
elif spanroot.pos_ not in ["VERB", "AUX"] and subjless:
category = "Non-finite adv clause 1"
elif entire_cl:
category = "Finite adverbial clause"
elif (
str(spanroot.morph)
in [
"Aspect=Prog|Tense=Pres|VerbForm=Part",
"Aspect=Perf|Tense=Past|VerbForm=Part",
]
and "aux" not in c_dep
):
# he doing his job
if argmentless:
# e.g., frankly speaking, strictly speaking
category = "Adverbial Phrase"
else:
category = "Non-finite adv clause 2"
elif (
spanroot.pos_ not in ["VERB", "AUX"] and "mark" in span_dep and subjless
):
category = "Non-finite adv clause 3"
elif "aux" in c_dep and "TO" in c_tag:
category = "Adverbial Phrase"
elif "mark" not in span_dep and spanroot.pos_ in ["VERB", "AUX"]:
category = "Dependent Verb phrase"
elif not argmentless:
category = "Adverbial clause"
elif spanroot.dep_ == "advcl":
category = "Adverbial phrase"
if spanroot.dep_ in ["relcl", "ccomp", "acl"]:
head = spanroot.head
if ";" in [t.norm_ for t in head.children]:
category = "Main verb 3"
elif "nsubj" not in span_dep:
category = "Dependent verb 1"
elif "mark" in span_dep:
category = "Complement clause"
elif (
str(spanroot.morph)
in [
"Aspect=Prog|Tense=Pres|VerbForm=Part",
"Aspect=Perf|Tense=Past|VerbForm=Part",
]
and "aux" not in c_dep
):
category = "Non-finite complement clause"
elif spanroot.dep_ in ["relcl"]:
category = "Relative clause"
elif spanroot.dep_ in ["ccomp"]:
category = "Complement clause"
elif spanroot.dep_ in ["acl"]:
category = "Noun Complement clause"
else:
# print(_check_for_to)
category = "this one"
## Specific constructions
# Extraposed that-clause or to-infinitives
if ("it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_) and spanroot.pos_ in [
"VERB",
"AUX",
]:
print(c_dep)
if ("acomp" in c_dep or "oprd" in c_dep) and "ccomp" in c_dep:
# eg it seems odd (oprd) that X.
# eg it is certain (acomp) that X.
category = (
"Extraposed that-cl (adj-complement)" # e.g., it is certain that X.
)
elif "xcomp" in c_dep or ("advcl" in c_dep):
if "for_mark" in _check_for_to:
category = (
"Extraposed to-cl (explicit subj)" # eg It is possible to .
)
elif _check_to:
category = "Extraposed to-cl 1" # eg It is possible to .
elif _check_ing:
category = "Extraposed -ing 1" # eg It is possible to .
elif (
("prep" in right_dep or "npadvmod" in right_dep)
and "ccomp" in right_dep
and spanroot.lemma_ == "be"
):
category = "Cleft construction"
elif "attr" in c_dep:
category = "Extraposed that-cl (copula)" # eg It is a wonder that X.
else:
category = "Extraposed that-cl (VERB)"
# if "ccomp" in c_dep and "auxpass" in c_dep and ("it_nsubjpass" in span_t_dep_ or "it_nsubj" in span_t_dep_):
# category = "Extraposed that-cl (VERB)1" #e.g., it has been shown that X.
elif (
"it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_
) and "acomp" in c_dep:
if "xcomp" in c_dep:
if _check_to:
category = "Extraposed to-cl 2" # eg it is difficult to decide.
elif _check_ing:
category = "Extraposed -ing 2" # eg it is difficult to decide.
else:
category = "Extraposed that-cl (adj-complement) 2"
elif ("it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_) and "oprd" in c_dep:
category = (
"Extraposed that-cl (adj-complement) 3" # eg it seems odd that X.
