PTB/PDTB files belonging to different genres
Features of these sets that motivate their treatment as separate genres are given in the
above paper.
- essays = wsj_0022, wsj_0039, wsj_0071, wsj_0087, wsj_0108, wsj_0186, wsj_0207, wsj_0239, wsj_0257, wsj_0275, wsj_0282, wsj_0290, wsj_0296, wsj_0339, wsj_0406, wsj_0446, wsj_0447, wsj_0450, wsj_0456, wsj_0550, wsj_0562, wsj_0571, wsj_0596, wsj_0676, wsj_0764, wsj_0765, wsj_0788, wsj_0790, wsj_0794, wsj_0819, wsj_0933, wsj_0937, wsj_0944, wsj_0946, wsj_0972, wsj_0978, wsj_1120, wsj_1131, wsj_1137, wsj_1158, wsj_1163, wsj_1164, wsj_1266, wsj_1272, wsj_1284, wsj_1286, wsj_1315, wsj_1323, wsj_1327, wsj_1388, wsj_1424, wsj_1436, wsj_1450, wsj_1453, wsj_1473, wsj_1504, wsj_1507, wsj_1529, wsj_1562, wsj_1566, wsj_1567, wsj_1568, wsj_1569, wsj_1570, wsj_1572, wsj_1622, wsj_1623, wsj_1631, wsj_1635, wsj_1636, wsj_1649, wsj_1657, wsj_1695, wsj_1737, wsj_1772, wsj_1809, wsj_1831, wsj_1849, wsj_1927, wsj_1936, wsj_1939, wsj_1947, wsj_1970, wsj_1984, wsj_1986, wsj_2017, wsj_2052, wsj_2059, wsj_2064, wsj_2106, wsj_2112, wsj_2144, wsj_2149, wsj_2153, wsj_2222, wsj_2227, wsj_2229, wsj_2343, wsj_2402, wsj_2407, wsj_2412, wsj_2431, wsj_2444
- highlights = wsj_0125, wsj_0137, wsj_0178, wsj_0219, wsj_0231, wsj_0271, wsj_0350, wsj_0374, wsj_0457, wsj_0476, wsj_0493, wsj_0586, wsj_0599, wsj_0602, wsj_0612, wsj_0675, wsj_0704, wsj_0770, wsj_0986, wsj_1001, wsj_1015, wsj_1043, wsj_1118, wsj_1156, wsj_1161, wsj_1187, wsj_1217, wsj_1247, wsj_1312, wsj_1337, wsj_1339, wsj_1364, wsj_1434, wsj_1441, wsj_1505, wsj_1540, wsj_1676, wsj_1723, wsj_1728, wsj_1743, wsj_1755, wsj_1781, wsj_1867, wsj_1876, wsj_1930, wsj_1950, wsj_1957, wsj_1974, wsj_2093, wsj_2230, wsj_2256, wsj_2257, wsj_2380, wsj_2399, wsj_2432
- letters = wsj_0091, wsj_0094, wsj_0095, wsj_0105, wsj_0248, wsj_0266, wsj_0268, wsj_0269, wsj_0360, wsj_0411, wsj_0433, wsj_0508, wsj_0687, wsj_0694, wsj_0710, wsj_0728, wsj_0732, wsj_0747, wsj_0772, wsj_0911, wsj_0957, wsj_0980, wsj_0985, wsj_1092, wsj_1107, wsj_1116, wsj_1253, wsj_1256, wsj_1259, wsj_1262, wsj_1402, wsj_1412, wsj_1416, wsj_1571, wsj_1585, wsj_1588, wsj_1602, wsj_1605, wsj_1632, wsj_1786, wsj_1814, wsj_1935, wsj_2011, wsj_2021, wsj_2029, wsj_2108, wsj_2206, wsj_2301, wsj_2352, wsj_2377
- errata = wsj_0104, wsj_0200, wsj_0211, wsj_0410, wsj_0603,
wsj_0605, wsj_0608, wsj_0611, wsj_0614, wsj_0974, wsj_1070, wsj_1401,
wsj_1417, wsj_1430, wsj_1745, wsj_1747, wsj_1751, wsj_1961, wsj_1964,
wsj_1965, wsj_2139, wsj_2311, wsj_2374
- news = wsj_0001, wsj_0003, wsj_0004, wsj_0005, wsj_0007, wsj_0008, wsj_0009, wsj_0010, wsj_0011, wsj_0012, wsj_0013, wsj_0014, wsj_0015, wsj_0016, wsj_0018, wsj_0019, wsj_0020, wsj_0021, wsj_0023, wsj_0024, wsj_0025, wsj_0026, wsj_0027, wsj_0029, wsj_0031, wsj_0033, wsj_0034, wsj_0035, wsj_0036, wsj_0037, wsj_0038, wsj_0040, wsj_0041, wsj_0043, wsj_0044, wsj_0045, wsj_0046, wsj_0047, wsj_0048, wsj_0049, wsj_0050, wsj_0051, wsj_0052, wsj_0054, wsj_0057, wsj_0059, wsj_0060, wsj_0062, wsj_0063, wsj_0064, wsj_0065, wsj_0066, wsj_0067, wsj_0068, wsj_0069, wsj_0070, wsj_0072, wsj_0073, wsj_0074, wsj_0075, wsj_0076, wsj_0077, wsj_0079, wsj_0080, wsj_0081, wsj_0082, wsj_0083, wsj_0084, wsj_0085, wsj_0086, wsj_0088, wsj_0089, wsj_0090, wsj_0092, wsj_0093, wsj_0096, wsj_0097, wsj_0098, wsj_0100, wsj_0101, wsj_0102, wsj_0103, wsj_0106, wsj_0107, wsj_0109, wsj_0111, wsj_0112, wsj_0113, wsj_0114, wsj_0115, wsj_0116, wsj_0117, wsj_0118, wsj_0119, wsj_0120, wsj_0121, wsj_0122, wsj_0123, wsj_0124, wsj_0126, wsj_0127, wsj_0128, wsj_0129, wsj_0130, wsj_0131, wsj_0132, wsj_0133, wsj_0134, wsj_0135, wsj_0136, wsj_0140, wsj_0141, wsj_0142, wsj_0143, wsj_0144, wsj_0145, wsj_0146, wsj_0147, wsj_0148, wsj_0149, wsj_0150, wsj_0151, wsj_0152, wsj_0153, wsj_0154, wsj_0155, wsj_0156, wsj_0157, wsj_0158, wsj_0159, wsj_0160, wsj_0161, wsj_0162, wsj_0163, wsj_0164, wsj_0165, wsj_0166, wsj_0167, wsj_0168, wsj_0169, wsj_0170, wsj_0171, wsj_0172, wsj_0173, wsj_0174, wsj_0175, wsj_0176, wsj_0177, wsj_0179, wsj_0180, wsj_0181, wsj_0182, wsj_0183, wsj_0184, wsj_0185, wsj_0187, wsj_0188, wsj_0189, wsj_0192, wsj_0194, wsj_0198, wsj_0199, wsj_0201, wsj_0202, wsj_0204, wsj_0208, wsj_0209, wsj_0210, wsj_0213, wsj_0214, wsj_0215, wsj_0216, wsj_0218, wsj_0220, wsj_0221, wsj_0222, wsj_0223, wsj_0224, wsj_0225, wsj_0227, wsj_0228, wsj_0229, wsj_0230, wsj_0232, wsj_0233, wsj_0235, wsj_0236, wsj_0237, wsj_0238, wsj_0240, wsj_0241, wsj_0242, wsj_0243, wsj_0244, wsj_0245, wsj_0246, wsj_0247, wsj_0250, wsj_0251, wsj_0252, wsj_0253, wsj_0254, wsj_0255, wsj_0256, wsj_0258, wsj_0259, wsj_0260, wsj_0261, wsj_0262, wsj_0263, wsj_0264, wsj_0265, wsj_0267, wsj_0270, wsj_0272, wsj_0273, wsj_0274, wsj_0276, wsj_0277, wsj_0278, wsj_0279, wsj_0280, wsj_0281, wsj_0283, wsj_0284, wsj_0286, wsj_0287, wsj_0288, wsj_0289, wsj_0291, wsj_0292, wsj_0293, wsj_0294, wsj_0295, wsj_0297, wsj_0298, wsj_0299, wsj_0300, wsj_0301, wsj_0302, wsj_0303, wsj_0304, wsj_0305, wsj_0306, wsj_0307, wsj_0308, wsj_0309, wsj_0310, wsj_0311, wsj_0313, wsj_0314, wsj_0315, wsj_0316, wsj_0317, wsj_0318, wsj_0319, wsj_0321, wsj_0322, wsj_0323, wsj_0324, wsj_0325, wsj_0326, wsj_0327, wsj_0328, wsj_0329, wsj_0331, wsj_0332, wsj_0333, wsj_0334, wsj_0335, wsj_0336, wsj_0337, wsj_0338, wsj_0340, wsj_0341, wsj_0342, wsj_0343, wsj_0344, wsj_0345, wsj_0346, wsj_0347, wsj_0348, wsj_0349, wsj_0351, wsj_0352, wsj_0353, wsj_0354, wsj_0355, wsj_0356, wsj_0357, wsj_0358, wsj_0359, wsj_0361, wsj_0362, wsj_0363, wsj_0365, wsj_0367, wsj_0368, wsj_0369, wsj_0370, wsj_0371, wsj_0372, wsj_0373, wsj_0375, wsj_0376, wsj_0377, wsj_0378, wsj_0379, wsj_0380, wsj_0400, wsj_0401, wsj_0402, wsj_0404, wsj_0405, wsj_0407, wsj_0408, wsj_0409, wsj_0412, wsj_0413, wsj_0414, wsj_0415, wsj_0416, wsj_0417, wsj_0418, wsj_0419, wsj_0420, wsj_0421, wsj_0422, wsj_0423, wsj_0424, wsj_0426, wsj_0427, wsj_0428, wsj_0429, wsj_0430, wsj_0431, wsj_0434, wsj_0435, wsj_0436, wsj_0437, wsj_0439, wsj_0440, wsj_0441, wsj_0442, wsj_0443, wsj_0444, wsj_0445, wsj_0448, wsj_0449, wsj_0451, wsj_0452