Upload tokenizer
Browse files
morph_tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"morph_encodings": {"<pad>": 0, "<eos>": 1, "<unk>": 2, "<extra_id_0>": 3, "IPro-NNP": 4, "V-PPA-AMP": 5, "PPro-DN1S": 6, "Art-VFS": 7, "Adj-ANP-C": 8, "V-APM-GMS": 9, "N-NFP": 10, "PPro-DF2S": 11, "V-APM-AMS": 12, "V-PPA-AMS": 13, "V-PSA-3S": 14, "PPro-AN3S": 15, "V-FIA-1P": 16, "IPro-ANS": 17, "V-PPA-GFP": 18, "V-RMM/P-2P": 19, "V-PPM/P-NFP": 20, "N-DNS": 21, "Adj-NMP": 22, "V-AIP-3P": 23, "V-RNA": 24, "Adj-DNS-C": 25, "V-ASM-2S": 26, "Art-ANS": 27, "V-FIP-2P": 28, "V-APA-NMP": 29, "V-IIM-2S": 30, "V-PPM-GNP": 31, "V-RPM/P-GNP": 32, "V-PMM/P-3S": 33, "IPro-GNS": 34, "V-PNM": 35, "N-NNP": 36, "V-FIP-2S": 37, "Art-AFP": 38, "RelPro-GNP": 39, "N-GFS": 40, "V-APM-DNP": 41, "V-RPM/P-GMP": 42, "V-RIM/P-2S": 43, "V-APM/P-GFS": 44, "RelPro-DMP": 45, "Adj-DMS-C": 46, "V-RPM/P-DFS": 47, "V-PPM-NMP": 48, "V-AMM-3P": 49, "Art-AMS": 50, "Adj-AMP": 51, "RelPro-GFP": 52, "IPro-NFS": 53, "RefPro-DM3S": 54, "Adj-VNP": 55, "V-AIP-2P": 56, "Adj-NNP-C": 57, "V-RPM/P-AFS": 58, "V-M-2S": 59, "Adj-AFP": 60, "Art-AFS": 61, "N-GMP": 62, "IPro-NMP": 63, "Adj-NMP-C": 64, "V-APM-GFP": 65, "Adj-DMP-C": 66, "Indec": 67, "V-ASP-1P": 68, "V-FPA-NMS": 69, "Prtcl": 70, "DPro-GMP": 71, "V-PPM-ANS": 72, "V-PPP-GMP": 73, "V-PPA-NFP": 74, "V-IIM-1P": 75, "IPro-DMP": 76, "V-AIA-3S": 77, "N-ANP": 78, "Art-DNS": 79, "V-APA-GMS": 80, "V-APM-GFS": 81, "PPro-AN1S": 82, "V-RNM/P": 83, "RelPro-GNS": 84, "IPro-AFS": 85, "PPro-DM3S": 86, "V-RPA-GMP": 87, "V-RPM-NMS": 88, "V-AOA-3P": 89, "V-RPA-DMP": 90, "V-RPM/P-DFP": 91, "PPro-G1S": 92, "V-PIA-2S": 93, "V-RIP-1P": 94, "V-IIP-1P": 95, "V-APP-GMS": 96, "V-PPM/P-DFP": 97, "V-APA-NFS": 98, "RelPro-AMS": 99, "V-PIA-2P": 100, "V-PPA-DMP": 101, "V-PPM/P-NMP": 102, "PPro-G2S": 103, "V-AMP-2P": 104, "V-AIM-3P": 105, "Art-DFP": 106, "PPro-AM1S": 107, "V-IIM/P-1S": 108, "PPro-AM3S": 109, "PPro-GM1S": 110, "PPro-AN2P": 111, "V-ASM-2P": 112, "RelPro-AFP": 113, "Art-GMS": 114, "N-GMS": 115, "Adj-VMS": 116, "Art-DMS": 117, "V-ASP-1S": 118, "V-AMM-3S": 119, "V-PSM-1S": 120, "V-RPA-ANP": 121, "V-APP-DNP": 122, "V-POM/P-3S": 123, "IPro-GMP": 124, "V-APP-NMP": 125, "Adj-NMS-C": 126, "PPro-AM1P": 127, "V-APA-ANP": 128, "Adj-DMP": 129, "V-AIM-1S": 130, "RefPro-DM3P": 131, "V-PSM/P-3S": 132, "Adj-AFP-C": 133, "PPro-AF2P": 134, "RelPro-GFS": 135, "N-AFS": 136, "Adj-GMP": 137, "V-PIM-2P": 138, "V-AIA-2S": 139, "V-APA-GNS": 140, "V-PPA-NMS": 141, "V-PIM/P-2S": 142, "Adj-ANS-C": 143, "V-RPM/P-VFS": 144, "RefPro-GM3S": 145, "Adj-DFS-C": 146, "PPro-A1S": 147, "V-RPA-DNS": 148, "V-PPM-GFP": 149, "V-IIM/P-2S": 150, "PPro-GM3S": 151, "V-ASA-1S": 152, "N-NMP": 153, "N-AMS": 154, "PPro-DM1P": 155, "IPro-ANP": 156, "IPro-AFP": 157, "Adj-DNS": 158, "V-APA-AFP": 159, "Adj-AMP-C": 160, "V-AIM-2S": 161, "V-APP-DMS": 162, "V-PNM/P": 163, "N-GFP": 164, "V-PMA-3P": 165, "Adj-VMP": 166, "V-PIA-1S": 167, "V-IIA-3S": 168, "DPro-NMP": 169, "Art-NMS": 170, "V-AMA-2S": 171, "Adj-GMS-C": 172, "V-PPM-DMS": 173, "Adj-NNS": 174, "V-PPM/P-DNP": 175, "V-ANA": 176, "V-FIP-1P": 177, "PPro-NM1S": 178, "PPro-N2P": 179, "V-AOM-1S": 180, "V-PIM-3P": 181, "Art-ANP": 182, "Art-GNP": 183, "IPro-GNP": 184, "V-PSA-1P": 185, "V-AIA-1S": 186, "V-PPA-GMP": 187, "V-PPM/P-DMP": 188, "RelPro-DNS": 189, "Art-DNP": 190, "IPro-DNS": 191, "IPro-DFS": 192, "V-LIM/P-3S": 193, "V-FIP-3P": 194, "V-PPA-DNP": 195, "Adj-DFS": 196, "V-RPA-GNP": 197, "V-APA-NFP": 198, "Adj-GMP-C": 199, "V-ASA-2S": 200, "RecPro-AMP": 201, "V-RIM/P-3P": 202, "RefPro-GF3S": 203, "V-PIM-3S": 204, "DPro-GFP": 205, "V-RPA-NFS": 206, "PPro-AN3P": 207, "RelPro-AMP": 208, "RefPro-AM3P": 209, "PPro-DF2P": 210, "N-DNP": 211, "V-LIM-3P": 212, "V-RIM/P-1S": 213, "V-APM-AFS": 214, "V-PNP": 215, "V-APP-NNS": 216, "V-FIP-1S": 217, "V-IIM/P-3P": 218, "V-APP-ANS": 219, "V-PPM/P-GFP": 220, "V-RPM/P-AFP": 221, "V-LIA-2P": 222, "V-AMA-3P": 223, "V-PPM/P-DNS": 224, "PPro-GF2P": 225, "RefPro-AN3P": 226, "V-AIP-3S": 227, "PPro-NF3S": 228, "V-PSA-2S": 229, "DPro-DFP": 230, "Adj-NMS": 231, "V-FIA-2S": 232, "PPro-D1P": 233, "DPro-NFP": 234, "V-RPA-GMS": 235, "V-PMM/P-3P": 236, "V-APA-GFS": 237, "V-PSA-1S": 238, "Art-VMS": 239, "Adj-ANP-S": 240, "DPro-AMS": 241, "DPro-AFS": 242, "DPro-GFS": 243, "V-AIP-1P": 244, "Adj-DMS": 245, "V-APP-AFS": 246, "V-AOP-3S": 247, "V-PPA-GMS": 248, "DPro-DMP": 249, "V-AOM-3S": 250, "V-AIP-2S": 251, "V-APA-ANS": 252, "PPro-NFS": 253, "V-APM-GNP": 254, "V-PIM/P-1S": 255, "PPro-GN3S": 256, "V-RPA-AFS": 257, "Adv-C": 258, "PPro-GM3P": 259, "Adj-NNP": 260, "V-APP-GMP": 261, "V-FIM-3S": 262, "V-RIM-2S": 263, "V-ASP-2S": 264, "V-FPP-GNP": 265, "V-AIM-1P": 266, "DPro-NMS": 267, "V-APM-DMP": 268, "Adj-DNS-S": 269, "RelPro-DMS": 270, "Adj-GNS-S": 271, "Art-DMP": 272, "V-APA-NNS": 273, "V-APP-DNS": 274, "V-APP-ANP": 275, "V-FIP-3S": 276, "V-APA-NNP": 277, "Adj-VFS": 278, "PPro-DF3S": 279, "V-RPM/P-NFP": 280, "I": 281, "RefPro-GN3P": 282, "Adj-GNS": 283, "DPro-DFS": 284, "PPro-NM3S": 285, "PPro-AF1S": 286, "V-AMP-3P": 287, "DPro-NNS": 288, "V-PPA-DFP": 289, "DPro-GMS": 290, "V-PSM-3S": 291, "V-IIM-3P": 292, "V-PMP-2P": 293, "RelPro-NMS": 294, "Art-GFP": 295, "V-IIM/P-3S": 296, "PPro-NM1P": 297, "V-RIM/P-1P": 298, "PPro-GF1S": 299, "V-PMM-2S": 