)
# something without dummy subject "it"
elif (
(("nsubj" in c_dep and spanroot.lemma_ in ["be"]) or "nsubjpass" in c_dep)
and spanroot.pos_ in ["AUX", "VERB"]
and "it" not in c_norm
):
# store xcomp, if the head of the xcomp is acomp
_check_xcomp = [
c.dep_
for c in spanroot.subtree
if c.dep_ in ["xcomp"] and c.head.dep_ == "acomp"
]
_check_ccomp = [
c.dep_
for c in spanroot.subtree
if c.dep_ in ["ccomp"] and c.head.dep_ == "acomp"
]
# _check_to = [c.dep_ for c in spanroot.subtree if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"]) and c.head.dep_ == "xcomp"]
# _check_ing = [c.dep_ for c in spanroot.subtree if "Prog" in str(c.morph) and c.dep_ == "xcomp"]
if ("attr" in c_dep or "acomp" in c_dep) and "ccomp" in c_dep:
if any(root_before_ccomp):
category = "Post-predicate that-cl"
else:
category = "Comment clause"
elif ("attr" in c_dep or "acomp" in c_dep) and "ccomp" in _check_ccomp:
category = "Post-predicate that-cl 2"
elif ("attr" in c_dep or "acomp" in c_dep) and "xcomp" in _check_xcomp:
category = "Post-predicate to-cl"
elif "xcomp" in c_dep and spanroot.lemma_ in ["be"] and _check_to:
category = "Subject predicate to-cl"
elif "xcomp" in c_dep and "auxpass" in c_dep and _check_to:
category = "Subject predicate to-cl (passive)"
elif "xcomp" in c_dep and spanroot.lemma_ in ["be"] and _check_ing:
category = "Subject predicate -ing"
elif "ccomp" in c_dep:
category = "Subject predicate that-cl"
elif "acomp" in c_dep:
category = "Adjectival predicate"
elif "mark" in c_dep and ("nsubj" in c_dep or "nsubjpass" in c_dep):
category = "Finite-adverbial clause"
else:
category = "Main verb 1"
## without dummy subject it, and lexical verbs
elif (
("nsubj" in c_dep or "nsubjpass" in c_dep) in c_dep
and spanroot.pos_ in ["AUX", "VERB"]
and "it" not in c_norm
and spanroot.lemma_ not in ["be"]
):
_check_wh = [
c.dep_
for c in spanroot.subtree
if (
c.dep_ in ["attr", "advmod", "dobj", "nsubj"]
and c.tag_ in ["WP", "WRB", "WDT", "WP$"]
)
and c.head.dep_ == "ccomp"
]
_check_if = [
c.dep_
for c in spanroot.subtree
if (c.dep_ in ["mark"] and c.norm_ in ["whether", "if"])
and c.head.dep_ == "ccomp"
]
# _check_to = [c.dep_ for c in spanroot.subtree if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"]) and c.head.dep_ == "xcomp"]
# _check_ing = [c.dep_ for c in spanroot.subtree if "Prog" in str(c.morph) and c.dep_ == "xcomp"]
if "ccomp" in c_dep and (_check_wh or _check_if):
category = "Post-predicate wh-cl"
elif "ccomp" in c_dep:
if any(root_before_ccomp):
category = "Post-predicate that-cl"
else:
category = "Comment clause"
elif "xcomp" in c_dep:
if _check_to:
category = "Post-predicate to-cl"
elif _check_ing:
category = "Post-predicate -ing"
# Existential
elif "expl" in c_dep and "NOUN" in c_pos and "mark" not in c_dep:
category = "There is/are NOUN"
elif (
"ccomp" in c_dep and "it_nsubj" in span_t_dep_ and spanroot.pos_ in ["AUX"]
):
category = "Cleft construction"
if spanroot.dep_ in ["parataxis"]:
if "_".join(span_dep) in [
"nsubj_parataxis",
"aux_parataxis",
"nsubj_aux_parataxis",
]:
category = "Comment clause"
else:
category = "parataxis (for now)"
## External comp
if spanroot.dep_ in ["xcomp"]:
if spanroot.head.pos_ == "ADJ" and "to_aux" in c_t_dep_:
category = "Adjective complement to-cl"
if spanroot.head.pos_ == "VERB" and "to_aux" in c_t_dep_:
category = "Verb complement to-cl"
if spanroot.dep_ in ["pcomp"]:
if (
str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]
and "ccomp" in c_dep
):
category = "Participle + that-cl"