, wsj_0453, wsj_0458, wsj_0460, wsj_0461, wsj_0462, wsj_0464, wsj_0465, wsj_0466, wsj_0467, wsj_0469, wsj_0470, wsj_0471, wsj_0472, wsj_0473, wsj_0474, wsj_0475, wsj_0477, wsj_0478, wsj_0479, wsj_0480, wsj_0481, wsj_0482, wsj_0483, wsj_0484, wsj_0485, wsj_0486, wsj_0487, wsj_0488, wsj_0489, wsj_0490, wsj_0491, wsj_0492, wsj_0494, wsj_0495, wsj_0496, wsj_0497, wsj_0498, wsj_0499, wsj_0500, wsj_0501, wsj_0502, wsj_0503, wsj_0504, wsj_0505, wsj_0507, wsj_0509, wsj_0510, wsj_0512, wsj_0514, wsj_0515, wsj_0516, wsj_0518, wsj_0519, wsj_0520, wsj_0521, wsj_0522, wsj_0523, wsj_0524, wsj_0525, wsj_0526, wsj_0527, wsj_0528, wsj_0529, wsj_0530, wsj_0531, wsj_0532, wsj_0533, wsj_0534, wsj_0535, wsj_0536, wsj_0537, wsj_0539, wsj_0540, wsj_0541, wsj_0542, wsj_0544, wsj_0545, wsj_0546, wsj_0547, wsj_0548, wsj_0551, wsj_0552, wsj_0553, wsj_0554, wsj_0556, wsj_0557, wsj_0558, wsj_0559, wsj_0560, wsj_0561, wsj_0563, wsj_0564, wsj_0565, wsj_0566, wsj_0567, wsj_0568, wsj_0569, wsj_0570, wsj_0572, wsj_0573, wsj_0574, wsj_0575, wsj_0576, wsj_0577, wsj_0578, wsj_0579, wsj_0580, wsj_0581, wsj_0582, wsj_0583, wsj_0584, wsj_0585, wsj_0587, wsj_0588, wsj_0589, wsj_0590, wsj_0592, wsj_0593, wsj_0595, wsj_0597, wsj_0598, wsj_0600, wsj_0601, wsj_0604, wsj_0606, wsj_0607, wsj_0609, wsj_0610, wsj_0613, wsj_0615, wsj_0616, wsj_0617, wsj_0618, wsj_0619, wsj_0621, wsj_0622, wsj_0623, wsj_0624, wsj_0625, wsj_0626, wsj_0627, wsj_0628, wsj_0629, wsj_0630, wsj_0631, wsj_0632, wsj_0633, wsj_0634, wsj_0635, wsj_0636, wsj_0637, wsj_0638, wsj_0639, wsj_0640, wsj_0641, wsj_0642, wsj_0643, wsj_0644, wsj_0645, wsj_0646, wsj_0647, wsj_0648, wsj_0649, wsj_0651, wsj_0652, wsj_0653, wsj_0654, wsj_0655, wsj_0656, wsj_0657, wsj_0658, wsj_0659, wsj_0660, wsj_0661, wsj_0662, wsj_0663, wsj_0664, wsj_0665, wsj_0666, wsj_0667, wsj_0668, wsj_0669, wsj_0670, wsj_0671, wsj_0672, wsj_0673, wsj_0674, wsj_0677, wsj_0679, wsj_0680, wsj_0681, wsj_0682, wsj_0683, wsj_0684, wsj_0686, wsj_0688, wsj_0689, wsj_0690, wsj_0692, wsj_0693, wsj_0695, wsj_0697, wsj_0700, wsj_0701, wsj_0702, wsj_0705, wsj_0706, wsj_0708, wsj_0709, wsj_0712, wsj_0713, wsj_0714, wsj_0717, wsj_0718, wsj_0719, wsj_0722, wsj_0723, wsj_0725, wsj_0726, wsj_0727, wsj_0729, wsj_0730, wsj_0731, wsj_0733, wsj_0734, wsj_0735, wsj_0736, wsj_0737, wsj_0738, wsj_0739, wsj_0740, wsj_0741, wsj_0742, wsj_0743, wsj_0744, wsj_0745, wsj_0746, wsj_0748, wsj_0750, wsj_0751, wsj_0752, wsj_0753, wsj_0754, wsj_0755, wsj_0756, wsj_0758, wsj_0759, wsj_0760, wsj_0761, wsj_0762, wsj_0763, wsj_0766, wsj_0767, wsj_0768, wsj_0769, wsj_0771, wsj_0773, wsj_0774, wsj_0775, wsj_0776, wsj_0777, wsj_0778, wsj_0779, wsj_0780, wsj_0781, wsj_0782, wsj_0783, wsj_0784, wsj_0785, wsj_0786, wsj_0787, wsj_0789, wsj_0791, wsj_0792, wsj_0793, wsj_0795, wsj_0796, wsj_0797, wsj_0798, wsj_0799, wsj_0800, wsj_0801, wsj_0802, wsj_0803, wsj_0804, wsj_0805, wsj_0806, wsj_0807, wsj_0808, wsj_0809, wsj_0810, wsj_0811, wsj_0812, wsj_0813, wsj_0814, wsj_0815, wsj_0816, wsj_0817, wsj_0818, wsj_0820, wsj_0900, wsj_0902, wsj_0903, wsj_0904, wsj_0905, wsj_0906, wsj_0907, wsj_0908, wsj_0909, wsj_0910, wsj_0912, wsj_0913, wsj_0914, wsj_0915, wsj_0916, wsj_0917, wsj_0918, wsj_0919, wsj_0922, wsj_0923, wsj_0924, wsj_0925, wsj_0926, wsj_0927, wsj_0928, wsj_0929, wsj_0930, wsj_0931, wsj_0932, wsj_0934, wsj_0935, wsj_0936, wsj_0938, wsj_0939, wsj_0940, wsj_0941, wsj_0942, wsj_0943, wsj_0945, wsj_0948, wsj_0949, wsj_0950, wsj_0952, wsj_0953, wsj_0954, wsj_0955, wsj_0956, wsj_0958, wsj_0959, wsj_0960, wsj_0961, wsj_0962, wsj_0963, wsj_0964, wsj_0965, wsj_0966, wsj_0967, wsj_0968, wsj_0969, wsj_0970, wsj_0971, wsj_0973, wsj_0975, wsj_0976, wsj_0977, wsj_0979, wsj_0981, wsj_0982, wsj_0983, wsj_0984, wsj_0987, wsj_0988, wsj_0989, wsj_0990, wsj_0991, wsj_0992, wsj_0993, wsj_0994, wsj_0995, wsj_0996, wsj_0997, wsj_0999, wsj_1000, wsj_1002, wsj_1003, wsj_1004, wsj_1005, wsj_1006, wsj_1007, wsj_1008, wsj_1010, wsj_1011, wsj_1012, wsj_1013, wsj_1014, wsj_1016, wsj_1017, wsj_1018, wsj_1019, wsj_1020, wsj_1021, wsj_1022, wsj_1023, wsj_1024, wsj_1025, wsj_1026, wsj_1027, wsj_1028, wsj_1029, wsj_1030, wsj_1031, wsj_1032, wsj_1033, wsj_1034, wsj_1035, wsj_1036, wsj_1037, wsj_1038, wsj_1039, wsj_1040, wsj_1041, wsj_1042, wsj_1044, wsj_1045, wsj_1046, wsj_1047, wsj_1048, wsj_1049, wsj_1050, wsj_1051, wsj_1052, wsj_1053, wsj_1055, wsj_1057, wsj_1058, wsj_1059, wsj_1060, wsj_1061, wsj_1062, wsj_1064, wsj_1065, wsj_1066, wsj_1068, wsj_1069, wsj_1071, wsj_1072, wsj_1073, wsj_1074, wsj_1075, wsj_1076, wsj_1078, wsj_1079, wsj_1080, wsj_1081, wsj_1082, wsj_1083, wsj_1084, wsj_1086, wsj_1089, wsj_1091, wsj_1093, wsj_1094, wsj_1095, wsj_1096, wsj_1097, wsj_1099, wsj_1100, wsj_1101, wsj_1102, wsj_1103, wsj_1105, wsj_1106, wsj_1108, wsj_1109, wsj_1110, wsj_1111, wsj_1112, wsj_1113, wsj_1117, wsj_1119, wsj_1121, wsj_1122, wsj_1123, wsj_1124, wsj_1125, wsj_1126, wsj_1127, wsj_1128, wsj_1130, wsj_1132, wsj_1133, wsj_1134, wsj_1135, wsj_1136, wsj_1138, wsj_1139, wsj_1140, wsj_1141, wsj_1142, wsj_1143, wsj_1144, wsj_1145, wsj_1146, wsj_1147, wsj_1148, wsj_1149, wsj_1150, wsj_1151, wsj_1152, wsj_1153, wsj_1154, wsj_1155, wsj_1157, wsj_1159, wsj_1160, wsj_1162, wsj_1165, wsj_1166, wsj_1167, wsj_1168, wsj_1169, wsj_1170, wsj_1171, wsj_1172, wsj_1173, wsj_1174, wsj_1175, wsj_1176, wsj_1177, wsj_1178, wsj_1179, wsj_1180, wsj_1181, wsj_1182, wsj_1183, wsj_1184, wsj_1185, wsj_1186, wsj_1188, wsj_1189, wsj_1190, wsj_1191, wsj_1192, wsj_1193, wsj_1194, wsj_1195, wsj_1196, wsj_1198, wsj_1199, wsj_1200, wsj_1201, wsj_1203, wsj_1204, wsj_1205, wsj_1206, wsj_1207, wsj_1208, wsj_1209, wsj_1210, wsj_1211, wsj_1213, wsj_1214, wsj_1215, wsj_1216, wsj_1218, wsj_1219, wsj_1220, wsj_1221, wsj_1222, wsj_1223, wsj_1224, wsj_1225, wsj_1226, wsj_1227, wsj_1229, wsj_1230, wsj_1231, wsj_1232, wsj_1233, wsj_1234, wsj_1235, wsj_1236, wsj_1237, wsj_1238, wsj_1239, wsj_1241, wsj_1242, wsj_1243, wsj_1244, wsj_1246, wsj_1248, wsj_1249, wsj_1250, wsj_1251, wsj_1254, wsj_1255, wsj_1257, wsj_1258, wsj_1260, wsj_1261, wsj_1263, wsj_1264