300, "V-PPM-AFS": 301, "Adj-AFS": 302, "IPro-AMS": 303, "V-APM-NFP": 304, "V-PPM-NMS": 305, "V-APP-NFS": 306, "V-RSA-1P": 307, "Adj": 308, "PPro-AN2S": 309, "Art-GNS": 310, "Adj-GMS": 311, "V-PPA-DFS": 312, "V-PPA-ANS": 313, "Adj-DMS-S": 314, "V-APA-DMP": 315, "V-RPM/P-DNP": 316, "V-LIM-3S": 317, "V-RMM/P-2S": 318, "PPro-A2S": 319, "V-PMA-2S": 320, "RelPro-NFP": 321, "V-PPA-NNP": 322, "V-APM-GNS": 323, "Art-GMP": 324, "PPro-NM3P": 325, "V-PPA-GFS": 326, "V-PPM-NFS": 327, "Art-VNS": 328, "PPro-GN1P": 329, "Adj-DFP": 330, "V-APA-GMP": 331, "Adj-GNP-S": 332, "V-APM-ANP": 333, "V-RIM/P-2P": 334, "DPro-ANS": 335, "Art-GFS": 336, "V-PMP-3S": 337, "V-PSA-3P": 338, "V-IIA-3P": 339, "V-PPM-AMP": 340, "IPro-NFP": 341, "V-IIM/P-1P": 342, "PPro-DF3P": 343, "V-PSA-2P": 344, "V-PPM-GMS": 345, "V-APM-NMP": 346, "V-PPM-DMP": 347, "V-IIM-3S": 348, "N-GNP": 349, "Adv": 350, "V-AOA-3S": 351, "V-RPM-NMP": 352, "V-PPM-NFP": 353, "V-APP-NFP": 354, "V-FIM-3P": 355, "Adj-NFS-S": 356, "V-ASA-2P": 357, "DPro-GNS": 358, "V-PIP-3S": 359, "V-AMA-2P": 360, "V-RPM/P-NNP": 361, "Adj-AFS-S": 362, "DPro-AMP": 363, "PPro-GF2S": 364, "N-GNS": 365, "V-ANM": 366, "V-PIM-1S": 367, "RecPro-DMP": 368, "V-PPM-GFS": 369, "RefPro-GM3P": 370, "Adj-VMP-C": 371, "V-IIA-1P": 372, "V-APA-DMS": 373, "Adj-NFS-C": 374, "V-PPA-ANP": 375, "V-AIP-1S": 376, "V-FIA-3P": 377, "V-APM-AMP": 378, "V-PMM/P-2P": 379, "Adj-ANS": 380, "V-PPA-NNS": 381, "V-APP-AMS": 382, "RefPro-DF3P": 383, "V-PIM/P-3S": 384, "N-DFS": 385, "PPro-D1S": 386, "V-IIA-2P": 387, "V-RMA-2P": 388, "V-AIM-3S": 389, "RefPro-AF3S": 390, "V-PNA": 391, "V-RPA-NMS": 392, "PPro-DM3P": 393, "V-APP-DFS": 394, "V-PPM/P-GMS": 395, "V-RIA-1P": 396, "RecPro-DNP": 397, "Adj-GFP-S": 398, "RelPro-NNS": 399, "V-PPM/P-VMP": 400, "V-PIM-1P": 401, "IPro-GMS": 402, "V-RPM/P-DMS": 403, "V-IIA-2S": 404, "V-AIA-1P": 405, "V-FPA-NMP": 406, "V-ASP-3P": 407, "Adj-AFS-C": 408, "PPro-GF3P": 409, "V-ASM-1P": 410, "V-PPM/P-AFP": 411, "PPro-NN2S": 412, "IPro-AMP": 413, "V-RPM/P-VMP": 414, "PPro-GF1P": 415, "PPro-NN1S": 416, "V-AMP-2S": 417, "PPro-N1P": 418, "V-POM/P-3P": 419, "V-RPM/P-ANS": 420, "N-DMP": 421, "N": 422, "V-PPM/P-NFS": 423, "V-PMM-2P": 424, "V-APM/P-NMS": 425, "N-VFP": 426, "V-PPM/P-NMS": 427, "PPro-GF3S": 428, "V-RIM/P-3S": 429, "Adj-NFP": 430, "V-ASP-2P": 431, "V-IIA-1S": 432, "V-RPM/P-GMS": 433, "V-RPM-AMS": 434, "V-PPM/P-NNS": 435, "PPro-DN1P": 436, "V-RPM/P-NNS": 437, "V-PPA-NMP": 438, "RefPro-GN3S": 439, "V-RSA-1S": 440, "PPro-DM2S": 441, "V-PPA-AFP": 442, "V-FIA-1S": 443, "Art-AMP": 444, "V-PIM/P-1P": 445, "V-APM-GMP": 446, "V-APM-ANS": 447, "V-PMM/P-2S": 448, "Adj-NFP-S": 449, "V-PPA-DNS": 450, "V-ASA-3P": 451, "Art-NFP": 452, "V-PPM/P-ANS": 453, "V-PSM/P-1S": 454, "V-RPA-ANS": 455, "V-PPM/P-GMP": 456, "DPro-GNP": 457, "V-APP-GFP": 458, "V-RPM/P-VMS": 459, "V-ASA-3S": 460, "V-FPA-ANP": 461, "V-ASM-1S": 462, "V-PPM/P-AMS": 463, "N-NFS": 464, "V-PPM/P-VMS": 465, "V-APP-AMP": 466, "V-AMP-3S": 467, "Adv-S": 468, "RelPro-DFS": 469, "V-PPM/P-GFS": 470, "V-PPM/P-NNP": 471, "RelPro-ANS": 472, "Adj-NNS-C": 473, "N-VNS": 474, "N-DFP": 475, "V-PPM-GMP": 476, "N-AMP": 477, "V-RPA-AMS": 478, "DPro-DNP": 479, "Prep": 480, "RefPro-AM3S": 481, "V-PPM/P-DMS": 482, "V-ANP": 483, "V-PPA-VMS": 484, "N-NNS": 485, "V-AIA-3P": 486, "V-APA-AFS": 487, "DPro-AFP": 488, "V-FIM-2S": 489, "V-APA-AMS": 490, "Adj-DFS-S": 491, "V-RPA-NNP": 492, "V-APM/P-ANP": 493, "Adj-VNS": 494, "V-PPM/P-DFS": 495, "Adj-GNP-C": 496, "N-AFP": 497, "V-APP-GNS": 498, "RelPro-DNP": 499, "PPro-DF1P": 500, "Art-NFS": 501, "V-LIA-1S": 502, "RelPro-NNP": 503, "V-PSM-1P": 504, "V-ASP-3S": 505, "IPro-GFP": 506, "PPro-AF3P": 507, "V-RPM/P-DNS": 508, "PPro-AF1P": 509, "IPro-DMS": 510, "V-RPM/P-NMP": 511, "PPro-DM2P": 512, "V-APP-GNP": 513, "V-PIA-1P": 514, "V-ASM-3P": 515, "V-AMA-3S": 516, "RelPro-NFS": 517, "V-PPM/P-GNP": 518, "V-POM/P-1S": 519, "N-VFS": 520, "V-POA-2P": 521, "PPro-GM2S": 522, "V-RPA-AMP": 523, "Adj-GMP-S": 524, "PPro-N2S": 525, "V-LIA-3S": 526, "PPro-N1S": 527, "V-AMM-2P": 528, "IPro-NNS": 529, "V-FIM/P-2P": 530, "Adj-AMS": 531, "RelPro-AFS": 532, "PPro-DM1S": 533, "Art-VMP": 534, "PPro-NN1P": 535, "DPro-NNP": 536, "N-VMP": 537, "V-PIA-3S": 538, "V-RIA-1S": 539, "V-RPM/P-NMS": 540, "DPro-DNS": 541, "V-PPM-AMS": 542, "RelPro-GMP": 543, "V-FIA-2P": 544, "N-VMS": 545, "PPro-AN1P": 546, "V-PPP-GMS": 547, "V-PPM-NNS": 548, "RelPro-DFP": 549, "PPro-AM2S": 550, "N-ANS": 551, "PPro-NM2S": 552, "V-RIA-3P": 553, "V-PPA-VFS": 554, "V-RIA-2S": 555, "V-APP-NMS": 556, "V-FIA-3S": 557, "V-PIA-3P": 558, "PPro-DN3P": 559, "N-VNP": 560, "V-RPM/P-AMP": 561, "V-IIP-3P": 562, "Art-VFP": 563, "V-PSM-2S": 564, "V-RPA-NFP": 565, "RelPro-ANP": 566, "V-PSM/P-1P": 567, "PPro-AF2S": 568, "V-RSA-2P": 569, "V-PPM/P-AFS": 570, "Conj": 571, "Adj-ANS-S": 572, "Adj-DNP-S": 573, "PPro-NN3S": 574, "V-RPA-GFS": 575, "V-FIM-1P": 576, "Adj-NFP-C": 577, "V-ANM/P": 578, "PPro-A1P": 579, "V-AIM-2P": 580, "RelPro-GMS": 581, "V-LIA-3P": 582, "Heb": 583, "Adj-GMS-S": 584, "V-RIM-3S": 585, "Adj-GNP": 586, "V-PPM/P-AMP": 587, "V-PSM/P-2P": 588, "V-PSM/P-3P": 589, "IntPrtcl": 590, "V-PPP-DMP": 591, "Art-NNS": 592, "V-APA-DFP": 593, "Art-NNP": 594, "V-PPA-VMP": 595, "Art-VNP": 596, "V-PIM/P-3P": 