elif str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]:
category = "Participle"
## Simple classifier
# if spanroot.dep_ in ['pcomp']:
# if str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]:
# category = "Gerund"
if spanroot.dep_ in ["neg"]:
category = "Negative particle"
if spanroot.dep_ in ["aux", "auxpass"]:
category = "Auxiliary"
# Modal verbs
if spanroot.tag_ == "MD":
category = "Modal auxiliary"
if spanroot.dep_ in ["dep", "csubj", "csubjpass"]:
if (
spanroot.head.dep_ in ["ROOT", "ccomp"]
and spanroot.head.pos_ in ["AUX", "VERB"]
and spanroot.pos_ in ["AUX", "VERB"]
):
if spanroot.morph == spanroot.head.morph:
category = "Main verb 4"
else:
category = "Dependent verb 2"
elif str(spanroot.morph) == "Aspect=Prog|Tense=Pres|VerbForm=Part":
category = "Gerund"
elif spanroot.head.dep_ in ["conj", "acl", "relcl"]:
if spanroot.morph == spanroot.head.morph:
category = "Main verb 4"
else:
category = "Dependent verb 2"
elif "VerbForm=Fin" in str(spanroot.morph):
category = "Dependent verb 2"
# Appositive phrases
if spanroot.dep_ in ["appos"]:
if "nummod" in c_dep:
category = "Apposition"
elif spanroot.pos_ in ["PROPN"]:
category = "Appositive Proper Nouns"
elif spanroot.pos_ in ["NOUN"]:
category = "Appositive Noun Phrase"
elif spanroot.pos_ in ["VERB", "AUX"]:
_check = any(
c.dep_ in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
if _check:
category = "Appositive Finite-clause"
if spanroot.dep_ in ["appos", "dep", "attr"]:
if not subjless and spanroot.pos_ in ["VERB", "AUX"]:
category = "Main verb 5"
if spanroot.dep_ in ["dep", "mark"]:
if spanroot.tag_ in ["RB", "IN", "CC"]:
category = "Conjunction"
# sometimes the extra-clausal links are not accurate
if spanroot.dep_ in ["aux", "auxpass", "oprd", "appos", "xcomp"]:
if spanroot.head.dep_ == "ROOT":
category = "Main verb"
else:
category = "dependent verb 5"
if span.label_ == "CITATION":
if "NNP" in span_tag or "NNPS" in span_tag:
if span_dep[0] == "punct" and span_dep[-1] == "punct":
category = "Parenthetical Citation"
elif span_tag[0] in ["NNP", "NNPS"]:
category = "Narrative Citation"
else:
category = "Other Citation"
if category == None:
category = spanroot.dep_
return category
def construction_classifier2(doc, span):
category = None
spanroot = span.root
## Grabbing lexico-grammatical information
span_t_dep_ = ["_".join([t.norm_, t.dep_]) for t in span]
span_dep = [t.dep_ for t in span]
span_token = [t.norm_ for t in span]
span_tag = [t.tag_ for t in span]
c = [c for c in spanroot.children]
c_t_dep_ = ["_".join([t.norm_, t.dep_]) for t in spanroot.children]
c_norm = [c.norm_ for c in spanroot.children]
c_dep = [c.dep_ for c in spanroot.children]
c_pos = [c.pos_ for c in spanroot.children]
c_tag = [c.tag_ for c in spanroot.children]
right_dep = [c.dep_ for c in spanroot.rights]
# conditionals
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
argmentless = all(
c.dep_
not in [
"nsubj",
"nsubjpass",
"csubj",
"csubjpass",
"dobj",
"ccomp",
"xcomp",
"dative",
"attr",
"oprd",
"acomp",
]
for c in spanroot.children
)
argless_span = all(
c.dep_
not in [
"nsubj",
"nsubjpass",
"csubj",
"csubjpass",
"dobj",
"ccomp",
"xcomp",
"dative",
"attr",
"oprd",
"acomp",
]
for c in span
)
argless_span = all(
c.dep_
not in [
"nsubj",
"nsubjpass",
"csubj",
"csubjpass",
"dobj",
"ccomp",
"xcomp",
"dative",
"attr",
"oprd",
"acomp",
]
for c in span
)
## nesting classifiers
if spanroot.dep_ == "conj":
while spanroot.dep_ == "conj":
spanroot = spanroot.head