, wsj_1265, wsj_1267, wsj_1268, wsj_1269, wsj_1270, wsj_1271, wsj_1273, wsj_1274, wsj_1275, wsj_1276, wsj_1278, wsj_1279, wsj_1280, wsj_1281, wsj_1282, wsj_1283, wsj_1285, wsj_1287, wsj_1288, wsj_1289, wsj_1290, wsj_1291, wsj_1292, wsj_1293, wsj_1294, wsj_1295, wsj_1296, wsj_1297, wsj_1298, wsj_1299, wsj_1300, wsj_1301, wsj_1302, wsj_1303, wsj_1304, wsj_1305, wsj_1306, wsj_1307, wsj_1308, wsj_1309, wsj_1310, wsj_1311, wsj_1313, wsj_1314, wsj_1316, wsj_1317, wsj_1318, wsj_1319, wsj_1320, wsj_1321, wsj_1322, wsj_1324, wsj_1325, wsj_1328, wsj_1329, wsj_1330, wsj_1331, wsj_1332, wsj_1333, wsj_1334, wsj_1335, wsj_1336, wsj_1338, wsj_1340, wsj_1341, wsj_1343, wsj_1345, wsj_1346, wsj_1347, wsj_1348, wsj_1349, wsj_1350, wsj_1351, wsj_1352, wsj_1353, wsj_1354, wsj_1355, wsj_1356, wsj_1357, wsj_1358, wsj_1359, wsj_1360, wsj_1361, wsj_1362, wsj_1363, wsj_1365, wsj_1366, wsj_1367, wsj_1368, wsj_1369, wsj_1370, wsj_1371, wsj_1372, wsj_1373, wsj_1374, wsj_1375, wsj_1376, wsj_1377, wsj_1379, wsj_1380, wsj_1381, wsj_1383, wsj_1386, wsj_1387, wsj_1389, wsj_1390, wsj_1391, wsj_1392, wsj_1394, wsj_1395, wsj_1396, wsj_1397, wsj_1399, wsj_1403, wsj_1404, wsj_1405, wsj_1407, wsj_1408, wsj_1409, wsj_1410, wsj_1411, wsj_1413, wsj_1414, wsj_1415, wsj_1418, wsj_1419, wsj_1421, wsj_1422, wsj_1423, wsj_1426, wsj_1428, wsj_1429, wsj_1431, wsj_1432, wsj_1433, wsj_1435, wsj_1437, wsj_1438, wsj_1439, wsj_1440, wsj_1442, wsj_1443, wsj_1445, wsj_1446, wsj_1447, wsj_1448, wsj_1449, wsj_1451, wsj_1452, wsj_1454, wsj_1455, wsj_1456, wsj_1457, wsj_1458, wsj_1459, wsj_1460, wsj_1461, wsj_1462, wsj_1463, wsj_1464, wsj_1465, wsj_1466, wsj_1467, wsj_1468, wsj_1469, wsj_1470, wsj_1471, wsj_1472, wsj_1474, wsj_1475, wsj_1476, wsj_1477, wsj_1478, wsj_1479, wsj_1480, wsj_1481, wsj_1483, wsj_1484, wsj_1485, wsj_1486, wsj_1487, wsj_1488, wsj_1489, wsj_1490, wsj_1491, wsj_1492, wsj_1493, wsj_1494, wsj_1495, wsj_1496, wsj_1497, wsj_1498, wsj_1499, wsj_1500, wsj_1501, wsj_1502, wsj_1503, wsj_1506, wsj_1508, wsj_1509, wsj_1510, wsj_1511, wsj_1512, wsj_1513, wsj_1514, wsj_1515, wsj_1516, wsj_1517, wsj_1518, wsj_1519, wsj_1520, wsj_1521, wsj_1522, wsj_1523, wsj_1524, wsj_1525, wsj_1526, wsj_1527, wsj_1528, wsj_1530, wsj_1531, wsj_1532, wsj_1533, wsj_1534, wsj_1535, wsj_1536, wsj_1537, wsj_1538, wsj_1539, wsj_1541, wsj_1542, wsj_1543, wsj_1544, wsj_1545, wsj_1546, wsj_1547, wsj_1548, wsj_1549, wsj_1550, wsj_1551, wsj_1552, wsj_1553, wsj_1554, wsj_1555, wsj_1556, wsj_1560, wsj_1561, wsj_1563, wsj_1564, wsj_1565, wsj_1573, wsj_1574, wsj_1575, wsj_1577, wsj_1578, wsj_1580, wsj_1581, wsj_1582, wsj_1583, wsj_1584, wsj_1586, wsj_1587, wsj_1589, wsj_1590, wsj_1591, wsj_1592, wsj_1593, wsj_1594, wsj_1595, wsj_1596, wsj_1597, wsj_1598, wsj_1599, wsj_1600, wsj_1601, wsj_1603, wsj_1604, wsj_1606, wsj_1607, wsj_1609, wsj_1610, wsj_1611, wsj_1612, wsj_1613, wsj_1614, wsj_1615, wsj_1616, wsj_1617, wsj_1618, wsj_1619, wsj_1620, wsj_1621, wsj_1624, wsj_1626, wsj_1627, wsj_1628, wsj_1629, wsj_1630, wsj_1633, wsj_1634, wsj_1637, wsj_1639, wsj_1640, wsj_1641, wsj_1642, wsj_1643, wsj_1644, wsj_1645, wsj_1646, wsj_1647, wsj_1648, wsj_1650, wsj_1651, wsj_1652, wsj_1654, wsj_1655, wsj_1656, wsj_1658, wsj_1659, wsj_1660, wsj_1661, wsj_1662, wsj_1663, wsj_1664, wsj_1665, wsj_1666, wsj_1667, wsj_1668, wsj_1669, wsj_1670, wsj_1671, wsj_1672, wsj_1673, wsj_1674, wsj_1675, wsj_1677, wsj_1678, wsj_1679, wsj_1680, wsj_1681, wsj_1682, wsj_1683, wsj_1684, wsj_1685, wsj_1686, wsj_1687, wsj_1688, wsj_1689, wsj_1690, wsj_1691, wsj_1692, wsj_1693, wsj_1694, wsj_1696, wsj_1697, wsj_1698, wsj_1699, wsj_1700, wsj_1701, wsj_1702, wsj_1703, wsj_1704, wsj_1705, wsj_1706, wsj_1707, wsj_1708, wsj_1709, wsj_1710, wsj_1711, wsj_1712, wsj_1713, wsj_1714, wsj_1715, wsj_1717, wsj_1718, wsj_1719, wsj_1720, wsj_1721, wsj_1722, wsj_1724, wsj_1725, wsj_1726, wsj_1727, wsj_1729, wsj_1730, wsj_1731, wsj_1732, wsj_1733, wsj_1734, wsj_1735, wsj_1736, wsj_1738, wsj_1739, wsj_1740, wsj_1741, wsj_1742, wsj_1744, wsj_1746, wsj_1748, wsj_1749, wsj_1750, wsj_1752, wsj_1753, wsj_1754, wsj_1756, wsj_1757, wsj_1759, wsj_1760, wsj_1761, wsj_1762, wsj_1763, wsj_1764, wsj_1765, wsj_1766, wsj_1767, wsj_1768, wsj_1769, wsj_1770, wsj_1773, wsj_1774, wsj_1775, wsj_1776, wsj_1777, wsj_1778, wsj_1779, wsj_1780, wsj_1782, wsj_1783, wsj_1784, wsj_1787, wsj_1788, wsj_1789, wsj_1790, wsj_1791, wsj_1792, wsj_1793, wsj_1794, wsj_1795, wsj_1796, wsj_1797, wsj_1799, wsj_1800, wsj_1802, wsj_1803, wsj_1804, wsj_1806, wsj_1808, wsj_1810, wsj_1811, wsj_1812, wsj_1813, wsj_1815, wsj_1816, wsj_1817, wsj_1818, wsj_1819, wsj_1820, wsj_1821, wsj_1822, wsj_1823, wsj_1824, wsj_1825, wsj_1826, wsj_1827, wsj_1828, wsj_1829, wsj_1830, wsj_1832, wsj_1833, wsj_1835, wsj_1837, wsj_1839, wsj_1840, wsj_1841, wsj_1842, wsj_1843, wsj_1844, wsj_1846, wsj_1847, wsj_1848, wsj_1850, wsj_1851, wsj_1852, wsj_1853, wsj_1854, wsj_1855, wsj_1856, wsj_1857, wsj_1858, wsj_1859, wsj_1860, wsj_1861, wsj_1862, wsj_1863, wsj_1864, wsj_1865, wsj_1866, wsj_1868, wsj_1869, wsj_1870, wsj_1872, wsj_1873, wsj_1874, wsj_1875, wsj_1877, wsj_1878, wsj_1879, wsj_1880, wsj_1881, wsj_1882, wsj_1883, wsj_1884, wsj_1885, wsj_1886, wsj_1887, wsj_1888, wsj_1889, wsj_1890, wsj_1891, wsj_1892, wsj_1893, wsj_1894, wsj_1895, wsj_1896, wsj_1897, wsj_1898, wsj_1899, wsj_1900, wsj_1901, wsj_1902, wsj_1903, wsj_1904, wsj_1905, wsj_1906, wsj_1907, wsj_1908, wsj_1909, wsj_1910, wsj_1911, wsj_1912, wsj_1913, wsj_1914, wsj_1915, wsj_1916, wsj_1917, wsj_1918, wsj_1919, wsj_1920, wsj_1921, wsj_1922, wsj_1923, wsj_1924, wsj_1925, wsj_1926, wsj_1928, wsj_1929, wsj_1931, wsj_1932, wsj_1934, wsj_1937, wsj_1938, wsj_1940, wsj_1943, wsj_1944, wsj_1945, wsj_1946, wsj_1948, wsj_1949, wsj_1951, wsj_1952, wsj_1953, wsj_1959, wsj_1960, wsj_1962, wsj_1963, wsj_1966, wsj_1967, wsj_1968, wsj_1969, wsj_1971, wsj_1972, wsj_1973, wsj_1975, wsj_1976, wsj_1977, wsj_1978, wsj_1980, wsj_1981, wsj_1982, wsj_1983, wsj_1985, wsj_1987, wsj_1988, wsj_1989, wsj_1990, wsj_1991, wsj_1992, wsj_1994, wsj_1996, wsj_1997, wsj_1998, wsj_1