597, "V-PPA-DMS": 598, "PPro-NF1P": 599, "PPro-NF1S": 600, "V-ASA-1P": 601, "V-APM-NFS": 602, "PPro-G1P": 603, "PPro-NN3P": 604, "V-RPM/P-GFP": 605, "Adj-GFS": 606, "V-APP-NNP": 607, "PPro-AF3S": 608, "IPro-NMS": 609, "V-APM-NNS": 610, "PPro-D2S": 611, "V-RPM/P-NFS": 612, "V-PPA-GNP": 613, "N-NMS": 614, "RelPro-NMP": 615, "RefPro-DF3S": 616, "V-PMA-3S": 617, "PPro-NF2P": 618, "Adj-GFP": 619, "DPro-DMS": 620, "Art-NMP": 621, "V-RPM/P-GFS": 622, "V-IIM-1S": 623, "V-PPM/P-ANP": 624, "V-PSM/P-2S": 625, "V-APA-DFS": 626, "V-RPA-NNS": 627, "V-PPP-NMP": 628, "V-RPM/P-DMP": 629, "PPro-AM2P": 630, "V-PIP-1S": 631, "V-APA-AMP": 632, "V-APP-GFS": 633, "Adj-DNP": 634, "Adj-NMS-S": 635, "PPro-GN3P": 636, "V-POA-3P": 637, "V-PIM/P-2P": 638, "V-PPA-AFS": 639, "PPro-A2P": 640, "RecPro-GMP": 641, "V-RIA-3S": 642, "V-PPM/P-GNS": 643, "V-PPA-GNS": 644, "V-IIM/P-2P": 645, "V-FPM-ANS": 646, "V-APM-NMS": 647, "RefPro-GF3P": 648, "DPro-NFS": 649, "Adj-AMS-C": 650, "PPro-G2P": 651, "PPro-DN3S": 652, "V-RPM/P-AMS": 653, "N-DMS": 654, "Art-DFS": 655, "PPro-NM2P": 656, "V-AIA-2P": 657, "V-RPA-NMP": 658, "V-RPM/P-GNS": 659, "PPro-AM3P": 660, "V-RPA-DMS": 661, "DPro-ANP": 662, "V-PPM-GNS": 663, "V-M-2P": 664, "V-RSA-2S": 665, "Adj-DFP-C": 666, "V-FIM-2P": 667, "V-AMM-2S": 668, "V-RIA-2P": 669, "V-PMA-2P": 670, "V-APA-NMS": 671, "V-PPA-NFS": 672, "RefPro-AF3P": 673, "V-ASM-3S": 674, "PPro-NN2P": 675, "PPro-D2P": 676, "Adj-ANP": 677, "IPro-GFS": 678, "PPro-DF1S": 679, "Adj-VMS-S": 680, "V-RPM/P-ANP": 681, "V-FIM-1S": 682, "V-POA-3S": 683, "V-FNM": 684, "Adj-NFS": 685, "V-LIA-2S": 686, "Adj-GFS-C": 687}, "special_tokens_map": {"pad_token": "<pad>", "eos_token": "<eos>", "unk_token": "<unk>", "block_separator_token": "<extra_id_0>"}, "unique_tags": ["DPro-NNP", "Art-GFP", "I", "Art-NNP", "V-RIA-2P", "V-LIM-3S", "Art-NMS", "V-ASP-1P", "V-FIM-2S", "Adj-DFP", "V-PPA-VMP", "PPro-NF1P", "V-APA-ANP", "Art-DMP", "N-NMP", "IPro-NFS", "IPro-GNS", "V-FIA-3S", "V-PPA-AMS", "IPro-GMS", "Adj-GMP-S", "PPro-GF1S", "V-AIA-1S", "Adj-VNS", "V-PMM-2S", "V-APP-DNP", "IPro-GNP", "V-FIM-3S", "V-AMA-3P", "Adj-ANP-S", "Adj-DNS-S", "PPro-DF3P", "V-RPM/P-VMS", "Adv-C", "V-RPM/P-NMP", "Adj-NMP-C", "V-PPM/P-VMS", "PPro-AF1P", "Adj-AFP", "DPro-GNP", "PPro-DN1S", "Art-AMP", "RelPro-ANP", "V-IIA-3S", "V-RPM/P-VMP", "V-IIM/P-1P", "RefPro-AF3P", "PPro-AM2S", "Art-VNP", "DPro-DMP", "V-POA-3P", "RelPro-AFP", "DPro-GFS", "V-APM-GMP", "V-APM-ANS", "PPro-A1S", "V-IIM/P-2P", "V-PPA-DMS", "V-POM/P-3S", "RecPro-AMP", "V-PPM-GFS", "V-PSM/P-2P", "Conj", "Adj-GNS", "PPro-GF2P", "V-FPP-GNP", "V-PNM/P", "IPro-AMS", "PPro-AN1P", "RefPro-GF3P", "V-AIM-2S", "N-GNS", "PPro-NN3P", "Art-NNS", "IntPrtcl", "Art-AFP", "V-PPM-NFS", "PPro-AF3P", "V-APP-AFS", "Adj-DNS", "V-AIM-2P", "V-APP-GFS", "V-PSM-1S", "V-RMM/P-2S", "V-AIA-2S", "V-LIM/P-3S", "V-FPA-ANP", "V-FPA-NMS", "Adj-GFP", "V-FIA-2P", "IPro-DNS", "PPro-N1S", "Adj-NFP", "Adj-DNP", "V-PPA-NNS", "RelPro-DNP", "Adj-DMS-S", "V-PMM/P-2P", "V-FIA-1S", "V-APP-GNS", "DPro-DFS", "V-ASP-3S", "V-ASA-3P", "Adj-VMP", "RelPro-ANS", "V-PPA-AFP", "RelPro-GNS", "V-PPM/P-ANS", "V-PIM-2P", "V-RIM/P-1P", "V-ASA-2S", "RefPro-GF3S", "V-RPM/P-AMS", "PPro-G1P", "Adj-GMS-C", "V-IIM/P-1S", "Art-VNS", "V-AMP-2P", "V-APP-GMP", "V-M-2S", "PPro-AF2S", "Adj-DMP", "V-ANM/P", "V-RPM/P-DMP", "RelPro-NNP", "V-FIP-1S", "PPro-D2P", "V-APA-AFS", "PPro-N2P", "V-PIP-1S", "N-GFS", "IPro-NMS", "V-AIM-3P", "Art-VFS", "V-AOP-3S", "V-APA-AMP", "V-PSM/P-3P", "V-PPA-GFP", "RefPro-AF3S", "RelPro-NNS", "Art-DMS", "Adj-ANS-C", "Adj-GMP-C", "Adj-GNS-S", "V-PPM/P-AFS", "Indec", "Adj-VMS", "Adj-GFS-C", "DPro-DMS", "IPro-GFS", "V-AOA-3S", "RefPro-GN3P", "V-APA-GMS", "N-GFP", "V-APA-NFP", "PPro-G1S", "V-APA-NNP", "Adj-ANP", "PPro-GN3P", "N-NMS", "V-PPM-GNP", "V-RPA-DMP", "V-ANP", "V-IIM/P-2S", "DPro-NFS", "V-RPM/P-VFS", "Adj-GFP-S", "V-PPM/P-DFS", "V-IIA-1P", "N-AMP", "V-PMA-2S", "V-PPM/P-GFS", "V-ANA", "V-RNM/P", "V-PPA-AMP", "Adj-NNS", "PPro-DM2P", "V-PIA-1P", "PPro-GF3P", "V-PPA-VFS", "V-PIM/P-1S", "V-PPA-ANS", "PPro-GF3S", "V-FIA-2S", "V-APM-AFS", "Adj-DMS", "IPro-DMP", "Adj-DFP-C", "Art-GNP", "V-PSM/P-2S", "V-ASP-1S", "Adj-AFS-S", "V-AIP-3P", "DPro-NFP", "N-GMP", "PPro-DM2S", "V-RPA-NFP", "V-RPA-GFS", "V-PPM-AMS", "V-AIP-2P", "V-APP-NNS", "Art-GNS", "PPro-GF1P", "Adj-DFS", "V-AIP-3S", "V-PMP-3S", "V-PMP-2P", "V-RPM/P-DMS", "Adj-GMP", "V-PPM-DMP", "V-PNP", "PPro-NM1S", "V-ASP-3P", "Adj-DFS-S", "V-PSA-1P", "Art-VFP", "DPro-GNS", "RelPro-GFS", "Adj-GNP", "Adv-S", "V-FIM-1P", "V-PIM/P-2P", "V-AMM-2S", "V-PMM/P-3S", "V-APM-GFP", "V-APM-DNP", "V-AIA-2P", "V-RPA-NNS", "V-PPA-GNS", "V-PPA-DNS", "V-APP-DFS", "V-PPM/P-DMS", "Adj-GMS", "PPro-N2S", "DPro-DFP", "V-PPA-GMS", "PPro-AF1S", "V-ASM-3P", "N-ANS", "V-PIM/P-3S", "RelPro-AFS", "V-PIM-3P", "V-PPP-GMS", "PPro-DF2P", "V-APM-NFP", "V-PPM-NMS", "PPro-DM1P", "PPro-NF2P", "PPro-NM1P", "RelPro-AMP", "RefPro-DF3P", "N-GNP", "PPro-GN3S", "V-APM-ANP", "V-RMM/P-2P", "V-PPM-AMP", "N-DNS", "IPro-NFP", "V-ASP-2P", "PPro-AF3S", "N-VNP", "V-RPA-GMP", "V-IIA-2P", "V-PPM-NMP", "PPro-NN2S", "V-RPA-GMS", "RefPro-DM3P", "V-ASM-1P", "PPro-NN1P", "V-RPM/P-AMP", "PPro-DN3S", "PPro-DM3S", "RecPro-DMP", "V-AMA-2P", "PPro-NN3S", "V-APM-GNS", "V-PPM-NFP", "V-RPM/P-DFS", "N-DFP", "RelPro-DNS", "PPro