if spanroot.dep_ == "poss":
head = spanroot.head
if head.dep_ in ["pobj", "dobj", "obj", "iobj", "dative"]:
category = "Posessive Noun (Object)"
elif head.dep_ in ["nsubj", "nsubjpass"]:
category = "Posessive Noun (Subject)"
else:
category = "Posessive Noun (Other)"
## Conjunctions
# Preconjunctions
if spanroot.dep_ in ["preconj", "cc"]:
category = "Conjunction"
## NOUN PHRASES
# adverbial phrases
if spanroot.dep_ in ["amod"]:
category = "Adjectival modifier"
# adverbial phrases
if spanroot.dep_ in ["compound"]:
category = "Compound noun"
## Nominal category
if spanroot.dep_ in ["pobj", "dobj", "obj", "iobj", "dative"]:
if "acl" in c_dep:
category = "Noun + Complement (Object)"
else:
category = "Object"
if spanroot.dep_ in ["nsubj", "nsubjpass"]:
if "acl" in c_dep:
category = "Noun + Complement (Subject)"
else:
category = "Subject"
## ADJUNCTS
# prep phrases
if spanroot.dep_ in ["prep", "agent"]:
category = "Prepositional phrase"
# adverbial phrases
if spanroot.dep_ in ["advmod", "npadvmod", "nmod", "npmod", "quantmod", "nummod"]:
category = "Adverbial phrase"
## Predication patterns
if spanroot.dep_ in ["acomp", "oprd"]:
if "xcomp" in c_dep:
category = "Subject predicate to-cl"
else:
category = "Adjectival complement"
if spanroot.dep_ in ["attr"]:
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
c_head = [c.dep_ for c in spanroot.head.children]
if "expl" in c_head and "no_det" in span_t_dep_:
category = "There is/are no NOUN"
elif "expl" in c_head and spanroot.pos_ in ["NOUN"]:
category = "There is/are + Noun complement"
elif "expl" in c_head and spanroot.tag_ in ["NN", "NNS"]:
category = "There is/are + Noun complement"
elif spanroot.pos_ in ["NOUN", "PRON"]:
if "acl" in c_dep:
category = "Noun + Complement (attr)"
else:
category = "Nominal complement"
elif not subjless and spanroot.pos_ in ["VERB", "AUX"]:
category = "Main verb 4"
elif spanroot.tag_ in ["NNP"]:
category = "Nominal complement"
## External comp
if spanroot.dep_ in ["xcomp"]:
if spanroot.head.pos_ == "ADJ" and "to_aux" in c_t_dep_:
category = "Adjective complement to-cl"
if spanroot.head.pos_ == "VERB" and "to_aux" in c_t_dep_:
category = "Verb complement to-cl"
if spanroot.dep_ in ["pcomp"]:
if (
str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]
and "ccomp" in c_dep
):
category = "Participle + that-cl"
elif str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]:
category = "Participle"
## Simple classifier
# if spanroot.dep_ in ['pcomp']:
# if str(spanroot.morph) in ["Aspect=Prog|Tense=Pres|VerbForm=Part"]:
# category = "Gerund"
if spanroot.dep_ in ["neg"]:
category = "Negative particle"
if spanroot.dep_ in ["aux", "auxpass"]:
category = "Auxiliary"
# Modal verbs
if spanroot.tag_ == "MD":
category = "Modal auxiliary"
####################################
### clausal ####
####################################
if spanroot.dep_ in ["ROOT", "advcl", "ccomp", "acl", "pcomp", "relcl", "punct"]:
_check_to = [
c.dep_
for c in spanroot.subtree
if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"])
and c.head.dep_ == "xcomp"
]
_check_ing = [
c.dep_
for c in spanroot.subtree
if "Prog" in str(c.morph) and c.dep_ == "xcomp"
]
root_before_ccomp = [
c.i > spanroot.i for c in spanroot.children if c.dep_ == "ccomp"
]
_check_for_to = [
"_".join([c.norm_, c.dep_])
for c in spanroot.subtree
if c.head.dep_ == "advcl" and (c.dep_ == "mark" or c.dep_ == "aux")
]
entire_cl = (
spanroot.left_edge.i == span.start and spanroot.right_edge.i == span.end
)