999, wsj_2000, wsj_2001, wsj_2002, wsj_2003, wsj_2004, wsj_2005, wsj_2006, wsj_2007, wsj_2008, wsj_2009, wsj_2010, wsj_2012, wsj_2013, wsj_2014, wsj_2015, wsj_2016, wsj_2018, wsj_2019, wsj_2020, wsj_2022, wsj_2023, wsj_2024, wsj_2025, wsj_2026, wsj_2027, wsj_2028, wsj_2030, wsj_2031, wsj_2032, wsj_2033, wsj_2034, wsj_2036, wsj_2037, wsj_2039, wsj_2040, wsj_2041, wsj_2042, wsj_2043, wsj_2044, wsj_2045, wsj_2046, wsj_2047, wsj_2048, wsj_2049, wsj_2051, wsj_2053, wsj_2054, wsj_2055, wsj_2056, wsj_2057, wsj_2058, wsj_2060, wsj_2061, wsj_2062, wsj_2063, wsj_2065, wsj_2066, wsj_2067, wsj_2068, wsj_2069, wsj_2070, wsj_2071, wsj_2072, wsj_2073, wsj_2074, wsj_2075, wsj_2076, wsj_2077, wsj_2078, wsj_2079, wsj_2080, wsj_2081, wsj_2082, wsj_2083, wsj_2084, wsj_2085, wsj_2086, wsj_2087, wsj_2088, wsj_2089, wsj_2091, wsj_2092, wsj_2094, wsj_2095, wsj_2096, wsj_2098, wsj_2099, wsj_2100, wsj_2101, wsj_2102, wsj_2103, wsj_2104, wsj_2105, wsj_2107, wsj_2109, wsj_2110, wsj_2111, wsj_2113, wsj_2115, wsj_2116, wsj_2118, wsj_2119, wsj_2120, wsj_2121, wsj_2123, wsj_2124, wsj_2125, wsj_2126, wsj_2127, wsj_2128, wsj_2129, wsj_2130, wsj_2131, wsj_2132, wsj_2133, wsj_2135, wsj_2136, wsj_2138, wsj_2140, wsj_2141, wsj_2142, wsj_2143, wsj_2145, wsj_2146, wsj_2148, wsj_2150, wsj_2151, wsj_2152, wsj_2154, wsj_2155, wsj_2156, wsj_2157, wsj_2158, wsj_2159, wsj_2160, wsj_2161, wsj_2162, wsj_2163, wsj_2164, wsj_2165, wsj_2166, wsj_2167, wsj_2168, wsj_2169, wsj_2172, wsj_2200, wsj_2201, wsj_2202, wsj_2203, wsj_2204, wsj_2205, wsj_2207, wsj_2208, wsj_2209, wsj_2210, wsj_2211, wsj_2212, wsj_2213, wsj_2214, wsj_2216, wsj_2217, wsj_2218, wsj_2219, wsj_2221, wsj_2223, wsj_2224, wsj_2225, wsj_2226, wsj_2228, wsj_2231, wsj_2232, wsj_2233, wsj_2234, wsj_2235, wsj_2237, wsj_2238, wsj_2239, wsj_2240, wsj_2241, wsj_2242, wsj_2243, wsj_2244, wsj_2245, wsj_2246, wsj_2247, wsj_2248, wsj_2249, wsj_2250, wsj_2251, wsj_2252, wsj_2253, wsj_2254, wsj_2255, wsj_2258, wsj_2259, wsj_2260, wsj_2261, wsj_2262, wsj_2264, wsj_2265, wsj_2266, wsj_2267, wsj_2268, wsj_2269, wsj_2270, wsj_2271, wsj_2272, wsj_2273, wsj_2274, wsj_2275, wsj_2276, wsj_2277, wsj_2278, wsj_2280, wsj_2281, wsj_2282, wsj_2300, wsj_2302, wsj_2303, wsj_2305, wsj_2306, wsj_2308, wsj_2309, wsj_2310, wsj_2313, wsj_2314, wsj_2315, wsj_2316, wsj_2317, wsj_2319, wsj_2320, wsj_2321, wsj_2322, wsj_2323, wsj_2324, wsj_2325, wsj_2326, wsj_2327, wsj_2328, wsj_2329, wsj_2330, wsj_2331, wsj_2332, wsj_2333, wsj_2334, wsj_2335, wsj_2336, wsj_2337, wsj_2338, wsj_2339, wsj_2340, wsj_2341, wsj_2342, wsj_2344, wsj_2345, wsj_2346, wsj_2347, wsj_2348, wsj_2350, wsj_2351, wsj_2353, wsj_2354, wsj_2355, wsj_2356, wsj_2357, wsj_2358, wsj_2359, wsj_2360, wsj_2361, wsj_2362, wsj_2363, wsj_2364, wsj_2365, wsj_2366, wsj_2367, wsj_2368, wsj_2369, wsj_2370, wsj_2371, wsj_2372, wsj_2373, wsj_2375, wsj_2376, wsj_2378, wsj_2379, wsj_2381, wsj_2382, wsj_2383, wsj_2384, wsj_2386, wsj_2387, wsj_2391, wsj_2392, wsj_2393, wsj_2394, wsj_2395, wsj_2396, wsj_2397, wsj_2398, wsj_2400, wsj_2403, wsj_2404, wsj_2405, wsj_2406, wsj_2408, wsj_2409, wsj_2410, wsj_2411, wsj_2413, wsj_2414, wsj_2415, wsj_2416, wsj_2417, wsj_2418, wsj_2419, wsj_2420, wsj_2421, wsj_2422, wsj_2423, wsj_2424, wsj_2425, wsj_2426, wsj_2427, wsj_2428, wsj_2429, wsj_2430, wsj_2433, wsj_2434, wsj_2435, wsj_2436, wsj_2437, wsj_2438, wsj_2439, wsj_2440, wsj_2441, wsj_2442, wsj_2443, wsj_2445, wsj_2446, wsj_2447, wsj_2448, wsj_2449, wsj_2450, wsj_2451, wsj_2452, wsj_2453, wsj_2454
II. Corresponding genre sets based on the meta-data found in ACL/DCI corpus
Modifications/Notes added by Barbara Plank (in red+boldface)
It is well-known that there is no meta-data in the individual files in the Penn
TreeBank Wall Street Journal Corpus. However, meta-data can be found by looking
at corresponding articles in the ACL/DCI
corpus available from the LDC,
in particular in the ACL/DCI Wall Street Journal (wsj) corpus from 1989.
Each article in the corpus has a unique document number (DOCNO).
The alignment between these two corpora is given in a downloadable TAR file
(pennTB_tipster_wsj_map.tar) that appears in the section headed DATA in the
PennTreeBank
entry in the LDC catalogue. Aligned are the PTB filenames and corresponding
WSJ DOCNO strings.
But even here, one will not find an explicit classification of the
articles in the ACL/DCI Wall Street Journal corpus into genres. Rather,
there is meta-data in the headline (HL) and IN fields that are
included for many (but not all) articles. This meta-data can be used in classifying
articles into different genres. I chose to consider the same set of genres as I used
above, but other sub-divisions of the corpus into genres are possible as well.
In the listing below (unlike in the ACL paper), I have split the
PTB/PDTB files that incorrectly contain two adjacent concatenated articles
from the ACL/DCI 1989 WSJ corpus, into two files, a and b. It should
be clear from the original PTB/PDTB file and the ACL/DCI alignment, where that split
should be. (In the above-mentioned TAR file, these errors are listed in
ptb_dual_tip.tbl)
Using the alignment of the PTB corpus with the ACL/DCI 1989 WSJ files
and culling off the meta-data from the HL and IN fields,
one can produce a more accurate classification of PTB/PDTB files into the same set
of genres as above. (However, the above set isn't that far off.)
- Letters, comprising all and only files with HL = Letters to
the Editor:
wsj_0091,
wsj_0094,
wsj_0095,
wsj_0105,
wsj_0248,
wsj_0266,
wsj_0268,
wsj_0269,
wsj_0360,
wsj_0411,
wsj_0433,
wsj_0434,
wsj_0508,
wsj_0576a,
wsj_0687,
wsj_0694,
wsj_0710,
wsj_0728,
wsj_0732,
wsj_0747,
wsj_0772,
wsj_0911,
wsj_0957,
wsj_0980,
wsj_0985,
wsj_0992,
wsj_1092,
wsj_1095,
wsj_1107,
wsj_1116,
wsj_1253,
wsj_1256,
wsj_1260,
wsj_1262,
wsj_1402,
wsj_1412,
wsj_1416,
wsj_1497,
wsj_1529,
wsj_1571,
wsj_1585,
wsj_1588,
wsj_1602,
wsj_1605,
wsj_1632,
wsj_1786,
wsj_1814,
wsj_1935,
wsj_2011,
wsj_2021,
wsj_2029,
wsj_2108,
wsj_2204,
wsj_2206,
wsj_2301,
wsj_2352,
wsj_2368,
wsj_2373,
wsj_2377