-NM3P", "Adj-VFS", "V-ASM-1S", "V-PPM/P-DMP", "V-AIA-1P", "V-APM/P-NMS", "V-RPA-NMS", "N-VFS", "V-IIA-2S", "V-APM-GMS", "V-ASM-2P", "Prep", "PPro-AM1P", "V-APA-NFS", "V-RPM-NMP", "IPro-GFP", "Adj-NFP-S", "V-PPA-DFP", "V-AIP-2S", "IPro-AFS", "PPro-NFS", "V-APP-GMS", "V-IIA-3P", "PPro-AN3S", "V-ASM-2S", "V-FIP-1P", "V-RPM/P-NFP", "Art-NFS", "V-APP-GNP", "DPro-DNS", "PPro-DM1S", "RelPro-DMP", "N-NFP", "V-RIP-1P", "V-RPM/P-GFS", "V-PSA-1S", "V-AOA-3P", "V-RIM/P-1S", "Adj-VNP", "Art-GFS", "V-RPM/P-ANS", "PPro-DF1P", "PPro-NF3S", "Adj-VMS-S", "V-APA-NMS", "RefPro-GM3P", "N-GMS", "DPro-NMS", "Adj", "V-RPM/P-GMS", "V-PPA-NNP", "V-APP-ANP", "V-RPM-NMS", "V-PPA-VMS", "DPro-ANP", "V-PIP-3S", "V-RPA-NNP", "V-PNM", "Art-VMS", "V-RPM/P-DFP", "PPro-A1P", "DPro-AMP", "V-RPM/P-ANP", "Adj-DNS-C", "N-VNS", "V-PPM/P-NMS", "V-PPM/P-NNS", "PPro-A2P", "V-FIP-3P", "PPro-GM3S", "PPro-DF2S", "V-ASP-2S", "V-IIP-3P", "V-PPA-DNP", "V-PIM-1P", "V-RPM/P-GNP", "Adj-AMS-C", "PPro-AN2S", "N-AFP", "RefPro-AN3P", "Adj-ANS-S", "Adj-NFS-C", "V-RPA-DMS", "V-AMP-2S", "IPro-DFS", "V-RSA-2P", "V-APM-DMP", "Adj-GFS", "V-APM-AMP", "V-RPM/P-NMS", "DPro-GMS", "V-RPM/P-NNP", "N-VMS", "Adj-DMP-C", "V-APA-GNS", "V-PPM/P-GNS", "V-FIA-1P", "V-ANM", "V-APP-DNS", "V-RIA-1P", "V-FIP-2P", "V-RPA-GNP", "V-RSA-1S", "RefPro-DM3S", "V-AMP-3S", "V-IIM/P-3S", "V-RPA-NFS", "V-PPA-NFS", "RefPro-GN3S", "RecPro-GMP", "PPro-AM3P", "V-PSM/P-1S", "V-APA-NMP", "PPro-DN3P", "V-APP-DMS", "V-APP-ANS", "V-PPA-GNP", "V-IIM-1S", "V-PPM-NNS", "PPro-AM1S", "PPro-DN1P", "V-PPM/P-GMP", "IPro-DMS", "DPro-NNS", "PPro-AF2P", "Adj-GMS-S", "PPro-NF1S", "V-AOM-1S", "V-AMP-3P", "V-APA-ANS", "V-RPA-ANP", "V-RPA-DNS", "V-RPM/P-DNP", "DPro-ANS", "V-IIM-3P", "RelPro-NMP", "V-PSM/P-3S", "Art-DNS", "Adj-NMS-S", "V-PPA-NMP", "DPro-AFS", "V-RPA-NMP", "V-RIM/P-2P", "N-DMS", "PPro-DF3S", "RelPro-DMS", "RelPro-NFP", "V-PIM/P-2S", "PPro-GM2S", "V-AMM-2P", "N-ANP", "V-PIM/P-1P", "N-NNS", "V-PIA-3P", "V-LIA-1S", "V-RPM/P-AFS", "RelPro-DFS", "DPro-GFP", "Prtcl", "V-PPM/P-GMS", "RelPro-NFS", "V-POA-3S", "N-VFP", "V-RPA-AMP", "PPro-AM2P", "V-RPM/P-NFS", "Adj-AFS-C", "IPro-GMP", "V-PPP-DMP", "V-APA-DMS", "N", "V-APP-NFP", "V-RPA-ANS", "V-PPP-NMP", "V-APA-AMS", "V-PPM/P-NMP", "V-PPM-AFS", "V-FIP-3S", "V-AMA-3S", "DPro-NMP", "V-RPM/P-GFP", "V-IIP-1P", "V-AIM-1S", "Adj-NFS-S", "V-FIM-3P", "PPro-GM3P", "V-PPM/P-DNS", "Adj-NFP-C", "V-FIM-1S", "V-PPP-GMP", "Art-VMP", "V-ASA-2P", "Adj-DNP-S", "V-AIP-1S", "N-DNP", "V-PPA-NFP", "V-FIP-2S", "V-POA-2P", "V-PPA-NMS", "PPro-N1P", "RefPro-AM3P", "V-APP-NNP", "Adj-AMP", "Adj-AMP-C", "V-PPM/P-ANP", "PPro-NM2P", "DPro-AMS", "V-M-2P", "V-APP-NFS", "N-AMS", "V-APM-NMP", "V-POM/P-3P", "Adv", "V-FNM", "V-APA-DFS", "IPro-AMP", "V-APA-GFS", "V-APP-AMS", "V-IIM-2S", "V-PNA", "V-PPM/P-DNP", "Adj-DMS-C", "PPro-GF2S", "V-PPM/P-AMS", "V-ASM-3S", "V-APA-DMP", "V-RPA-AMS", "V-PPM-DMS", "Art-NMP", "V-PMA-3P", "N-DFS", "V-APM-AMS", "Art-DNP", "V-PIM/P-3P", "V-PIM-1S", "Adj-NMS-C", "PPro-NM2S", "V-AMA-2S", "IPro-NNS", "PPro-G2P", "Adj-NNP", "IPro-ANS", "V-IIM/P-3P", "Art-DFS", "PPro-D1S", "V-PPA-AFS", "PPro-A2S", "V-PPM/P-GNP", "V-ASA-1S", "V-APP-NMS", "V-RNA", "V-PMM/P-2S", "V-PSM-2S", "V-PPA-GMP", "N-AFS", "PPro-NN2P", "RelPro-GMP", "V-APP-GFP", "V-LIA-2S", "Art-DFP", "V-APP-NMP", "Art-NFP", "V-AIA-3P", "V-AIP-1P", "V-APM-NFS", "V-RIM-3S", "RefPro-AM3S", "V-APA-GMP", "Adj-GNP-S", "PPro-AN2P", "N-VMP", "PPro-DF1S", "V-RPM/P-AFP", "V-RIM/P-2S", "V-AMM-3S", "V-IIM-1P", "V-PSA-2P", "Adj-NMP", "PPro-GM1S", "V-PIA-1S", "V-PPM/P-NNP", "V-AOM-3S", "V-LIM-3P", "V-PPM-ANS", "RelPro-DFP", "V-PSM-1P", "V-PPM/P-GFP", "V-PSA-2S", "Adj-NMS", "RelPro-GFP", "V-APA-DFP", "PPro-AM3S", "DPro-GMP", "V-APM-GFS", "DPro-AFP", "Adj-NNP-C", "Adj-DFS-C", "DPro-DNP", "V-RPM/P-GMP", "V-FPM-ANS", "Art-GMP", "V-AIM-3S", "V-PPA-ANP", "V-PPA-DMP", "V-PPM-GFP", "RelPro-GMS", "RelPro-AMS", "V-PPM/P-AFP", "V-LIA-3S", "V-IIM-3S", "RecPro-DNP", "V-PMM/P-3P", "V-IIA-1S", "V-PPM-GMP", "V-PPA-DFS", "V-PPM/P-VMP", "V-PPA-GFS", "V-RIA-3S", "V-PSA-3P", "V-FPA-NMP", "V-PPM/P-NFP", "V-PSA-3S", "V-PIA-3S", "V-APM/P-ANP", "V-APA-AFP", "V-RIM-2S", "V-PMA-2P", "V-RPM/P-NNS", "V-APM/P-GFS", "RelPro-NMS", "Art-AMS", "N-NFS", "V-RIM/P-3P", "Adj-AFP-C", "Art-ANP", "PPro-GN1P", "V-AIM-1P", "PPro-D1P", "Art-GMS", "V-AMM-3P", "IPro-NMP", "V-AIA-3S", "IPro-ANP", "V-PIA-2S", "Art-ANS", "RefPro-DF3S", "V-ASA-3S", "V-PIM-3S", "V-RMA-2P", "Adj-VMP-C", "PPro-NN1S", "V-APP-AMP", "Adj-AMS", "V-PPM/P-NFS", "V-PMA-3S", "PPro-D2S", "V-PPM/P-DFP", "PPro-AN3P", "IPro-NNP", "PPro-DM3P", "N-DMP", "RefPro-GM3S", "V-PMM-2P", "V-PPM-GNS", "V-LIA-3P", "N-NNP", "V-ASA-1P", "PPro-G2S", "V-APM-NMS", "Adj-GNP-C", "IPro-AFP", "PPro-NM3S", "V-PPM/P-AMP", "V-APA-NNS", "V-RIM/P-3S", "V-RSA-2S", "V-RPM/P-GNS", "V-RIA-2S", "V-RPM/P-DNS", "V-LIA-2P", "V-RIA-1S", "V-PSM/P-1P", "PPro-AN1S", "Adj-ANS", "Adj-NNS-C", "V-POM/P-1S", "V-APM-NNS", "V-PSM-3S", "Adj-AFS", "V-RSA-1P", "V-RPM-AMS", "V-APM-GNP", "V-FIM/P-2P", "Adj-ANP-C", "Heb", "V-PIA-2P", "Art-AFS", "V-PPM-GMS", "V-RPA-AFS", "V-FIM-2P", "V-FIA-3P", "V-RIA-3P", "RelPro-GNP", "Adj-NFS"]}
|
|
|
|
| 1 |
+