## Start with broad category, which is then re-evaluated for specific constructions.
if spanroot.dep_ in ["advcl", "acl", "punct", "pcomp"]: #'mark',
## Adverbial clauses
subjless = all(
c.dep_ not in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
entire_cl = (
spanroot.left_edge.i == span.start and spanroot.right_edge.i == span.end
)
### Finite-adverbial clauses
if "mark" in span_dep and (
spanroot.pos_ in ["VERB", "AUX"] or "aux" in span_dep
):
category = "Finite adverbial clause"
elif "mark" in span_dep and "aux" in span_dep:
category = "Finite adverbial clause"
elif (
"mark" in span_dep
and spanroot.pos_ in ["VERB", "AUX"]
and "expl" in c_dep
):
category = "Finite adverbial clause"
elif "advmod" in span_dep and ("WRB" in span_tag or "WDT" in span_tag):
if spanroot.pos_ in ["VERB", "AUX"]:
category = "Finite adverbial clause"
elif spanroot.pos_ not in ["VERB", "AUX"] and subjless:
category = "Non-finite adv clause 1"
elif not argmentless:
category = "Finite adverbial clause"
## non-finite
elif (
str(spanroot.morph)
in [
"Aspect=Prog|Tense=Pres|VerbForm=Part",
"Aspect=Perf|Tense=Past|VerbForm=Part",
]
and "aux" not in c_dep
):
# he doing his job
if argmentless:
# e.g., frankly speaking, strictly speaking
category = "Adverbial Phrase"
else:
category = "Non-finite adv clause 2"
elif (
spanroot.pos_ not in ["VERB", "AUX"] and "mark" in span_dep and subjless
):
category = "Non-finite adv clause 3"
elif "aux" in c_dep and "TO" in c_tag:
category = "Adverbial Phrase"
elif "mark" not in span_dep and spanroot.pos_ in ["VERB", "AUX"]:
category = "Dependent Verb phrase"
elif not argmentless:
category = "Adverbial clause"
elif spanroot.dep_ == "advcl":
category = "Adverbial phrase"
else:
category = "Finite adverbial clause "
if spanroot.dep_ in ["relcl", "ccomp", "acl", "punct", "pcomp"]:
head = spanroot.head
if ";" in [t.norm_ for t in head.children]:
category = "Main verb 3"
elif "nsubj" not in span_dep:
category = "Dependent verb 1"
elif "mark" in span_dep:
category = "Complement clause"
elif (
str(spanroot.morph)
in [
"Aspect=Prog|Tense=Pres|VerbForm=Part",
"Aspect=Perf|Tense=Past|VerbForm=Part",
]
and "aux" not in c_dep
):
category = "Non-finite complement clause"
elif spanroot.dep_ in ["relcl"]:
category = "Relative clause"
elif spanroot.dep_ in ["ccomp"]:
category = "Complement clause"
elif spanroot.dep_ in ["acl"]:
category = "Noun Complement clause"
## Specific constructions
# Extraposed that-clause or to-infinitives
if ("it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_) and spanroot.pos_ in [
"VERB",
"AUX",
]:
# print(c_dep)
if ("acomp" in c_dep or "oprd" in c_dep) and "ccomp" in c_dep:
# eg it seems odd (oprd) that X.
# eg it is certain (acomp) that X.
category = (
"Extraposed that-cl (adj-complement)" # e.g., it is certain that X.
)
elif "xcomp" in c_dep or ("advcl" in c_dep):
if "for_mark" in _check_for_to:
category = (
"Extraposed to-cl (explicit subj)" # eg It is possible to .
)
elif _check_to:
category = "Extraposed to-cl 1" # eg It is possible to .
elif _check_ing:
category = "Extraposed -ing 1" # eg It is possible to .
elif (
("prep" in right_dep or "npadvmod" in right_dep)
and "ccomp" in right_dep
and spanroot.lemma_ == "be"
):
category = "Cleft construction"
elif "attr" in c_dep:
category = "Extraposed that-cl (copula)" # eg It is a wonder that X.
else:
category = "Extraposed that-cl (VERB)"
# if "ccomp" in c_dep and "auxpass" in c_dep and ("it_nsubjpass" in span_t_dep_ or "it_nsubj" in span_t_dep_):
# category = "Extraposed that-cl (VERB)1" #e.g., it has been shown that X.
elif (
"it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_
) and "acomp" in c_dep:
if "xcomp" in c_dep:
if _check_to:
category = "Extraposed to-cl 2" # eg it is difficult to decide.
elif _check_ing:
category = "Extraposed -ing 2" # eg it is difficult to decide.
else:
category = "Extraposed that-cl (adj-complement) 2"
elif ("it_nsubjpass" in c_t_dep_ or "it_nsubj" in c_t_dep_) and "oprd" in c_dep:
category = (
"Extraposed that-cl (adj-complement) 3" # eg it seems odd that X.