- Highlights, compising those files with
- HL = World Markets
- HL = New Securities Issues
- HL = Recent SEC Filings
- HL = Money Rates
wsj_0125,
wsj_0137,
wsj_0219,
wsj_0231,
wsj_0271,
wsj_0374,
wsj_0457,
wsj_0476,
wsj_0586,
wsj_0599,
wsj_0602,
wsj_0612,
wsj_0704,
wsj_0770,
wsj_0986,
wsj_1001,
wsj_1015,
wsj_1118,
wsj_1156b,
wsj_1161,
wsj_1187,
wsj_1247,
wsj_1312,
wsj_1337,
wsj_1339,
wsj_1434,
wsj_1441,
wsj_1505,
wsj_1676,
wsj_1723,
wsj_1743a,
wsj_1781,
wsj_1867,
wsj_1876,
wsj_1950,
wsj_1957,
wsj_1974,
wsj_2230,
wsj_2257,
wsj_2380,
wsj_2399
- Essays, comprising those files with
- HL = LEISURE & ARTS
- HL = Centennial Journal: 100 Years in Business
- IN = BIOGRAPHY (BIO)
- HL = "The Outlook"
- HL = "Politics & Policy"
- HL = "International -- Washington Insight"
- HL = "Business and Urban Crime: Battles Won and Lost"
- HL includes "(Editorial)" or "(Editorial) -- Asides" or "(A Special Report)" or
"Manager's Journal" or "Viewpoint"
wsj_0022, wsj_0037a, wsj_0039, wsj_0041, wsj_0045, wsj_0071, wsj_0103, wsj_0108, wsj_0126, wsj_0130, wsj_0134, wsj_0186, wsj_0207, wsj_0208, wsj_0239, wsj_0257,
wsj_0267,
wsj_0288,
wsj_0303,
wsj_0309,
wsj_0314,
wsj_0339,
wsj_0406,
wsj_0423,
wsj_0426,
wsj_0450,
wsj_0456,
wsj_0458,
wsj_0461,
wsj_0474,
wsj_0526,
wsj_0550,
wsj_0553,
wsj_0561,
wsj_0562,
wsj_0580,
wsj_0590,
wsj_0598,
wsj_0609,
wsj_0623,
wsj_0655,
wsj_0676,
wsj_0765,
wsj_0783,
wsj_0787,
wsj_0790,
wsj_0793,
wsj_0800,
wsj_0808,
wsj_0817,
wsj_0819,
wsj_0820,
wsj_0933,
wsj_0937,
wsj_0955,
wsj_0960,
wsj_0964,
wsj_0966,
wsj_0972,
wsj_0976,
wsj_0984,
wsj_0996,
wsj_1017,
wsj_1034,
wsj_1053,
wsj_1094,
wsj_1143,
wsj_1149,
wsj_1152,
wsj_1154a,
wsj_1158,
wsj_1163,
wsj_1164,
wsj_1189,
wsj_1266,
wsj_1272,
wsj_1303,
wsj_1307,
wsj_1308,
wsj_1315,
wsj_1323,
wsj_1327,
wsj_1349,
wsj_1366,
wsj_1388,
wsj_1389,
wsj_1396,
wsj_1397,
wsj_1405,
wsj_1411,
wsj_1413,
wsj_1436,
wsj_1450,
wsj_1457,
wsj_1473,
wsj_1495,
wsj_1499,
wsj_1504,
wsj_1506,
wsj_1507,
wsj_1520,
wsj_1562,
wsj_1563,
wsj_1564,
wsj_1565,
wsj_1566,
wsj_1567,
wsj_1568,
wsj_1569,
wsj_1570,
wsj_1572,
wsj_1574,
wsj_1618,
wsj_1623,
wsj_1628,
wsj_1631,
wsj_1635,
wsj_1636,
wsj_1643,
wsj_1647,
wsj_1649,
wsj_1655,
wsj_1690,
wsj_1698,
wsj_1700,
wsj_1737,
wsj_1755,
wsj_1772,
wsj_1797,
wsj_1809a *) note below,
wsj_1818,
wsj_1831,
wsj_1846,
wsj_1847,
wsj_1849,
wsj_1869,
wsj_1927,
wsj_1936,
wsj_1947,
wsj_1952,
wsj_1963,
wsj_1984,
wsj_1986,
wsj_2012,
wsj_2013,
wsj_2047,
wsj_2053,
wsj_2054,
wsj_2106,
wsj_2144,
wsj_2149,
wsj_2202,
wsj_2231,
wsj_2233,
wsj_2237,
wsj_2264,
wsj_2282,
wsj_2316,
wsj_2343,
wsj_2369,
wsj_2372,
wsj_2384,
wsj_2397,
wsj_2402,
wsj_2429,
wsj_2444
- Errata, comprising those files with HL = Corrections & Amplifications:
wsj_0104, wsj_0200, wsj_0211, wsj_0410, wsj_0603, wsj_0605, wsj_0608, wsj_0611, wsj_0614, wsj_0974, wsj_1070, wsj_1401, wsj_1417, wsj_1430, wsj_1745, wsj_1747, wsj_1751, wsj_1871, wsj_1961, wsj_1964, wsj_1965, wsj_2014, wsj_2139, wsj_2311, wsj_2374
- News, comprising the rest:
wsj_0001,
wsj_0003,
wsj_0004,
wsj_0005,
wsj_0007,
wsj_0008,
wsj_0009,
wsj_0010,
wsj_0011,
wsj_0012,
wsj_0013,
wsj_0014,
wsj_0015,
wsj_0016,
wsj_0018,
wsj_0019,
wsj_0020,
wsj_0021,
wsj_0023,
wsj_0024,
wsj_0025,
wsj_0026,
wsj_0027,
wsj_0029,
wsj_0031,
wsj_0033,
wsj_0034,
wsj_0035,
wsj_0036,
wsj_0037b,
wsj_0038,
wsj_0040,
wsj_0043,
wsj_0044,
wsj_0046,
wsj_0047,
wsj_0048,
wsj_0049,
wsj_0050,
wsj_0051,
wsj_0052,
wsj_0054,
wsj_0057,
wsj_0059,
wsj_0060,
wsj_0062,
wsj_0063,
wsj_0064,
wsj_0065,
wsj_0066,
wsj_0067,
wsj_0068,
wsj_0069,
wsj_0070,
wsj_0072,
wsj_0073,
wsj_0074,
wsj_0075,
wsj_0076,
wsj_0077,
wsj_0079,
wsj_0080,
wsj_0081,
wsj_0082,
wsj_0083,
wsj_0084,
wsj_0085,
wsj_0086,
wsj_0087,
wsj_0088,
wsj_0089,
wsj_0090,
wsj_0092,
wsj_0093,
wsj_0096,
wsj_0097,
wsj_0098,
wsj_0100,
wsj_0101,
wsj_0102,
wsj_0106,
wsj_0107,
wsj_0109,
wsj_0111,
wsj_0112,
wsj_0113,
wsj_0114,
wsj_0115,
wsj_0116,
wsj_0117,
wsj_0118 (redundant; was replaced by a/b files),
wsj_0118a,
wsj_0118b,
wsj_0119,
wsj_0120,
wsj_0121,
wsj_0122,
wsj_0123,
wsj_0124,
wsj_0127,
wsj_0128,
wsj_0129,
wsj_0131,
wsj_0132,
wsj_0133,
wsj_0135,
wsj_0136,
wsj_0140,
wsj_0141,
wsj_0142,
wsj_0143,
wsj_0144,
wsj_0145,
wsj_0146,
wsj_0147,
wsj_0148,
wsj_0149,
wsj_0150,
wsj_0151,
wsj_0152,
wsj_0153,
wsj_0154,
wsj_0155,
wsj_0156,
wsj_0157,
wsj_0158,
wsj_0159,
wsj_0160,
wsj_0161,
wsj_0162,
wsj_0163,
wsj_0164,
wsj_0165,
wsj_0166a,
wsj_0166b,
wsj_0167,
wsj_0168,
wsj_0169,
wsj_0170,
wsj_0171,
wsj_0172,
wsj_0173,
wsj_0174,
wsj_0175,
wsj_0176,
wsj_0177,
wsj_0178,
wsj_0179,
wsj_0180,
wsj_0181,
wsj_0182,
wsj_0183,
wsj_0184,
wsj_0185,
wsj_0187,
wsj_0188,
wsj_0189,
wsj_0192,
wsj_0194,
wsj_0198,
wsj_0199,
wsj_0201,
wsj_0202,
wsj_0204,
wsj_0209,
wsj_0210,
wsj_0213,
wsj_0214,
wsj_0215,
wsj_0216,
wsj_0218,
wsj_0220,
wsj_0221,
wsj_0222,
wsj_0223,
wsj_0224,
wsj_0225,
wsj_0227,
wsj_0228,
wsj_0229,
wsj_0230,
wsj_0232,
wsj_0233,
wsj_0235,
wsj_0236,
wsj_0237,
wsj_0238,
wsj_0240,
wsj_0241,
wsj_0242,
wsj_0243,
wsj_0244,
wsj_0245,
wsj_0246,
wsj_0247,
wsj_0250,
wsj_0251,
wsj_0252,
wsj_0253,
wsj_0254,
wsj_0255,
wsj_0256,
wsj_0258,
wsj_0259,
wsj_0260,
wsj_0261,
wsj_0262,
wsj_0263,
wsj_0264,
wsj_0265,
wsj_0270,
wsj_0272,
wsj_0273,
wsj_0274,
wsj_0275,
wsj_0276,
wsj_0277,
wsj_0278,
wsj_0279,
wsj_0280,
wsj_0281,
wsj_0282,
wsj_0283a,
wsj_0283b,
wsj_0284,
wsj_0286,
wsj_0287,
wsj_0289,
wsj_0290,
wsj_0291,
wsj_0292,
wsj_0293,
wsj_0294,
wsj_0295,
wsj_0296,
wsj_0297,
wsj_0298,
wsj_0299,
wsj_0300,
wsj_0301,
wsj_0302,
wsj_0304,
wsj_0305,
wsj_0306,
wsj_0307,
wsj_0308,
wsj_0310,
wsj_0311,
wsj_0313,
wsj_0315,
wsj_0316,
wsj_0317,
wsj_0318,
wsj_0319,
wsj_0321,
wsj_0322,
wsj_0323,
wsj_0324,
wsj_0325,
wsj_0326,
wsj_0327,
wsj_0328,
wsj_0329,
wsj_0331,
wsj_0332,
wsj_0333,
wsj_0334,
wsj_0335,
wsj_0336,
wsj_0337,
wsj_0338,
wsj_0340,
wsj_0341,
wsj_0342,
wsj_0343,
wsj_0344,
wsj_0345,
wsj_0346,
wsj_0347,
wsj_0348,
wsj_0349,
wsj_0350,
wsj_0351,
wsj_0352,
wsj_0353,
wsj_0354,
wsj_0355,
wsj_0356,
wsj_0357,
wsj_0358,
wsj_0359,
wsj_0361,
wsj_0363,
wsj_0365,
wsj_0367,
wsj_0368,
wsj_0369,
wsj_0370,
wsj_0371,
wsj_0372,
wsj_0373,
