Hello, I noticed with the following warning when I train my Arabic bot, I don’t know if this affect the model or not, any one can advice? this is the log of the rasa training (version 2.3.3)
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'أبغى أعمل مقابلة' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 16, 'new')]) in the training data match the token boundaries ([(0, 4, 'أبغى'), (5, 9, 'أعمل'), (10, 16, 'مقابلة')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'أبغى أقابل شخص مسئول' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 10, 'new')]) in the training data match the token boundaries ([(0, 4, 'أبغى'), (5, 10, 'أقابل'), (11, 14, 'شخص'), (15, 20, 'مسئول')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'أعلم انه يمكننى حجز موعد من خلالك, برجاء حجز موعد لى غداً مع فراس الأحمدي من الإدارة العليا - مع العلم أننى موظف فى المؤسسة ورقمي الوظيفي هو 9887633 ورقم الجوال الخاص بي هو 0556478912' with intent 'Appointment'. Make sure the start and end values of entities ([(16, 25, 'new'), (41, 49, 'new'), (61, 73, 'فراس الأحمدي'), (77, 91, 'الإدارة العليا'), (108, 112, 'employee'), (141, 148, '9887633'), (173, 183, '0556478912')]) in the training data match the token boundaries ([(0, 4, 'أعلم'), (5, 8, 'انه'), (9, 15, 'يمكننى'), (16, 19, 'حجز'), (20, 24, 'موعد'), (25, 27, 'من'), (28, 33, 'خلالك'), (35, 40, 'برجاء'), (41, 44, 'حجز'), (45, 49, 'موعد'), (50, 52, 'لى'), (53, 57, 'غداً'), (58, 60, 'مع'), (61, 65, 'فراس'), (66, 73, 'الأحمدي'), (74, 76, 'من'), (77, 84, 'الإدارة'), (85, 91, 'العليا'), (94, 96, 'مع'), (97, 102, 'العلم'), (103, 107, 'أننى'), (108, 112, 'موظف'), (113, 115, 'فى'), (116, 123, 'المؤسسة'), (124, 129, 'ورقمي'), (130, 137, 'الوظيفي'), (138, 140, 'هو'), (141, 148, '9887633'), (149, 153, 'ورقم'), (154, 160, 'الجوال'), (161, 166, 'الخاص'), (167, 169, 'بي'), (170, 172, 'هو'), (173, 183, '0556478912')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'أنا زائرة لاستاذه داليا الخولى من مصر' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 10, 'visitor'), (18, 30, 'داليا الخولى'), (34, 37, 'مصري')]) in the training data match the token boundaries ([(0, 3, 'أنا'), (4, 9, 'زائرة'), (10, 17, 'لاستاذه'), (18, 23, 'داليا'), (24, 30, 'الخولى'), (31, 33, 'من'), (34, 37, 'مصر')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'أنا موظف هنا ورقمي الوظيفي هو 221545488888 وأريد حجز موعد جديد' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 9, 'employee'), (30, 43, '221545488888 '), (53, 62, 'new')]) in the training data match the token boundaries ([(0, 3, 'أنا'), (4, 8, 'موظف'), (9, 12, 'هنا'), (13, 18, 'ورقمي'), (19, 26, 'الوظيفي'), (27, 29, 'هو'), (30, 42, '221545488888'), (43, 48, 'وأريد'), (49, 52, 'حجز'), (53, 57, 'موعد'), (58, 62, 'جديد')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'ابي احدد موعد مقابلة مع إدارة الحياة البحرية والبيئة\n وهذا رقم هاتفي 0158787566' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 14, 'new'), (24, 52, 'إدارة الحياة البحرية والبيئة'), (70, 80, '0158787566')]) in the training data match the token boundaries ([(0, 3, 'ابي'), (4, 8, 'احدد'), (9, 13, 'موعد'), (14, 20, 'مقابلة'), (21, 23, 'مع'), (24, 29, 'إدارة'), (30, 36, 'الحياة'), (37, 44, 'البحرية'), (45, 52, 'والبيئة'), (53, 54, 'n'), (55, 59, 'وهذا'), (60, 63, 'رقم'), (64, 69, 'هاتفي'), (70, 80, '0158787566')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اتيت لزيارة إدارة الموارد البشرية وهذا رقم