)
# something without dummy subject "it"
elif (
(("nsubj" in c_dep and spanroot.lemma_ in ["be"]) or "nsubjpass" in c_dep)
and spanroot.pos_ in ["AUX", "VERB"]
and "it" not in c_norm
):
# store xcomp, if the head of the xcomp is acomp
_check_xcomp = [
c.dep_
for c in spanroot.subtree
if c.dep_ in ["xcomp"] and c.head.dep_ == "acomp"
]
_check_ccomp = [
c.dep_
for c in spanroot.subtree
if c.dep_ in ["ccomp"] and c.head.dep_ == "acomp"
]
# _check_to = [c.dep_ for c in spanroot.subtree if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"]) and c.head.dep_ == "xcomp"]
# _check_ing = [c.dep_ for c in spanroot.subtree if "Prog" in str(c.morph) and c.dep_ == "xcomp"]
if ("attr" in c_dep or "acomp" in c_dep) and "ccomp" in c_dep:
if any(root_before_ccomp):
category = "Post-predicate that-cl"
else:
category = "Comment clause"
elif ("attr" in c_dep or "acomp" in c_dep) and "ccomp" in _check_ccomp:
category = "Post-predicate that-cl 2"
elif ("attr" in c_dep or "acomp" in c_dep) and "xcomp" in _check_xcomp:
category = "Post-predicate to-cl"
elif "xcomp" in c_dep and spanroot.lemma_ in ["be"] and _check_to:
category = "Subject predicate to-cl"
elif "xcomp" in c_dep and "auxpass" in c_dep and _check_to:
category = "Subject predicate to-cl (passive)"
elif "xcomp" in c_dep and spanroot.lemma_ in ["be"] and _check_ing:
category = "Subject predicate -ing"
elif "ccomp" in c_dep:
category = "Subject predicate that-cl"
elif "acomp" in c_dep:
category = "Adjectival predicate"
elif "mark" in c_dep and ("nsubj" in c_dep or "nsubjpass" in c_dep):
category = "Finite-adverbial clause"
elif not argmentless and "SCONJ" in c_pos:
category = "Finite-adverbial clause"
else:
category = "Main verb 1"
## without dummy subject it, and lexical verbs
elif (
("nsubj" in c_dep or "nsubjpass" in c_dep) in c_dep
and spanroot.pos_ in ["AUX", "VERB"]
and "it" not in c_norm
and spanroot.lemma_ not in ["be"]
):
_check_wh = [
c.dep_
for c in spanroot.subtree
if (
c.dep_ in ["attr", "advmod", "dobj", "nsubj"]
and c.tag_ in ["WP", "WRB", "WDT", "WP$"]
)
and c.head.dep_ == "ccomp"
]
_check_if = [
c.dep_
for c in spanroot.subtree
if (c.dep_ in ["mark"] and c.norm_ in ["whether", "if"])
and c.head.dep_ == "ccomp"
]
# _check_to = [c.dep_ for c in spanroot.subtree if (c.dep_ in ["aux"] and c.pos_ in ["PART", "SCONJ"]) and c.head.dep_ == "xcomp"]
# _check_ing = [c.dep_ for c in spanroot.subtree if "Prog" in str(c.morph) and c.dep_ == "xcomp"]
if "ccomp" in c_dep and (_check_wh or _check_if):
category = "Post-predicate wh-cl"
elif "ccomp" in c_dep:
if any(root_before_ccomp):
category = "Post-predicate that-cl"
else:
category = "Comment clause"
elif "xcomp" in c_dep:
if _check_to:
category = "Post-predicate to-cl"
elif _check_ing:
category = "Post-predicate -ing"
# Existential
elif "expl" in c_dep and "NOUN" in c_pos and "mark" not in c_dep:
category = "There is/are NOUN"
elif (
"ccomp" in c_dep and "it_nsubj" in span_t_dep_ and spanroot.pos_ in ["AUX"]
):
category = "Cleft construction"
### The end of clausal analysis
if spanroot.dep_ in ["parataxis"]:
if "_".join(span_dep) in [
"nsubj_parataxis",
"aux_parataxis",
"nsubj_aux_parataxis",
]:
category = "Comment clause"
else:
category = "Parataxis"
if spanroot.dep_ in ["dep", "csubj", "csubjpass"]:
if (
spanroot.head.dep_ in ["ROOT", "ccomp"]
and spanroot.head.pos_ in ["AUX", "VERB"]
and spanroot.pos_ in ["AUX", "VERB"]
):
if spanroot.morph == spanroot.head.morph:
category = "Main verb 4"
else:
category = "Dependent verb 2"
elif str(spanroot.morph) == "Aspect=Prog|Tense=Pres|VerbForm=Part":
category = "Gerund"