wsj_0375,
wsj_0376,
wsj_0377,
wsj_0378,
wsj_0379,
wsj_0380,
wsj_0400,
wsj_0401,
wsj_0402,
wsj_0404,
wsj_0405,
wsj_0407,
wsj_0408,
wsj_0409,
wsj_0412,
wsj_0413,
wsj_0414,
wsj_0415,
wsj_0416,
wsj_0417,
wsj_0418,
wsj_0419,
wsj_0420,
wsj_0421,
wsj_0422,
wsj_0424,
wsj_0427,
wsj_0428,
wsj_0429,
wsj_0430,
wsj_0431,
wsj_0435,
wsj_0436,
wsj_0437,
wsj_0439,
wsj_0440,
wsj_0441,
wsj_0442,
wsj_0443,
wsj_0444,
wsj_0445,
wsj_0446,
wsj_0447,
wsj_0448,
wsj_0449,
wsj_0451,
wsj_0452,
wsj_0453,
wsj_0460,
wsj_0462,
wsj_0464,
wsj_0465,
wsj_0466,
wsj_0467,
wsj_0469,
wsj_0470,
wsj_0471,
wsj_0472,
wsj_0473,
wsj_0475,
wsj_0477,
wsj_0478,
wsj_0479,
wsj_0480,
wsj_0481,
wsj_0482,
wsj_0483,
wsj_0484,
wsj_0485,
wsj_0486,
wsj_0487,
wsj_0488,
wsj_0489,
wsj_0490,
wsj_0491,
wsj_0492,
wsj_0493,
wsj_0494,
wsj_0495,
wsj_0496,
wsj_0497,
wsj_0498,
wsj_0499,
wsj_0500,
wsj_0501,
wsj_0502,
wsj_0503,
wsj_0504,
wsj_0505,
wsj_0507,
wsj_0509,
wsj_0510,
wsj_0512,
wsj_0514,
wsj_0515,
wsj_0516,
wsj_0518,
wsj_0519,
wsj_0520,
wsj_0521,
wsj_0522,
wsj_0523,
wsj_0524,
wsj_0525,
wsj_0527,
wsj_0528,
wsj_0529,
wsj_0530,
wsj_0531,
wsj_0532,
wsj_0533,
wsj_0534,
wsj_0535,
wsj_0536,
wsj_0537,
wsj_0539,
wsj_0540,
wsj_0541,
wsj_0542,
wsj_0544,
wsj_0545b (b is missing),
wsj_0545a,
wsj_0546,
wsj_0547,
wsj_0548,
wsj_0551,
wsj_0552,
wsj_0554,
wsj_0556,
wsj_0557,
wsj_0558,
wsj_0559,
wsj_0560,
wsj_0563,
wsj_0564,
wsj_0565,
wsj_0566,
wsj_0567,
wsj_0568,
wsj_0569,
wsj_0570,
wsj_0571,
wsj_0572,
wsj_0573,
wsj_0574,
wsj_0575,
wsj_0576b,
wsj_0577,
wsj_0578,
wsj_0579,
wsj_0581,
wsj_0582,
wsj_0583,
wsj_0584,
wsj_0585,
wsj_0587,
wsj_0588,
wsj_0589,
wsj_0592,
wsj_0593,
wsj_0595,
wsj_0596,
wsj_0597,
wsj_0600,
wsj_0601,
wsj_0604,
wsj_0606,
wsj_0607,
wsj_0610,
wsj_0613,
wsj_0615,
wsj_0616,
wsj_0617,
wsj_0618,
wsj_0619,
wsj_0621,
wsj_0622,
wsj_0624,
wsj_0625,
wsj_0626,
wsj_0627,
wsj_0628,
wsj_0629,
wsj_0630,
wsj_0631,
wsj_0632,
wsj_0633,
wsj_0634,
wsj_0635,
wsj_0636,
wsj_0637,
wsj_0638,
wsj_0639,
wsj_0640,
wsj_0641,
wsj_0642,
wsj_0643,
wsj_0644,
wsj_0645,
wsj_0646,
wsj_0647,
wsj_0648,
wsj_0649,
wsj_0651,
wsj_0652,
wsj_0653,
wsj_0654,
wsj_0656,
wsj_0657,
wsj_0658,
wsj_0659,
wsj_0660,
wsj_0661,
wsj_0662,
wsj_0663,
wsj_0664,
wsj_0665,
wsj_0666,
wsj_0667,
wsj_0668,
wsj_0669,
wsj_0670,
wsj_0671,
wsj_0672,
wsj_0673,
wsj_0674,
wsj_0675,
wsj_0677,
wsj_0679,
wsj_0680,
wsj_0681,
wsj_0682,
wsj_0683,
wsj_0684,
wsj_0686,
wsj_0688,
wsj_0689,
wsj_0690,
wsj_0692,
wsj_0693,
wsj_0695,
wsj_0697,
wsj_0700,
wsj_0701,
wsj_0702,
wsj_0705,
wsj_0706,
wsj_0708,
wsj_0709,
wsj_0712,
wsj_0713,
wsj_0714,
wsj_0717,
wsj_0718,
wsj_0719,
wsj_0722,
wsj_0723,
wsj_0725,
wsj_0726,
wsj_0727,
wsj_0729,
wsj_0730,
wsj_0731,
wsj_0733,
wsj_0734,
wsj_0735,
wsj_0736,
wsj_0737,
wsj_0738,
wsj_0739,
wsj_0740,
wsj_0741,
wsj_0742,
wsj_0743,
wsj_0744,
wsj_0745,
wsj_0746,
wsj_0748,
wsj_0750,
wsj_0751,
wsj_0752,
wsj_0753,
wsj_0754,
wsj_0755,
wsj_0756,
wsj_0758,
wsj_0759,
wsj_0760,
wsj_0761,
wsj_0762,
wsj_0763,
wsj_0764,
wsj_0766,
wsj_0767,
wsj_0768,
wsj_0769,
wsj_0771,
wsj_0773,
wsj_0774,
wsj_0775,
wsj_0776,
wsj_0777,
wsj_0778,
wsj_0779,
wsj_0780,
wsj_0781,
wsj_0782,
wsj_0784,
wsj_0785,
wsj_0786,
wsj_0788,
wsj_0789,
wsj_0791,
wsj_0792,
wsj_0794,
wsj_0795,
wsj_0796,
wsj_0797,
wsj_0798,
wsj_0799,
wsj_0801,
wsj_0802,
wsj_0803,
wsj_0804,
wsj_0805,
wsj_0806,
wsj_0807,
wsj_0809,
wsj_0810,
wsj_0811,
wsj_0812,
wsj_0813,
wsj_0814 (should be replaced by: wsj_0814a,wsj_0814b),
wsj_0815,
wsj_0816,
wsj_0818,
wsj_0900,
wsj_0902,
wsj_0903,
wsj_0904,
wsj_0905,
wsj_0906,
wsj_0907,
wsj_0908,
wsj_0909,
wsj_0910,
wsj_0912,
wsj_0913,
wsj_0914,
wsj_0915,
wsj_0916,
wsj_0917,
wsj_0918,
wsj_0919,
wsj_0922,
wsj_0923,
wsj_0924,
wsj_0925,
wsj_0926,
wsj_0927,
wsj_0928,
wsj_0929,
wsj_0930,
wsj_0931,
wsj_0932,
wsj_0934,
wsj_0935,
wsj_0936,
wsj_0938,
wsj_0939,
wsj_0940,
wsj_0941,
wsj_0942,
wsj_0943,
wsj_0944,
wsj_0945,
wsj_0946,
wsj_0948,
wsj_0949,
wsj_0950,
wsj_0952,
wsj_0953,
wsj_0954,
wsj_0956,
wsj_0958,
wsj_0959,
wsj_0961,
wsj_0962,
wsj_0963,
wsj_0965,
wsj_0967,
wsj_0968,
wsj_0969,
wsj_0970,
wsj_0971,
wsj_0973,
wsj_0975,
wsj_0977,
wsj_0978,
wsj_0979,
wsj_0981,
wsj_0982,
wsj_0983,
wsj_0987,
wsj_0988,
wsj_0989,
wsj_0990a,
wsj_0990b,
wsj_0991,
wsj_0993,
wsj_0994,
wsj_0995,
wsj_0997,
wsj_0999,
wsj_1000,
wsj_1002,
wsj_1003,
wsj_1004,
wsj_1005,
wsj_1006,
wsj_1007,
wsj_1008,
wsj_1010,
wsj_1011,
wsj_1012,
wsj_1013,
wsj_1014,
wsj_1016,
wsj_1018,
wsj_1019,
wsj_1020,
wsj_1021,
wsj_1022,
wsj_1023,
wsj_1024,
wsj_1025,
wsj_1026,
wsj_1027,
wsj_1028,
wsj_1029,
wsj_1030,
wsj_1031,
wsj_1032,
wsj_1033,
wsj_1035,
wsj_1036,
wsj_1037,
wsj_1038,
wsj_1039,
wsj_1040,
wsj_1041,
wsj_1042,
wsj_1043,
wsj_1044,
wsj_1045,
wsj_1046,
wsj_1047,
wsj_1048,
wsj_1049,
wsj_1050,
wsj_1051,
wsj_1052,
wsj_1055,
wsj_1057,
wsj_1058,
wsj_1059,
wsj_1060,
wsj_1061,
wsj_1062,
wsj_1064,
wsj_1065,
wsj_1066,
wsj_1068,
wsj_1069,
wsj_1071,
wsj_1072,
wsj_1073,
wsj_1074,
wsj_1075,
wsj_1076,
wsj_1078,
wsj_1079,
wsj_1080,
wsj_1081,
wsj_1082,
wsj_1083,
wsj_1084,
wsj_1086,
wsj_1089,
wsj_1091,
wsj_1093,
wsj_1096,
wsj_1097,
wsj_1099,
wsj_1100,
wsj_1101,
wsj_1102,
wsj_1103,
wsj_1105,
wsj_1106,
wsj_1108,
wsj_1109,
wsj_1110,
wsj_1111,
wsj_1112,
wsj_1113,
wsj_1117,
wsj_1119,
wsj_1120,
wsj_1121,
wsj_1122,
wsj_1123,
wsj_1124,
wsj_1125,
wsj_1126,
wsj_1127,
wsj_1128,
wsj_1130,
wsj_1131,
wsj_1132,
wsj_1133,
wsj_1134,
wsj_1135,
wsj_1136,
wsj_1137,
wsj_1138,
wsj_1139,
wsj_1140,
wsj_1142,
wsj_1144,
wsj_1145,
wsj_1146,
wsj_1147,
wsj_1148,
wsj_1150,
wsj_1151,
wsj_1153,
wsj_1154b,
wsj_1155,
wsj_1156a,
wsj_1157,
wsj_1159,
wsj_1160,
wsj_1162,
wsj_1165,
wsj_1166,
wsj_1167,
wsj_1168,
wsj_1169,
wsj_1170,
wsj_1171,
wsj_1172,
wsj_1173,
wsj_1174,
wsj_1175,
wsj_1176,
wsj_1177,
wsj_1178,
wsj_1179,
wsj_1180,
wsj_1181,
wsj_1182,
wsj_1183,
wsj_1184,
wsj_1185,
wsj_1186,
wsj_1188,
wsj_1190,
wsj_1191,
wsj_1192,
wsj_1193,
wsj_1194,
wsj_1195,
wsj_1196,
wsj_1198,
wsj_1199,
wsj_1200,
wsj_1201,
wsj_1203,
wsj_1204,
wsj_1205,
wsj_1206,
wsj_1207,
wsj_1208,
wsj_1209,
wsj_1210,
wsj_1211,
wsj_1213,
wsj_1214,
wsj_1215,
wsj_1216,
wsj_1217,
wsj_1218,
wsj_1219,
wsj_1220,