{"morph_encodings": {"<pad>": 0, "<eos>": 1, "<unk>": 2, "<extra_id_0>": 3, "IPro-NNP": 4, "V-PPA-AMP": 5, "PPro-DN1S": 6, "Art-VFS": 7, "Adj-ANP-C": 8, "V-APM-GMS": 9, "N-NFP": 10, "PPro-DF2S": 11, "V-APM-AMS": 12, "V-PPA-AMS": 13, "V-PSA-3S": 14, "PPro-AN3S": 15, "V-FIA-1P": 16, "IPro-ANS": 17, "V-PPA-GFP": 18, "V-RMM/P-2P": 19, "V-PPM/P-NFP": 20, "N-DNS": 21, "Adj-NMP": 22, "V-AIP-3P": 23, "V-RNA": 24, "Adj-DNS-C": 25, "V-ASM-2S": 26, "Art-ANS": 27, "V-FIP-2P": 28, "V-APA-NMP": 29, "V-IIM-2S": 30, "V-PPM-GNP": 31, "V-RPM/P-GNP": 32, "V-PMM/P-3S": 33, "IPro-GNS": 34, "V-PNM": 35, "N-NNP": 36, "V-FIP-2S": 37, "Art-AFP": 38, "RelPro-GNP": 39, "N-GFS": 40, "V-APM-DNP": 41, "V-RPM/P-GMP": 42, "V-RIM/P-2S": 43, "V-APM/P-GFS": 44, "RelPro-DMP": 45, "Adj-DMS-C": 46, "V-RPM/P-DFS": 47, "V-PPM-NMP": 48, "V-AMM-3P": 49, "Art-AMS": 50, "Adj-AMP": 51, "RelPro-GFP": 52, "IPro-NFS": 53, "RefPro-DM3S": 54, "Adj-VNP": 55, "V-AIP-2P": 56, "Adj-NNP-C": 57, "V-RPM/P-AFS": 58, "V-M-2S": 59, "Adj-AFP": 60, "Art-AFS": 61, "N-GMP": 62, "IPro-NMP": 63, "Adj-NMP-C": 64, "V-APM-GFP": 65, "Adj-DMP-C": 66, "Indec": 67, "V-ASP-1P": 68, "V-FPA-NMS": 69, "Prtcl": 70, "DPro-GMP": 71, "V-PPM-ANS": 72, "V-PPP-GMP": 73, "V-PPA-NFP": 74, "V-IIM-1P": 75, "IPro-DMP": 76, "V-AIA-3S": 77, "N-ANP": 78, "Art-DNS": 79, "V-APA-GMS": 80, "V-APM-GFS": 81, "PPro-AN1S": 82, "V-RNM/P": 83, "RelPro-GNS": 84, "IPro-AFS": 85, "PPro-DM3S": 86, "V-RPA-GMP": 87, "V-RPM-NMS": 88, "V-AOA-3P": 89, "V-RPA-DMP": 90, "V-RPM/P-DFP": 91, "PPro-G1S": 92, "V-PIA-2S": 93, "V-RIP-1P": 94, "V-IIP-1P": 95, "V-APP-GMS": 96, "V-PPM/P-DFP": 97, "V-APA-NFS": 98, "RelPro-AMS": 99, "V-PIA-2P": 100, "V-PPA-DMP": 101, "V-PPM/P-NMP": 102, "PPro-G2S": 103, "V-AMP-2P": 104, "V-AIM-3P": 105, "Art-DFP": 106, "PPro-AM1S": 107, "V-IIM/P-1S": 108, "PPro-AM3S": 109, "PPro-GM1S": 110, "PPro-AN2P": 111, "V-ASM-2P": 112, "RelPro-AFP": 113, "Art-GMS": 114, "N-GMS": 115, "Adj-VMS": 116, "Art-DMS": 117, "V-ASP-1S": 118, "V-AMM-3S": 119, "V-PSM-1S": 120, "V-RPA-ANP": 121, "V-APP-DNP": 122, "V-POM/P-3S": 123, "IPro-GMP": 124, "V-APP-NMP": 125, "Adj-NMS-C": 126, "PPro-AM1P": 127, "V-APA-ANP": 128, "Adj-DMP": 129, "V-AIM-1S": 130, "RefPro-DM3P": 131, "V-PSM/P-3S": 132, "Adj-AFP-C": 133, "PPro-AF2P": 134, "RelPro-GFS": 135, "N-AFS": 136, "Adj-GMP": 137, "V-PIM-2P": 138, "V-AIA-2S": 139, "V-APA-GNS": 140, "V-PPA-NMS": 141, "V-PIM/P-2S": 142, "Adj-ANS-C": 143, "V-RPM/P-VFS": 144, "RefPro-GM3S": 145, "Adj-DFS-C": 146, "PPro-A1S": 147, "V-RPA-DNS": 148, "V-PPM-GFP": 149, "V-IIM/P-2S": 150, "PPro-GM3S": 151, "V-ASA-1S": 152, "N-NMP": 153, "N-AMS": 154, "PPro-DM1P": 155, "IPro-ANP": 156, "IPro-AFP": 157, "Adj-DNS": 158, "V-APA-AFP": 159, "Adj-AMP-C": 160, "V-AIM-2S": 161, "V-APP-DMS": 162, "V-PNM/P": 163, "N-GFP": 164, "V-PMA-3P": 165, "Adj-VMP": 166, "V-PIA-1S": 167, "V-IIA-3S": 168, "DPro-NMP": 169, "Art-NMS": 170, "V-AMA-2S": 171, "Adj-GMS-C": 172, "V-PPM-DMS": 173, "Adj-NNS": 174, "V-PPM/P-DNP": 175, "V-ANA": 176, "V-FIP-1P": 177, "PPro-NM1S": 178, "PPro-N2P": 179, "V-AOM-1S": 180, "V-PIM-3P": 181, "Art-ANP": 182, "Art-GNP": 183, "IPro-GNP": 184, "V-PSA-1P": 185, "V-AIA-1S": 186, "V-PPA-GMP": 187, "V-PPM/P-DMP": 188, "RelPro-DNS": 189, "Art-DNP": 190, "IPro-DNS": 191, "IPro-DFS": 192, "V-LIM/P-3S": 193, "V-FIP-3P": 194, "V-PPA-DNP": 195, "Adj-DFS": 196, "V-RPA-GNP": 197, "V-APA-NFP": 198, "Adj-GMP-C": 199, "V-ASA-2S": 200, "RecPro-AMP": 201, "V-RIM/P-3P": 202, "RefPro-GF3S": 203, "V-PIM-3S": 204, "DPro-GFP": 205, "V-RPA-NFS": 206, "PPro-AN3P": 207, "RelPro-AMP": 208, "RefPro-AM3P": 209, "PPro-DF2P": 210, "N-DNP": 211, "V-LIM-3P": 212, "V-RIM/P-1S": 213, "V-APM-AFS": 214, "V-PNP": 215, "V-APP-NNS": 216, "V-FIP-1S": 217, "V-IIM/P-3P": 218, "V-APP-ANS": 219, "V-PPM/P-GFP": 220, "V-RPM/P-AFP": 221, "V-LIA-2P": 222, "V-AMA-3P": 223, "V-PPM/P-DNS": 224, "PPro-GF2P": 225, "RefPro-AN3P": 226, "V-AIP-3S": 227, "PPro-NF3S": 228, "V-PSA-2S": 229, "DPro-DFP": 230, "Adj-NMS": 231, "V-FIA-2S": 232, "PPro-D1P": 233, "DPro-NFP": 234, "V-RPA-GMS": 235, "V-PMM/P-3P": 236, "V-APA-GFS": 237, "V-PSA-1S": 238, "Art-VMS": 239, "Adj-ANP-S": 240, "DPro-AMS": 241, "DPro-AFS": 242, "DPro-GFS": 243, "V-AIP-1P": 244, "Adj-DMS": 245, "V-APP-AFS": 246, "V-AOP-3S": 247, "V-PPA-GMS": 248, "DPro-DMP": 249, "V-AOM-3S": 250, "V-AIP-2S": 251, "V-APA-ANS": 252, "PPro-NFS": 253, "V-APM-GNP": 254, "V-PIM/P-1S": 255, "PPro-GN3S": 256, "V-RPA-AFS": 257, "Adv-C": 258, "PPro-GM3P": 259, "Adj-NNP": 260, "V-APP-GMP": 261, "V-FIM-3S": 262, "V-RIM-2S": 263, "V-ASP-2S": 264, "V-FPP-GNP": 265, "V-AIM-1P": 266, "DPro-NMS": 267, "V-APM-DMP": 268, "Adj-DNS-S": 269, "RelPro-DMS": 270, "Adj-GNS-S": 271, "Art-DMP": 272, "V-APA-NNS": 273, "V-APP-DNS": 274, "V-APP-ANP": 275, "V-FIP-3S": 276, "V-APA-NNP": 277, "Adj-VFS": 278, "PPro-DF3S": 279, "V-RPM/P-NFP": 280, "I": 281, "RefPro-GN3P": 282, "Adj-GNS": 283, "DPro-DFS": 284, "PPro-NM3S": 285, "PPro-AF1S": 286, "V-AMP-3P": 287, "DPro-NNS": 288, "V-PPA-DFP": 289, "DPro-GMS": 290, "V-PSM-3S": 291, "V-IIM-3P": 292, "V-PMP-2P": 293, "RelPro-NMS": 294, "Art-GFP": 295, "V-IIM/P-3S": 296, "PPro-NM1P": 297, "V-RIM/P-1P": 298, "PPro-GF1S": 299, "V-PMM-2S": 300, "V-PPM-AFS": 301, "Adj-AFS": 302, "IPro-AMS": 303, "V-APM-NFP": 304, "V-PPM-NMS": 305, "V-APP-NFS": 306, "V-RSA-1P": 307, "Adj": 308, "PPro-AN2S": 309, "Art-GNS": 310, "Adj-GMS": 311, "V-PPA-DFS": 312, "V-PPA-ANS": 