إقامة 68888699 انا قطري الجنسية' with intent 'Appointment'. Make sure the start and end values of entities ([(12, 33, 'إدارة الموارد البشرية'), (42, 43, ' '), (44, 49, 'إقامة'), (50, 59, '68888699 '), (63, 68, 'قطري ')]) in the training data match the token boundaries ([(0, 4, 'اتيت'), (5, 11, 'لزيارة'), (12, 17, 'إدارة'), (18, 25, 'الموارد'), (26, 33, 'البشرية'), (34, 38, 'وهذا'), (39, 42, 'رقم'), (44, 49, 'إقامة'), (50, 58, '68888699'), (59, 62, 'انا'), (63, 67, 'قطري'), (68, 75, 'الجنسية')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اريد التقديم على طلب زيارة' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 26, 'new')]) in the training data match the token boundaries ([(0, 4, 'اريد'), (5, 12, 'التقديم'), (13, 16, 'على'), (17, 20, 'طلب'), (21, 26, 'زيارة')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اريد حجز مقابلة مع راجا محمد من إدارة البيئة أنا زائر قادم من مصر وأريد مقابلته مع العلم أن رقم هاتفى الجوال هو 0577555222' with intent 'Appointment'. Make sure the start and end values of entities ([(5, 16, 'new'), (19, 28, 'راجا محمد'), (32, 44, 'إدارة الحياة البحرية والبيئة'), (49, 54, 'visitor'), (62, 65, 'مصري'), (112, 122, '0577555222')]) in the training data match the token boundaries ([(0, 4, 'اريد'), (5, 8, 'حجز'), (9, 15, 'مقابلة'), (16, 18, 'مع'), (19, 23, 'راجا'), (24, 28, 'محمد'), (29, 31, 'من'), (32, 37, 'إدارة'), (38, 44, 'البيئة'), (45, 48, 'أنا'), (49, 53, 'زائر'), (54, 58, 'قادم'), (59, 61, 'من'), (62, 65, 'مصر'), (66, 71, 'وأريد'), (72, 79, 'مقابلته'), (80, 82, 'مع'), (83, 88, 'العلم'), (89, 91, 'أن'), (92, 95, 'رقم'), (96, 101, 'هاتفى'), (102, 108, 'الجوال'), (109, 111, 'هو'), (112, 122, '0577555222')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اسمى هبة اريد مقابله السيد محمد عبد العزيز من قسم الحسابات' with intent 'Appointment'. Make sure the start and end values of entities ([(5, 9, 'هبة '), (46, 58, 'إدارة الحسابات')]) in the training data match the token boundaries ([(0, 4, 'اسمى'), (5, 8, 'هبة'), (9, 13, 'اريد'), (14, 20, 'مقابله'), (21, 26, 'السيد'), (27, 31, 'محمد'), (32, 35, 'عبد'), (36, 42, 'العزيز'), (43, 45, 'من'), (46, 49, 'قسم'), (50, 58, 'الحسابات')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اسمي ماهر ورقم الإقامة هو 434343 واريد مقابلة حسين في الادارة العليا' with intent 'Appointment'. Make sure the start and end values of entities ([(5, 9, 'ماهر'), (15, 23, 'إقامة'), (26, 32, '434343'), (54, 68, 'الادارة العليا')]) in the training data match the token boundaries ([(0, 4, 'اسمي'), (5, 9, 'ماهر'), (10, 14, 'ورقم'), (15, 22, 'الإقامة'), (23, 25, 'هو'), (26, 32, '434343'), (33, 38, 'واريد'), (39, 45, 'مقابلة'), (46, 50, 'حسين'), (51, 53, 'في'), (54, 61, 'الادارة'), (62, 68, 'العليا')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'انا جاي اقابل مومن يعمل في إدارة المخازن\nوهذا رقمي 01566555555' with intent 'Appointment'. Make sure the start and end values of entities ([(14, 19, 'مومن '), (28, 41, 'إدارة المخازن'), (53, 64, '01566555555')]) in the training data match the token boundaries ([(0, 3, 'انا'), (4, 7, 'جاي'), (8, 13, 'اقابل'), (14, 18, 'مومن'), (20, 24, 'يعمل'), (25, 27, 'في'), (28, 33, 'إدارة'), (34, 41, 'المخازن'), (42, 47, 'nوهذا'), (48, 52, 'رقمي'), (53, 64, '01566555555')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'انا زائر سعودي الجنسية ورقم هاتفي061564989626 وابي احدد موعد اجتماع مع إدارة تكنولوجيا المعلومات' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 