wsj_1221,
wsj_1222,
wsj_1223,
wsj_1224,
wsj_1225,
wsj_1226,
wsj_1227,
wsj_1229,
wsj_1230,
wsj_1231,
wsj_1232,
wsj_1233,
wsj_1234,
wsj_1235,
wsj_1236,
wsj_1237,
wsj_1238,
wsj_1239,
wsj_1241,
wsj_1242,
wsj_1243,
wsj_1244,
wsj_1246,
wsj_1248,
wsj_1249,
wsj_1250a,
wsj_1250b,
wsj_1251,
wsj_1254,
wsj_1255,
wsj_1257,
wsj_1258,
wsj_1259,
wsj_1261,
wsj_1263,
wsj_1264,
wsj_1265,
wsj_1267,
wsj_1268,
wsj_1269,
wsj_1270,
wsj_1271,
wsj_1273,
wsj_1274,
wsj_1275,
wsj_1276,
wsj_1278,
wsj_1279,
wsj_1280,
wsj_1281,
wsj_1282,
wsj_1283,
wsj_1284,
wsj_1285,
wsj_1286,
wsj_1287,
wsj_1288,
wsj_1289,
wsj_1290,
wsj_1291,
wsj_1292,
wsj_1293,
wsj_1294,
wsj_1295,
wsj_1296,
wsj_1297,
wsj_1298,
wsj_1299,
wsj_1300,
wsj_1301,
wsj_1302,
wsj_1304,
wsj_1305,
wsj_1306,
wsj_1309,
wsj_1310,
wsj_1311,
wsj_1313,
wsj_1314,
wsj_1316,
wsj_1317,
wsj_1318,
wsj_1319,
wsj_1320,
wsj_1321,
wsj_1322,
wsj_1324,
wsj_1325,
wsj_1328,
wsj_1329,
wsj_1330,
wsj_1331,
wsj_1332,
wsj_1333,
wsj_1334,
wsj_1335,
wsj_1336,
wsj_1338,
wsj_1340,
wsj_1341,
wsj_1343,
wsj_1345,
wsj_1346,
wsj_1347,
wsj_1348,
wsj_1350,
wsj_1351,
wsj_1352,
wsj_1353,
wsj_1354,
wsj_1355,
wsj_1356,
wsj_1357,
wsj_1358,
wsj_1359,
wsj_1360,
wsj_1361,
wsj_1362,
wsj_1363,
wsj_1364,
wsj_1365,
wsj_1367,
wsj_1368,
wsj_1369,
wsj_1370,
wsj_1371,
wsj_1372,
wsj_1373,
wsj_1374,
wsj_1375,
wsj_1376,
wsj_1377,
wsj_1379,
wsj_1380,
wsj_1381,
wsj_1383,
wsj_1386,
wsj_1387,
wsj_1390,
wsj_1391,
wsj_1392,
wsj_1394,
wsj_1395,
wsj_1399,
wsj_1403,
wsj_1404,
wsj_1407,
wsj_1408,
wsj_1409,
wsj_1410,
wsj_1414,
wsj_1415,
wsj_1418,
wsj_1419,
wsj_1421,
wsj_1422,
wsj_1423,
wsj_1424,
wsj_1426,
wsj_1428,
wsj_1429,
wsj_1431,
wsj_1432,
wsj_1433,
wsj_1435,
wsj_1437,
wsj_1438,
wsj_1439,
wsj_1440,
wsj_1442,
wsj_1443,
wsj_1445,
wsj_1446,
wsj_1447,
wsj_1448,
wsj_1449,
wsj_1451,
wsj_1453,
wsj_1454,
wsj_1455,
wsj_1456,
wsj_1458,
wsj_1459,
wsj_1460,
wsj_1461,
wsj_1462,
wsj_1463,
wsj_1464,
wsj_1465,
wsj_1466,
wsj_1467a,
wsj_1467b,
wsj_1468,
wsj_1469,
wsj_1470,
wsj_1471,
wsj_1472,
wsj_1474,
wsj_1475,
wsj_1476,
wsj_1477,
wsj_1478,
wsj_1479,
wsj_1480,
wsj_1481,
wsj_1483,
wsj_1484,
wsj_1485,
wsj_1486,
wsj_1487,
wsj_1488,
wsj_1489,
wsj_1490,
wsj_1491,
wsj_1492,
wsj_1493,
wsj_1494,
wsj_1496,
wsj_1498,
wsj_1500,
wsj_1501,
wsj_1502,
wsj_1503,
wsj_1508,
wsj_1509,
wsj_1510,
wsj_1511,
wsj_1512,
wsj_1513,
wsj_1514,
wsj_1515,
wsj_1516,
wsj_1517,
wsj_1518,
wsj_1519,
wsj_1521,
wsj_1522,
wsj_1523,
wsj_1524,
wsj_1525,
wsj_1526,
wsj_1527,
wsj_1528,
wsj_1530,
wsj_1531,
wsj_1532,
wsj_1533,
wsj_1534,
wsj_1535,
wsj_1536,
wsj_1537,
wsj_1538,
wsj_1539,
wsj_1540,
wsj_1541,
wsj_1542,
wsj_1543,
wsj_1544,
wsj_1545,
wsj_1546,
wsj_1547,
wsj_1548,
wsj_1549,
wsj_1550,
wsj_1551,
wsj_1552,
wsj_1553,
wsj_1554,
wsj_1555,
wsj_1556,
wsj_1560,
wsj_1561,
wsj_1573,
wsj_1575,
wsj_1577,
wsj_1578,
wsj_1580,
wsj_1581,
wsj_1582,
wsj_1583,
wsj_1584,
wsj_1586,
wsj_1587,
wsj_1589,
wsj_1590,
wsj_1591,
wsj_1592,
wsj_1593,
wsj_1594,
wsj_1595,
wsj_1596,
wsj_1597,
wsj_1598,
wsj_1599,
wsj_1600,
wsj_1601,
wsj_1603,
wsj_1604,
wsj_1606,
wsj_1607,
wsj_1609,
wsj_1610,
wsj_1611,
wsj_1612,
wsj_1613,
wsj_1614,
wsj_1615,
wsj_1616,
wsj_1617,
wsj_1619,
wsj_1620,
wsj_1621,
wsj_1622,
wsj_1624,
wsj_1626,
wsj_1627,
wsj_1629,
wsj_1630,
wsj_1633,
wsj_1634,
wsj_1637,
wsj_1639,
wsj_1640,
wsj_1641,
wsj_1642,
wsj_1644,
wsj_1645,
wsj_1646,
wsj_1648,
wsj_1650,
wsj_1651,
wsj_1652,
wsj_1654,
wsj_1656,
wsj_1657,
wsj_1658,
wsj_1659,
wsj_1660,
wsj_1661,
wsj_1662,
wsj_1663,
wsj_1664,
wsj_1665,
wsj_1666,
wsj_1667,
wsj_1668,
wsj_1669,
wsj_1670,
wsj_1671,
wsj_1672,
wsj_1673,
wsj_1674,
wsj_1675,
wsj_1677,
wsj_1678,
wsj_1679,
wsj_1680,
wsj_1681,
wsj_1682,
wsj_1683,
wsj_1684,
wsj_1686,
wsj_1687,
wsj_1688,
wsj_1689,
wsj_1691,
wsj_1692,
wsj_1693,
wsj_1694,
wsj_1695,
wsj_1696,
wsj_1697,
wsj_1699,
wsj_1701,
wsj_1702,
wsj_1703,
wsj_1704,
wsj_1705,
wsj_1706,
wsj_1707,
wsj_1708,
wsj_1709,
wsj_1710,
wsj_1711,
wsj_1712,
wsj_1713,
wsj_1714,
wsj_1715,
wsj_1717,
wsj_1718,
wsj_1719,
wsj_1720,
wsj_1721,
wsj_1722,
wsj_1724,
wsj_1725,
wsj_1726,
wsj_1727,
wsj_1728,
wsj_1729,
wsj_1730,
wsj_1731,
wsj_1732,
wsj_1733,
wsj_1734,
wsj_1735,
wsj_1736,
wsj_1738,
wsj_1739,
wsj_1740,
wsj_1741,
wsj_1742,
wsj_1743b,
wsj_1744,
wsj_1746,
wsj_1748,
wsj_1749,
wsj_1750,
wsj_1752,
wsj_1753,
wsj_1754,
wsj_1756,
wsj_1757,
wsj_1759,
wsj_1760,
wsj_1761,
wsj_1762,
wsj_1763,
wsj_1764,
wsj_1765,
wsj_1766,
wsj_1767,
wsj_1768,
wsj_1769,
wsj_1770,
wsj_1773,
wsj_1774,
wsj_1775,
wsj_1776,
wsj_1777,
wsj_1778,
wsj_1779,
wsj_1780,
wsj_1782,
wsj_1783,
wsj_1784,
wsj_1787,
wsj_1788,
wsj_1789,
wsj_1790,
wsj_1791,
wsj_1792,
wsj_1793,
wsj_1794,
wsj_1795,
wsj_1796,
wsj_1799,
wsj_1800,
wsj_1802,
wsj_1803,
wsj_1804,
wsj_1806,
wsj_1808,
wsj_1810,
wsj_1811,
wsj_1812,
wsj_1813,
wsj_1815,
wsj_1816,
wsj_1817,
wsj_1819,
wsj_1820,
wsj_1821,
wsj_1822,
wsj_1823,
wsj_1824,
wsj_1825,
wsj_1826,
wsj_1827,
wsj_1828,
wsj_1829,
wsj_1830,
wsj_1832,
wsj_1833,
wsj_1835,
wsj_1837,
wsj_1840,
wsj_1841,
wsj_1842,
wsj_1843,
wsj_1844,
wsj_1848,
wsj_1850,
wsj_1851,
wsj_1852,
wsj_1853,
wsj_1854,
wsj_1855,
wsj_1856,
wsj_1857,
wsj_1858,
wsj_1859,
wsj_1860,
wsj_1861,
wsj_1862,
wsj_1863,
wsj_1864,
wsj_1865,
wsj_1866,
wsj_1868,
wsj_1870,
wsj_1872,
wsj_1873,
wsj_1874,
wsj_1875a,
wsj_1875b,
wsj_1877,
wsj_1878,
wsj_1879,
wsj_1880,
wsj_1881,
wsj_1882,
wsj_1883,
wsj_1884,
wsj_1885,
wsj_1886,
wsj_1887,
wsj_1888,
wsj_1889,
wsj_1890,
wsj_1891,
wsj_1892,
wsj_1893,
wsj_1894,
wsj_1895,
wsj_1896,
wsj_1897,
wsj_1898,
wsj_1899,
wsj_1900,
wsj_1901,
wsj_1902,
wsj_1903,
wsj_1904,
wsj_1905,
wsj_1906,
wsj_1907,
wsj_1908,
wsj_1909,
wsj_1910,
wsj_1911,
wsj_1912,
wsj_1913,
wsj_1914,
wsj_1915,
wsj_1916,
wsj_1917,
wsj_1918,
wsj_1919,
wsj_1920,
wsj_1921,
wsj_1922,
wsj_1923,
wsj_1924,
wsj_1925,
wsj_1926,
wsj_1928,
wsj_1929,
wsj_1930,
wsj_1931,
wsj_1932,
wsj_1934,
wsj_1937,
wsj_1938,
wsj_1939,
wsj_1940,
wsj_1943,
wsj_1944,
wsj_1945,
wsj_1946,
wsj_1948,
wsj_1949,
wsj_1951,
wsj_1953,
wsj_1959,
wsj_1960,
wsj_1962,
wsj_1966,
wsj_1967,
wsj_1968,
wsj_1969,
wsj_1970,
wsj_1971,
wsj_1972,
wsj_1973,
wsj_1975,
wsj_1976,
wsj_1977,
wsj_1978,
wsj_1980,
wsj_1981,