313, "Adj-DMS-S": 314, "V-APA-DMP": 315, "V-RPM/P-DNP": 316, "V-LIM-3S": 317, "V-RMM/P-2S": 318, "PPro-A2S": 319, "V-PMA-2S": 320, "RelPro-NFP": 321, "V-PPA-NNP": 322, "V-APM-GNS": 323, "Art-GMP": 324, "PPro-NM3P": 325, "V-PPA-GFS": 326, "V-PPM-NFS": 327, "Art-VNS": 328, "PPro-GN1P": 329, "Adj-DFP": 330, "V-APA-GMP": 331, "Adj-GNP-S": 332, "V-APM-ANP": 333, "V-RIM/P-2P": 334, "DPro-ANS": 335, "Art-GFS": 336, "V-PMP-3S": 337, "V-PSA-3P": 338, "V-IIA-3P": 339, "V-PPM-AMP": 340, "IPro-NFP": 341, "V-IIM/P-1P": 342, "PPro-DF3P": 343, "V-PSA-2P": 344, "V-PPM-GMS": 345, "V-APM-NMP": 346, "V-PPM-DMP": 347, "V-IIM-3S": 348, "N-GNP": 349, "Adv": 350, "V-AOA-3S": 351, "V-RPM-NMP": 352, "V-PPM-NFP": 353, "V-APP-NFP": 354, "V-FIM-3P": 355, "Adj-NFS-S": 356, "V-ASA-2P": 357, "DPro-GNS": 358, "V-PIP-3S": 359, "V-AMA-2P": 360, "V-RPM/P-NNP": 361, "Adj-AFS-S": 362, "DPro-AMP": 363, "PPro-GF2S": 364, "N-GNS": 365, "V-ANM": 366, "V-PIM-1S": 367, "RecPro-DMP": 368, "V-PPM-GFS": 369, "RefPro-GM3P": 370, "Adj-VMP-C": 371, "V-IIA-1P": 372, "V-APA-DMS": 373, "Adj-NFS-C": 374, "V-PPA-ANP": 375, "V-AIP-1S": 376, "V-FIA-3P": 377, "V-APM-AMP": 378, "V-PMM/P-2P": 379, "Adj-ANS": 380, "V-PPA-NNS": 381, "V-APP-AMS": 382, "RefPro-DF3P": 383, "V-PIM/P-3S": 384, "N-DFS": 385, "PPro-D1S": 386, "V-IIA-2P": 387, "V-RMA-2P": 388, "V-AIM-3S": 389, "RefPro-AF3S": 390, "V-PNA": 391, "V-RPA-NMS": 392, "PPro-DM3P": 393, "V-APP-DFS": 394, "V-PPM/P-GMS": 395, "V-RIA-1P": 396, "RecPro-DNP": 397, "Adj-GFP-S": 398, "RelPro-NNS": 399, "V-PPM/P-VMP": 400, "V-PIM-1P": 401, "IPro-GMS": 402, "V-RPM/P-DMS": 403, "V-IIA-2S": 404, "V-AIA-1P": 405, "V-FPA-NMP": 406, "V-ASP-3P": 407, "Adj-AFS-C": 408, "PPro-GF3P": 409, "V-ASM-1P": 410, "V-PPM/P-AFP": 411, "PPro-NN2S": 412, "IPro-AMP": 413, "V-RPM/P-VMP": 414, "PPro-GF1P": 415, "PPro-NN1S": 416, "V-AMP-2S": 417, "PPro-N1P": 418, "V-POM/P-3P": 419, "V-RPM/P-ANS": 420, "N-DMP": 421, "N": 422, "V-PPM/P-NFS": 423, "V-PMM-2P": 424, "V-APM/P-NMS": 425, "N-VFP": 426, "V-PPM/P-NMS": 427, "PPro-GF3S": 428, "V-RIM/P-3S": 429, "Adj-NFP": 430, "V-ASP-2P": 431, "V-IIA-1S": 432, "V-RPM/P-GMS": 433, "V-RPM-AMS": 434, "V-PPM/P-NNS": 435, "PPro-DN1P": 436, "V-RPM/P-NNS": 437, "V-PPA-NMP": 438, "RefPro-GN3S": 439, "V-RSA-1S": 440, "PPro-DM2S": 441, "V-PPA-AFP": 442, "V-FIA-1S": 443, "Art-AMP": 444, "V-PIM/P-1P": 445, "V-APM-GMP": 446, "V-APM-ANS": 447, "V-PMM/P-2S": 448, "Adj-NFP-S": 449, "V-PPA-DNS": 450, "V-ASA-3P": 451, "Art-NFP": 452, "V-PPM/P-ANS": 453, "V-PSM/P-1S": 454, "V-RPA-ANS": 455, "V-PPM/P-GMP": 456, "DPro-GNP": 457, "V-APP-GFP": 458, "V-RPM/P-VMS": 459, "V-ASA-3S": 460, "V-FPA-ANP": 461, "V-ASM-1S": 462, "V-PPM/P-AMS": 463, "N-NFS": 464, "V-PPM/P-VMS": 465, "V-APP-AMP": 466, "V-AMP-3S": 467, "Adv-S": 468, "RelPro-DFS": 469, "V-PPM/P-GFS": 470, "V-PPM/P-NNP": 471, "RelPro-ANS": 472, "Adj-NNS-C": 473, "N-VNS": 474, "N-DFP": 475, "V-PPM-GMP": 476, "N-AMP": 477, "V-RPA-AMS": 478, "DPro-DNP": 479, "Prep": 480, "RefPro-AM3S": 481, "V-PPM/P-DMS": 482, "V-ANP": 483, "V-PPA-VMS": 484, "N-NNS": 485, "V-AIA-3P": 486, "V-APA-AFS": 487, "DPro-AFP": 488, "V-FIM-2S": 489, "V-APA-AMS": 490, "Adj-DFS-S": 491, "V-RPA-NNP": 492, "V-APM/P-ANP": 493, "Adj-VNS": 494, "V-PPM/P-DFS": 495, "Adj-GNP-C": 496, "N-AFP": 497, "V-APP-GNS": 498, "RelPro-DNP": 499, "PPro-DF1P": 500, "Art-NFS": 501, "V-LIA-1S": 502, "RelPro-NNP": 503, "V-PSM-1P": 504, "V-ASP-3S": 505, "IPro-GFP": 506, "PPro-AF3P": 507, "V-RPM/P-DNS": 508, "PPro-AF1P": 509, "IPro-DMS": 510, "V-RPM/P-NMP": 511, "PPro-DM2P": 512, "V-APP-GNP": 513, "V-PIA-1P": 514, "V-ASM-3P": 515, "V-AMA-3S": 516, "RelPro-NFS": 517, "V-PPM/P-GNP": 518, "V-POM/P-1S": 519, "N-VFS": 520, "V-POA-2P": 521, "PPro-GM2S": 522, "V-RPA-AMP": 523, "Adj-GMP-S": 524, "PPro-N2S": 525, "V-LIA-3S": 526, "PPro-N1S": 527, "V-AMM-2P": 528, "IPro-NNS": 529, "V-FIM/P-2P": 530, "Adj-AMS": 531, "RelPro-AFS": 532, "PPro-DM1S": 533, "Art-VMP": 534, "PPro-NN1P": 535, "DPro-NNP": 536, "N-VMP": 537, "V-PIA-3S": 538, "V-RIA-1S": 539, "V-RPM/P-NMS": 540, "DPro-DNS": 541, "V-PPM-AMS": 542, "RelPro-GMP": 543, "V-FIA-2P": 544, "N-VMS": 545, "PPro-AN1P": 546, "V-PPP-GMS": 547, "V-PPM-NNS": 548, "RelPro-DFP": 549, "PPro-AM2S": 550, "N-ANS": 551, "PPro-NM2S": 552, "V-RIA-3P": 553, "V-PPA-VFS": 554, "V-RIA-2S": 555, "V-APP-NMS": 556, "V-FIA-3S": 557, "V-PIA-3P": 558, "PPro-DN3P": 559, "N-VNP": 560, "V-RPM/P-AMP": 561, "V-IIP-3P": 562, "Art-VFP": 563, "V-PSM-2S": 564, "V-RPA-NFP": 565, "RelPro-ANP": 566, "V-PSM/P-1P": 567, "PPro-AF2S": 568, "V-RSA-2P": 569, "V-PPM/P-AFS": 570, "Conj": 571, "Adj-ANS-S": 572, "Adj-DNP-S": 573, "PPro-NN3S": 574, "V-RPA-GFS": 575, "V-FIM-1P": 576, "Adj-NFP-C": 577, "V-ANM/P": 578, "PPro-A1P": 579, "V-AIM-2P": 580, "RelPro-GMS": 581, "V-LIA-3P": 582, "Heb": 583, "Adj-GMS-S": 584, "V-RIM-3S": 585, "Adj-GNP": 586, "V-PPM/P-AMP": 587, "V-PSM/P-2P": 588, "V-PSM/P-3P": 589, "IntPrtcl": 590, "V-PPP-DMP": 591, "Art-NNS": 592, "V-APA-DFP": 593, "Art-NNP": 594, "V-PPA-VMP": 595, "Art-VNP": 596, "V-PIM/P-3P": 597, "V-PPA-DMS": 598, "PPro-NF1P": 599, "PPro-NF1S": 600, "V-ASA-1P": 601, "V-APM-NFS": 602, "PPro-G1P": 603, "PPro-NN3P": 604, "V-RPM/P-GFP": 605, "Adj-GFS": 606, "V-APP-NNP": 607, "PPro-AF3S": 608, "IPro-NMS": 609, "V-APM-NNS": 