elif "VerbForm=Fin" in str(spanroot.morph) or "VerbForm=Inf" in str(
spanroot.morph
):
category = "Dependent verb 2"
elif spanroot.dep_ in ["csubj", "csubjpass"]:
category = "Dependent verb (csubj)"
# Appositive phrases
if spanroot.dep_ in ["appos"]:
if "nummod" in c_dep:
category = "Apposition"
if spanroot.pos_ in ["PROPN"]:
category = "Appositive Proper Nouns"
elif spanroot.pos_ in ["NOUN"]:
category = "Appositive Noun Phrase"
elif spanroot.pos_ in ["VERB", "AUX"]:
_check = any(
c.dep_ in ["nsubj", "nsubjpass", "csubj", "csubjpass"]
for c in spanroot.children
)
if _check:
category = "Appositive Finite-clause"
if spanroot.dep_ in ["appos", "dep", "attr"]:
if not subjless and spanroot.pos_ in ["VERB", "AUX"]:
category = "Main verb (likely parsing error)"
# sometimes the dep are on the conjunctions
if spanroot.dep_ in ["dep", "mark"]:
if spanroot.tag_ in ["RB", "IN", "CC"]:
category = "Conjunction"
if spanroot.dep_ in ["intj"]:
category = "Introjection"
# sometimes the extra-clausal links are not accurate
if (
spanroot.dep_
in ["aux", "auxpass", "oprd", "appos", "xcomp", "attr", "dep", "meta", "prt"]
and category == None
):
if spanroot.head.dep_ == "ROOT":
category = "Main verb"
else:
category = "dependent verb 5"
if span.label_ == "CITATION":
if "NNP" in span_tag or "NNPS" in span_tag:
if span_dep[0] == "punct" and span_dep[-1] == "punct":
category = "Parenthetical Citation"
elif span_tag[0] in ["NNP", "NNPS"]:
category = "Narrative Citation"
else:
category = "Other Citation"
if category == None:
category = spanroot.dep_
return category
def const_table(
doc: Union[spacy.tokens.Doc, Dict[str, str]],
spans_key: str = "sc",
attrs: List[str] = SPAN_ATTRS,
):
columns = attrs + [
"Conf. score",
"sent no.",
"grammatical realization",
"span dep",
"ner",
"POS",
"span dep seq",
"TAG sequence",
"POS sequence",
"head",
"head dep",
"children",
"morphology",
"sent",
]
data = []
# data = span_info_aggregator(doc, columns)
sentences = {s: i for i, s in enumerate(doc.sents)}
for span, score in zip(doc.spans[spans_key], doc.spans[spans_key].attrs["scores"]):
span_info = []
span_info.extend([str(getattr(span, attr)) for attr in attrs])
span_info.append(score)
span_info.append(int(sentences[span.sent]))
span_info.append(construction_classifier2(doc, span))
span_info.append(span.root.dep_)
span_info.append(span.root.ent_type_)
span_info.append(span.root.tag_)
span_info.append("_".join([t.dep_ for t in span]))
span_info.append("_".join([t.tag_ for t in span]))
span_info.append("_".join([t.pos_ for t in span]))
span_info.append(span.root.head.norm_)
span_info.append(span.root.head.dep_)
span_info.append("_".join([c.dep_ for c in span.root.children]))
span_info.append(str(span.root.morph))
span_info.append(span.sent.text.strip())
data.append(span_info)
return data, columns
def ngrammar(seq: list, n=2, concat=False, sep="-"):
result = []
n_item = len(seq)
for idx, item in enumerate(seq):
if idx + n <= n_item:
if concat:
result.append(sep.join(seq[idx : idx + n]))
else:
result.append(seq[idx : idx + n])
return result
def diversity_values(count_vec: list):
result = {}
if len(count_vec) == 0:
count_vec = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
result["shannon"] = dv.alpha.shannon(list(count_vec), base=2)
result["brillouin_d"] = dv.alpha.brillouin_d(list(count_vec))
result["simpson_d"] = 1 - dv.alpha.simpson(list(count_vec))
result["simpson_e"] = dv.alpha.simpson_e(list(count_vec))
# result['gini_index'] = dv.alpha.gini_index(list(count_vec))
# result['faith_pd'] = dv.alpha.faith_pd(list(count_vec))
return result
|