wsj_1982,
wsj_1983,
wsj_1985,
wsj_1987,
wsj_1988,
wsj_1989,
wsj_1990,
wsj_1991,
wsj_1992,
wsj_1994,
wsj_1996,
wsj_1997,
wsj_1998,
wsj_1999,
wsj_2000,
wsj_2001,
wsj_2002,
wsj_2003,
wsj_2004,
wsj_2005,
wsj_2006,
wsj_2007,
wsj_2008,
wsj_2009,
wsj_2010,
wsj_2015,
wsj_2016,
wsj_2017,
wsj_2018,
wsj_2019,
wsj_2020,
wsj_2022,
wsj_2023,
wsj_2024,
wsj_2025,
wsj_2026,
wsj_2027,
wsj_2028,
wsj_2030,
wsj_2031,
wsj_2032,
wsj_2033,
wsj_2034,
wsj_2036,
wsj_2037,
wsj_2039,
wsj_2040,
wsj_2041,
wsj_2042,
wsj_2043,
wsj_2044,
wsj_2045,
wsj_2046,
wsj_2048,
wsj_2049,
wsj_2051,
wsj_2052,
wsj_2055a,
wsj_2055b,
wsj_2056,
wsj_2057,
wsj_2058,
wsj_2059,
wsj_2060,
wsj_2061,
wsj_2062,
wsj_2063,
wsj_2064,
wsj_2065,
wsj_2066,
wsj_2067,
wsj_2068,
wsj_2069,
wsj_2070,
wsj_2071,
wsj_2072,
wsj_2073,
wsj_2074,
wsj_2075,
wsj_2076,
wsj_2077,
wsj_2078,
wsj_2079,
wsj_2080,
wsj_2081,
wsj_2082,
wsj_2083,
wsj_2084,
wsj_2085,
wsj_2086,
wsj_2087,
wsj_2088,
wsj_2089,
wsj_2091,
wsj_2092,
wsj_2093,
wsj_2094,
wsj_2095,
wsj_2096,
wsj_2098,
wsj_2099,
wsj_2100,
wsj_2101,
wsj_2102,
wsj_2103,
wsj_2104,
wsj_2105,
wsj_2107,
wsj_2109,
wsj_2110,
wsj_2111,
wsj_2112,
wsj_2113,
wsj_2115,
wsj_2116,
wsj_2118,
wsj_2119,
wsj_2120,
wsj_2121,
wsj_2123,
wsj_2124,
wsj_2125,
wsj_2126,
wsj_2127,
wsj_2128,
wsj_2129,
wsj_2130,
wsj_2131,
wsj_2132,
wsj_2133,
wsj_2135,
wsj_2136a,
wsj_2136b,
wsj_2138,
wsj_2140,
wsj_2141,
wsj_2142,
wsj_2143,
wsj_2145,
wsj_2146,
wsj_2148,
wsj_2150,
wsj_2151,
wsj_2152,
wsj_2153,
wsj_2154,
wsj_2155,
wsj_2156,
wsj_2157,
wsj_2158,
wsj_2159,
wsj_2160,
wsj_2161,
wsj_2162,
wsj_2163,
wsj_2164,
wsj_2165,
wsj_2166,
wsj_2167,
wsj_2168,
wsj_2169,
wsj_2172,
wsj_2200,
wsj_2201,
wsj_2203,
wsj_2205,
wsj_2207,
wsj_2208,
wsj_2209,
wsj_2210,
wsj_2211,
wsj_2212,
wsj_2213,
wsj_2214,
wsj_2216,
wsj_2218,
wsj_2219,
wsj_2221,
wsj_2222,
wsj_2223,
wsj_2224,
wsj_2225,
wsj_2226,
wsj_2227,
wsj_2228,
wsj_2229,
wsj_2232,
wsj_2234,
wsj_2235,
wsj_2238,
wsj_2239,
wsj_2240,
wsj_2241,
wsj_2242,
wsj_2243,
wsj_2244,
wsj_2245,
wsj_2246,
wsj_2247,
wsj_2248,
wsj_2249,
wsj_2250,
wsj_2251,
wsj_2252,
wsj_2253,
wsj_2254,
wsj_2255,
wsj_2256,
wsj_2258,
wsj_2259,
wsj_2260,
wsj_2261,
wsj_2262,
wsj_2265,
wsj_2266,
wsj_2267,
wsj_2268,
wsj_2269,
wsj_2270,
wsj_2271,
wsj_2272,
wsj_2273,
wsj_2274,
wsj_2275,
wsj_2276,
wsj_2277,
wsj_2278,
wsj_2280,
wsj_2281,
wsj_2300,
wsj_2302,
wsj_2303,
wsj_2305,
wsj_2306,
wsj_2308,
wsj_2309,
wsj_2310,
wsj_2313,
wsj_2314,
wsj_2315,
wsj_2317,
wsj_2319,
wsj_2320,
wsj_2321,
wsj_2322,
wsj_2323,
wsj_2324,
wsj_2325,
wsj_2326,
wsj_2327,
wsj_2328,
wsj_2329,
wsj_2330,
wsj_2331,
wsj_2332,
wsj_2333,
wsj_2334,
wsj_2335,
wsj_2336,
wsj_2337,
wsj_2338,
wsj_2339,
wsj_2340,
wsj_2341,
wsj_2342,
wsj_2344,
wsj_2345,
wsj_2346a,
wsj_2346b,
wsj_2347,
wsj_2348,
wsj_2350,
wsj_2351,
wsj_2353,
wsj_2354,
wsj_2355,
wsj_2356,
wsj_2357,
wsj_2358,
wsj_2359,
wsj_2360,
wsj_2361,
wsj_2362,
wsj_2363,
wsj_2364,
wsj_2365,
wsj_2366,
wsj_2367,
wsj_2370,
wsj_2371,
wsj_2375,
wsj_2376,
wsj_2378,
wsj_2379,
wsj_2381,
wsj_2382,
wsj_2383,
wsj_2386,
wsj_2387,
wsj_2391,
wsj_2392,
wsj_2393,
wsj_2394,
wsj_2395,
wsj_2396,
wsj_2398,
wsj_2400,
wsj_2403,
wsj_2404,
wsj_2405,
wsj_2406,
wsj_2407,
wsj_2408,
wsj_2409,
wsj_2410,
wsj_2411,
wsj_2412,
wsj_2413,
wsj_2414,
wsj_2415,
wsj_2416,
wsj_2417a,
wsj_2417b,
wsj_2418,
wsj_2419,
wsj_2420,
wsj_2421,
wsj_2422,
wsj_2423,
wsj_2424,
wsj_2425,
wsj_2426,
wsj_2427,
wsj_2428,
wsj_2430,
wsj_2431,
wsj_2432,
wsj_2433,
wsj_2434,
wsj_2435,
wsj_2436,
wsj_2437,
wsj_2438,
wsj_2439,
wsj_2440,
wsj_2441,
wsj_2442,
wsj_2443,
wsj_2445,
wsj_2446,
wsj_2447,
wsj_2448,
wsj_2449,
wsj_2450,
wsj_2451,
wsj_2452,
wsj_2453,
wsj_2454,
- Wit and short verse, comprising those files with HL= Pepper...and Salt
wsj_0139,
wsj_0312, wsj_0594, wsj_0403, wsj_0757, wsj_1054,
wsj_1212, wsj_1252, wsj_1398, wsj_1758, wsj_1798,
wsj_2038, wsj_2215, wsj_2401, (wsj_2497 --> is not in PDTB)
- Quarterly progress reports, comprises multiple copies of
the file wsj_0190 (because the distinguishing company listings have
been omitted). The file has heading HL=Quarterly Earnings
Surprises
wsj_0190, wsj_0364, wsj_0511, wsj_0696, wsj_1056,
wsj_1228, wsj_1382, wsj_1557, wsj_1558, wsj_1941,
wsj_2114, (wsj_2458 --> is not in PDTB)
- Notable & Quotable, comprising those files with HL= Notable & Quotable (there was one more DOCID, namely 891013-0085, but this file is not in the mapping, i.e. not in the PTB/PDTB, and thus was ignored)
wsj_0362, wsj_1141, wsj_1452, wsj_1685, wsj_1839, wsj_2217 (they were listed as news in Part I but actually form a new class)
Note: file wsj_1809 should be split in two, even though it's not mentioned in the "dual" mapping file. The second part (b) just contains one sentence -- ignore (because the original tipster filed contained a list of books but that was ignored in the annotation). mapping wsj/tipsterDOCNO: wsj_1089 891019-0135 + 891019-0134.
Overview files:
II.errata: 25
II.essays: 166
II.highlights: 41
II.letters: 59
II.news: 1855
wit and short verse: 14 (+ 1; not in PDTB)
quarterly progress reports: 11 (+1; not in PDTB)
notable & quotable: 6
---
total genre annotated: 2146 + 6 + 14 + 11 = 2177 + 2 (not in PDTB)
total PT wsj files (original mrg files): 2312
total PT wsj files after split in a/b files: 2331 (19 files split)
rest: 2331 - 2177 = 154 files (remaining files that are not in the PDTB and hence not annotated) - 2 (annotated) = 152
Note: wsj_1259 and wsj_1862 do point to the same tipster doc 891024-0126. However, one of them contains one line more plus their syntactic annotation differs. Hence, ignore them. This means we have 2175 remaining genre annotated files. Moreover, if we ignore the 10 copies of file wsj_0190 (quarterly profit reports), we are left with 2165 genre annotated files.
Those 154 (153 + 1) files are not in the Penn discourse treeebank (see list here: files-not-in-pdtb.txt) -- 153 files mentioned by Bonnie in ACL 2009 paper plus one file: wsj_1809b -- the strange one sentence file mentioned above.
remaining-files.txt (now all annotated)
Makefile to get split of 19 WSJ files into a/b parts.