610, "PPro-D2S": 611, "V-RPM/P-NFS": 612, "V-PPA-GNP": 613, "N-NMS": 614, "RelPro-NMP": 615, "RefPro-DF3S": 616, "V-PMA-3S": 617, "PPro-NF2P": 618, "Adj-GFP": 619, "DPro-DMS": 620, "Art-NMP": 621, "V-RPM/P-GFS": 622, "V-IIM-1S": 623, "V-PPM/P-ANP": 624, "V-PSM/P-2S": 625, "V-APA-DFS": 626, "V-RPA-NNS": 627, "V-PPP-NMP": 628, "V-RPM/P-DMP": 629, "PPro-AM2P": 630, "V-PIP-1S": 631, "V-APA-AMP": 632, "V-APP-GFS": 633, "Adj-DNP": 634, "Adj-NMS-S": 635, "PPro-GN3P": 636, "V-POA-3P": 637, "V-PIM/P-2P": 638, "V-PPA-AFS": 639, "PPro-A2P": 640, "RecPro-GMP": 641, "V-RIA-3S": 642, "V-PPM/P-GNS": 643, "V-PPA-GNS": 644, "V-IIM/P-2P": 645, "V-FPM-ANS": 646, "V-APM-NMS": 647, "RefPro-GF3P": 648, "DPro-NFS": 649, "Adj-AMS-C": 650, "PPro-G2P": 651, "PPro-DN3S": 652, "V-RPM/P-AMS": 653, "N-DMS": 654, "Art-DFS": 655, "PPro-NM2P": 656, "V-AIA-2P": 657, "V-RPA-NMP": 658, "V-RPM/P-GNS": 659, "PPro-AM3P": 660, "V-RPA-DMS": 661, "DPro-ANP": 662, "V-PPM-GNS": 663, "V-M-2P": 664, "V-RSA-2S": 665, "Adj-DFP-C": 666, "V-FIM-2P": 667, "V-AMM-2S": 668, "V-RIA-2P": 669, "V-PMA-2P": 670, "V-APA-NMS": 671, "V-PPA-NFS": 672, "RefPro-AF3P": 673, "V-ASM-3S": 674, "PPro-NN2P": 675, "PPro-D2P": 676, "Adj-ANP": 677, "IPro-GFS": 678, "PPro-DF1S": 679, "Adj-VMS-S": 680, "V-RPM/P-ANP": 681, "V-FIM-1S": 682, "V-POA-3S": 683, "V-FNM": 684, "Adj-NFS": 685, "V-LIA-2S": 686, "Adj-GFS-C": 687}, "special_tokens_map": {"pad_token": "<pad>", "eos_token": "<eos>", "unk_token": "<unk>", "block_separator_token": "<extra_id_0>"}, "unique_tags": ["DPro-NNP", "Art-GFP", "I", "Art-NNP", "V-RIA-2P", "V-LIM-3S", "Art-NMS", "V-ASP-1P", "V-FIM-2S", "Adj-DFP", "V-PPA-VMP", "PPro-NF1P", "V-APA-ANP", "Art-DMP", "N-NMP", "IPro-NFS", "IPro-GNS", "V-FIA-3S", "V-PPA-AMS", "IPro-GMS", "Adj-GMP-S", "PPro-GF1S", "V-AIA-1S", "Adj-VNS", "V-PMM-2S", "V-APP-DNP", "IPro-GNP", "V-FIM-3S", "V-AMA-3P", "Adj-ANP-S", "Adj-DNS-S", "PPro-DF3P", "V-RPM/P-VMS", "Adv-C", "V-RPM/P-NMP", "Adj-NMP-C", "V-PPM/P-VMS", "PPro-AF1P", "Adj-AFP", "DPro-GNP", "PPro-DN1S", "Art-AMP", "RelPro-ANP", "V-IIA-3S", "V-RPM/P-VMP", "V-IIM/P-1P", "RefPro-AF3P", "PPro-AM2S", "Art-VNP", "DPro-DMP", "V-POA-3P", "RelPro-AFP", "DPro-GFS", "V-APM-GMP", "V-APM-ANS", "PPro-A1S", "V-IIM/P-2P", "V-PPA-DMS", "V-POM/P-3S", "RecPro-AMP", "V-PPM-GFS", "V-PSM/P-2P", "Conj", "Adj-GNS", "PPro-GF2P", "V-FPP-GNP", "V-PNM/P", "IPro-AMS", "PPro-AN1P", "RefPro-GF3P", "V-AIM-2S", "N-GNS", "PPro-NN3P", "Art-NNS", "V-FIA-3P", "IntPrtcl", "Art-AFP", "V-PPM-NFS", "PPro-AF3P", "V-APP-AFS", "Adj-DNS", "V-AIM-2P", "V-APP-GFS", "V-PSM-1S", "V-RMM/P-2S", "V-AIA-2S", "V-LIM/P-3S", "V-FPA-ANP", "V-FPA-NMS", "Adj-GFP", "V-FIA-2P", "IPro-DNS", "PPro-N1S", "Adj-NFP", "Adj-DNP", "V-PPA-NNS", "RelPro-DNP", "Adj-DMS-S", "V-PMM/P-2P", "V-FIA-1S", "V-APP-GNS", "DPro-DFS", "V-ASP-3S", "V-ASA-3P", "Adj-VMP", "RelPro-ANS", "V-PPA-AFP", "RelPro-GNS", "V-PPM/P-ANS", "V-PIM-2P", "V-RIM/P-1P", "V-ASA-2S", "RefPro-GF3S", "V-RPM/P-AMS", "PPro-G1P", "Adj-GMS-C", "V-IIM/P-1S", "Art-VNS", "V-AMP-2P", "V-APP-GMP", "V-M-2S", "PPro-AF2S", "Adj-DMP", "V-ANM/P", "V-RPM/P-DMP", "RelPro-NNP", "V-FIP-1S", "PPro-D2P", "V-APA-AFS", "PPro-N2P", "V-PIP-1S", "N-GFS", "IPro-NMS", "V-AIM-3P", "Art-VFS", "V-AOP-3S", "V-APA-AMP", "V-PSM/P-3P", "V-PPA-GFP", "RefPro-AF3S", "RelPro-NNS", "Art-DMS", "Adj-ANS-C", "Adj-GMP-C", "Adj-GNS-S", "V-PPM/P-AFS", "Indec", "Adj-VMS", "Adj-GFS-C", "DPro-DMS", "IPro-GFS", "V-AOA-3S", "RefPro-GN3P", "V-APA-GMS", "N-GFP", "V-APA-NFP", "PPro-G1S", "V-APA-NNP", "Adj-ANP", "PPro-GN3P", "N-NMS", "V-PPM-GNP", "V-RPA-DMP", "V-ANP", "V-IIM/P-2S", "DPro-NFS", "V-RPM/P-VFS", "Adj-GFP-S", "V-IIA-1P", "N-AMP", "V-PMA-2S", "V-PPM/P-GFS", "V-ANA", "V-RNM/P", "V-PPA-AMP", "Adj-NNS", "PPro-DM2P", "V-PIA-1P", "PPro-GF3P", "V-PPA-VFS", "V-PIM/P-1S", "V-PPA-ANS", "PPro-GF3S", "V-FIA-2S", "V-APM-AFS", "Adj-DMS", "IPro-DMP", "Adj-DFP-C", "Art-GNP", "V-PSM/P-2S", "V-ASP-1S", "Adj-AFS-S", "V-AIP-3P", "DPro-NFP", "N-GMP", "PPro-DM2S", "V-RPA-NFP", "V-RPA-GFS", "V-PPM-AMS", "V-AIP-2P", "V-APP-NNS", "Art-GNS", "PPro-GF1P", "Adj-DFS", "V-AIP-3S", "V-PMP-3S", "V-PMP-2P", "V-RPM/P-DMS", "Adj-GMP", "V-PPM-DMP", "V-PNP", "PPro-NM1S", "V-ASP-3P", "Adj-DFS-S", "V-PSA-1P", "Art-VFP", "DPro-GNS", "RelPro-GFS", "Adj-GNP", "Adv-S", "V-FIM-1P", "V-PIM/P-2P", "V-AMM-2S", "V-PMM/P-3S", "V-APM-GFP", "V-APM-DNP", "V-AIA-2P", "V-RPA-NNS", "V-PPA-GNS", "V-PPA-DNS", "V-APP-DFS", "V-PPM/P-DMS", "Adj-GMS", "PPro-N2S", "DPro-DFP", "V-PPA-GMS", "PPro-AF1S", "V-ASM-3P", "N-ANS", "V-PIM/P-3S", "RelPro-AFS", "V-PIM-3P", "V-PPP-GMS", "PPro-DF2P", "V-APM-NFP", "V-PPM-NMS", "PPro-DM1P", "PPro-NF2P", "PPro-NM1P", "RelPro-AMP", "RefPro-DF3P", "N-GNP", "PPro-GN3S", "V-APM-ANP", "V-RMM/P-2P", "V-PPM-AMP", "N-DNS", "IPro-NFP", "V-ASP-2P", "PPro-AF3S", "N-VNP", "V-RPA-GMP", "V-IIA-2P", "V-PPM-NMP", "PPro-NN2S", "V-RPA-GMS", "RefPro-DM3P", "V-ASM-1P", "PPro-NN1P", "V-RPM/P-AMP", "PPro-DN3S", "PPro-DM3S", "RecPro-DMP", "V-AMA-2P", "PPro-NN3S", "V-APM-GNS", "V-PPM-NFP", "V-RPM/P-DFS", "N-DFP", "RelPro-DNS", "PPro-NM3P", "Adj-VFS", "V-ASM-1S", "V-PPM/P-DMP", "V-AIA-1P", "V-APM/P-NMS", "V-RPA-NMS", "N-VFS", "V-IIA-2S", "V-APM-GMS", "V-ASM-2P", "Prep", "PPro-AM1P", "V-APA-NFS", "V-RPM-NMP", "IPro-GFP", "Adj-NFP-S", "V-PPA-DFP", "V-AIP-2S", "IPro-AFS", "PPro-NFS", "V-APP-GMS", "V-IIA-3P", "PPro-AN3S", "V-ASM-2S", "V-FIP-1P", "V-RPM/P-NFP", "Art-NFS", "V-APP-GNP", "DPro-DNS", "PPro-DM1S", "RelPro-DMP", "N-NFP", "V-RIP-1P", "V-RPM/P-GFS", "V-PSA-1S", "V-AOA-3P", "V-RIM/P-1S", "Adj-VNP", "Art-GFS", "V-RPM/P-ANS", "PPro-DF1P", "PPro-NF3S", "Adj-VMS-S", "V-APA-NMS", "RefPro-GM3P", "N-GMS", "DPro-NMS", "Adj", "V-RPM/P-GMS", "V-PPA-NNP", "V-APP-ANP", "V-RPM-NMS", "V-PPA-VMS", "DPro-ANP", "V-PIP-3S", "V-RPA-NNP", "V-PNM", "Art-VMS", "V-RPM/P-DFP", "PPro-A1P", "DPro-AMP", "V-RPM/P-ANP", "Adj-DNS-C", "N-VNS", "V-PPM/P-NMS", "V-PPM/P-NNS", "PPro-A2P", "V-FIP-3P", "PPro-GM3S", "PPro-DF2S", "V-ASP-2S", "V-IIP-3P", "V-PPA-DNP", "V-PIM-1P", "V-RPM/P-GNP", "Adj-AMS-C", "PPro-AN2S", "N-AFP", "RefPro-AN3P", "Adj-ANS-S", "Adj-NFS-C", "V-RPA-DMS", "V-AMP-2S", "IPro-DFS", "V-RSA-2P", "V-APM-DMP", "Adj-GFS", "V-APM-AMP", "V-RPM/P-NMS", "DPro-GMS", "V-RPM/P-NNP", "N-VMS", "Adj-DMP-C", "V-APA-GNS", "V-PPM/P-GNS", "V-FIA-1P", "V-ANM", "V-APP-DNS", "V-RIA-1P", "V-FIP-2P", "V-RPA-GNP", "V-RSA-1S", "RefPro-DM3S", "V-AMP-3S", "V-IIM/P-3S", "V-RPA-NFS", "V-PPA-NFS", "RefPro-GN3S", "RecPro-GMP", "PPro-AM3P", "V-PSM/P-1S", "V-APA-NMP", "PPro-DN3P", "V-APP-DMS", "V-APP-ANS", "V-PPA-GNP", "V-IIM-1S", "V-PPM-NNS", "PPro-AM1S", "PPro-DN1P", "V-PPM/P-GMP", "IPro-DMS", "DPro-NNS", "PPro-AF2P", "Adj-GMS-S", "PPro-NF1S", "V-AOM-1S", "V-AMP-3P", "V-APA-ANS", "V-RPA-ANP", "V-RPA-DNS", "V-RPM/P-DNP", "DPro-ANS", "V-IIM-3P", "RelPro-NMP", "V-PSM/P-3S", "Art-DNS", "Adj-NMS-S", "V-PPA-NMP", "DPro-AFS", "V-RPA-NMP", "V-RIM/P-2P", "N-DMS", "PPro-DF3S", "RelPro-DMS", "RelPro-NFP", "V-PIM/P-2S", "PPro-GM2S", "V-AMM-2P", "N-ANP", "V-PIM/P-1P", "N-NNS", "V-PIA-3P", "V-LIA-1S", "V-RPM/P-AFS", "RelPro-DFS", "DPro-GFP", "Prtcl", "V-PPM/P-GMS", "RelPro-NFS", "V-POA-3S", "N-VFP", "V-RPA-AMP", "PPro-AM2P", "V-RPM/P-NFS", "Adj-AFS-C", "IPro-GMP", "V-PPP-DMP", "V-APA-DMS", "N", "V-APP-NFP", "V-RPA-ANS", "V-PPP-NMP", "V-APA-AMS", "V-PPM/P-NMP", "V-PPM-AFS", "V-FIP-3S", "V-AMA-3S", "DPro-NMP", "V-RPM/P-GFP", "V-IIP-1P", "V-AIM-1S", "Adj-NFS-S", "V-FIM-3P", "PPro-GM3P", "V-PPM/P-DNS", "Adj-NFP-C", "V-FIM-1S", "V-PPP-GMP", "Art-VMP", "V-ASA-2P", "Adj-DNP-S", "V-AIP-1S", "N-DNP", "V-PPA-NFP", "V-FIP-2S", "V-POA-2P", "V-PPA-NMS", "PPro-N1P", "RefPro-AM3P", "V-APP-NNP", "Adj-AMP", "Adj-AMP-C", "V-PPM/P-ANP", "PPro-NM2P", "DPro-AMS", "V-M-2P", "V-APP-NFS", "N-AMS", "V-APM-NMP", "V-POM/P-3P", "Adv", "V-FNM", "V-APA-DFS", "IPro-AMP", "V-APA-GFS", "V-APP-AMS", "V-IIM-2S", "V-PNA", "V-PPM/P-DNP", "Adj-DMS-C", "PPro-GF2S", "V-PPM/P-AMS", "V-ASM-3S", "V-APA-DMP", "V-RPA-AMS", "V-PPM-DMS", "Art-NMP", "V-PMA-3P", "N-DFS", "V-APM-AMS", "Art-DNP", "V-PIM/P-3P", "V-PIM-1S", "Adj-NMS-C", "PPro-NM2S", "V-AMA-2S", "IPro-NNS", "PPro-G2P", "Adj-NNP", "IPro-ANS", "V-IIM/P-3P", "Art-DFS", "PPro-D1S", "V-PPA-AFS", "PPro-A2S", "V-PPM/P-GNP", "V-ASA-1S", "V-APP-NMS", "V-RNA", "V-PMM/P-2S", "V-PSM-2S", "V-PPA-GMP", "N-AFS", "PPro-NN2P", "RelPro-GMP", "V-APP-GFP", "V-LIA-2S", "Art-DFP", "V-APP-NMP", "Art-NFP", "V-AIA-3P", "V-AIP-1P", "V-APM-NFS", "V-RIM-3S", "RefPro-AM3S", "V-APA-GMP", "Adj-GNP-S", "PPro-AN2P", "N-VMP", "PPro-DF1S", "V-RPM/P-AFP", "V-RIM/P-2S", "V-AMM-3S", "V-IIM-1P", "V-PSA-2P", "Adj-NMP", "PPro-GM1S", "V-PIA-1S", "V-PPM/P-NNP", "V-AOM-3S", "V-LIM-3P", "V-PPM-ANS", "RelPro-DFP", "V-PSM-1P", "V-PPM/P-GFP", "V-PSA-2S", "Adj-NMS", "RelPro-GFP", "V-APA-DFP", "PPro-AM3S", "DPro-GMP", "V-APM-GFS", "DPro-AFP", "Adj-NNP-C", "Adj-DFS-C", "DPro-DNP", "V-RPM/P-GMP", "V-FPM-ANS", "Art-GMP", "V-AIM-3S", "V-PPA-ANP", "V-PPA-DMP", "V-PPM-GFP", "RelPro-GMS", "RelPro-AMS", "V-PPM/P-AFP", "V-LIA-3S", "V-IIM-3S", "RecPro-DNP", "V-PMM/P-3P", "V-IIA-1S", "V-PPM-GMP", "V-PPA-DFS", "V-PPM/P-VMP", "V-PPA-GFS", "V-RIA-3S", "V-PSA-3P", "V-FPA-NMP", "V-PPM/P-NFP", "V-PSA-3S", "V-PIA-3S", "V-APM/P-ANP", "V-APA-AFP", "V-RIM-2S", "V-PMA-2P", "V-RPM/P-NNS", "V-APM/P-GFS", "RelPro-NMS", "Art-AMS", "N-NFS", "V-RIM/P-3P", "Adj-AFP-C", "Art-ANP", "PPro-GN1P", "V-AIM-1P", "PPro-D1P", "Art-GMS", "V-AMM-3P", "IPro-NMP", "V-AIA-3S", "IPro-ANP", "V-PIA-2S", "Art-ANS", "RefPro-DF3S", "V-ASA-3S", "V-PIM-3S", "V-RMA-2P", "Adj-VMP-C", "PPro-NN1S", "V-APP-AMP", "Adj-AMS", "V-PPM/P-NFS", "V-PMA-3S", "PPro-D2S", "V-PPM/P-DFP", "PPro-AN3P", "IPro-NNP", "PPro-DM3P", "N-DMP", "RefPro-GM3S", "V-PMM-2P", "V-PPM-GNS", "V-LIA-3P", "N-NNP", "V-ASA-1P", "PPro-G2S", "V-APM-NMS", "Adj-GNP-C", "IPro-AFP", "PPro-NM3S", "V-PPM/P-AMP", "V-APA-NNS", "V-RIM/P-3S", "V-RSA-2S", "V-RPM/P-GNS", "V-RIA-2S", "V-RPM/P-DNS", "V-LIA-2P", "V-RIA-1S", "V-PSM/P-1P", "PPro-AN1S", "Adj-ANS", "Adj-NNS-C", "V-POM/P-1S", "V-APM-NNS", "V-PSM-3S", "Adj-AFS", "V-RSA-1P", "V-RPM-AMS", "V-APM-GNP", "V-FIM/P-2P", "Adj-ANP-C", "Heb", "V-PIA-2P", "Art-AFS", "V-PPM-GMS", "V-RPA-AFS", "V-FIM-2P", "V-PPM/P-DFS", "V-RIA-3P", "RelPro-GNP", "Adj-NFS"]}
|
text_tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
text_tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"filename_prefix": "text_tokenizer",
|
| 108 |
+
"legacy": false,
|
| 109 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 110 |
+
"pad_token": "<pad>",
|
| 111 |
+
"tokenizer_class": "T5Tokenizer",
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|