9, 'visitor'), (10, 15, 'سعودي'), (34, 46, '061564989626'), (52, 61, 'new'), (72, 97, 'إدارة تكنولوجيا المعلومات')]) in the training data match the token boundaries ([(0, 3, 'انا'), (4, 8, 'زائر'), (10, 15, 'سعودي'), (16, 23, 'الجنسية'), (24, 28, 'ورقم'), (29, 46, 'هاتفي061564989626'), (47, 51, 'وابي'), (52, 56, 'احدد'), (57, 61, 'موعد'), (62, 68, 'اجتماع'), (69, 71, 'مع'), (72, 77, 'إدارة'), (78, 87, 'تكنولوجيا'), (88, 97, 'المعلومات')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'انا هنا لتحديد موعد زيارة مع نهاد وهذا رقم جواز سفر الخاص بي 66599215' with intent 'Appointment'. Make sure the start and end values of entities ([(7, 20, 'new'), (29, 34, 'نهاد '), (44, 52, 'جواز سفر'), (62, 70, '66599215')]) in the training data match the token boundaries ([(0, 3, 'انا'), (4, 7, 'هنا'), (8, 14, 'لتحديد'), (15, 19, 'موعد'), (20, 25, 'زيارة'), (26, 28, 'مع'), (29, 33, 'نهاد'), (35, 39, 'وهذا'), (40, 43, 'رقم'), (44, 48, 'جواز'), (49, 52, 'سفر'), (53, 58, 'الخاص'), (59, 61, 'بي'), (62, 70, '66599215')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'اولا اريد ان اقول لكم انني حاتم من السعودية ورقم بطاقة الهوية 223232323 واريد ان اجتمع بقسم الادارة العليا لعرض مشكلة.' with intent 'Appointment'. Make sure the start and end values of entities ([(36, 45, 'سعودي'), (51, 63, 'بطاقة الهوية'), (64, 74, '223232323 '), (94, 108, 'الادارة العليا')]) in the training data match the token boundaries ([(0, 4, 'اولا'), (5, 9, 'اريد'), (10, 12, 'ان'), (13, 17, 'اقول'), (18, 21, 'لكم'), (22, 26, 'انني'), (27, 31, 'حاتم'), (33, 35, 'من'), (36, 44, 'السعودية'), (46, 50, 'ورقم'), (51, 56, 'بطاقة'), (57, 63, 'الهوية'), (64, 73, '223232323'), (74, 79, 'واريد'), (80, 82, 'ان'), (83, 88, 'اجتمع'), (89, 93, 'بقسم'), (94, 101, 'الادارة'), (102, 108, 'العليا'), (109, 113, 'لعرض'), (114, 119, 'مشكلة')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'رقم بطاقة الهوية 777777 وانا من مصر ولكن انا ضيف لذا احتاج منك مساعدتي في حجز مقابلة مع موعد قسم الموارد البشرية' with intent 'Appointment'. Make sure the start and end values of entities ([(4, 16, 'بطاقة الهوية'), (17, 23, '777777'), (32, 35, 'مصري'), (44, 48, 'visitor'), (74, 84, 'new'), (93, 112, 'إدارة الموارد البشرية')]) in the training data match the token boundaries ([(0, 3, 'رقم'), (4, 9, 'بطاقة'), (10, 16, 'الهوية'), (17, 23, '777777'), (24, 28, 'وانا'), (29, 31, 'من'), (32, 35, 'مصر'), (36, 40, 'ولكن'), (41, 44, 'انا'), (45, 48, 'ضيف'), (49, 52, 'لذا'), (53, 58, 'احتاج'), (59, 62, 'منك'), (63, 70, 'مساعدتي'), (71, 73, 'في'), (74, 77, 'حجز'), (78, 84, 'مقابلة'), (85, 87, 'مع'), (88, 92, 'موعد'), (93, 96, 'قسم'), (97, 104, 'الموارد'), (105, 112, 'البشرية')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'قام أحد الأشخاص بإبلاغي أنه يمكن حجز زيارة عن طريقك فبرجاء تسجيل زيارة لي فى أقرب وقت حيث أنني سائح تونسي وأريد الإستعلام عن بعض المعلومات مع الإدارة العليا' with intent 'Appointment'. Make sure the start and end values of entities ([(33, 42, 'new'), (95, 100, 'visitor'), (101, 105, 'تونسي'), (142, 156, 'الإدارة العليا')]) in the training data match the token boundaries ([(0, 3, 'قام'), (4, 7, 'أحد'), (8, 15, 'الأشخاص'), (16, 23, 'بإبلاغي'), (24, 27, 'أنه'), (28, 32, 'يمكن'), (33, 36, 'حجز'), (37, 42, 'زيارة'), (43, 45, 'عن'), (46, 51, 'طريقك'), (52, 58, 'فبرجاء'), (59, 64, 'تسجيل'), (65, 70, 'زيارة'), (71, 73, 'لي'), (74, 76, 'فى'), (77, 81, 'أقرب'), (82, 85, 'وقت'), (86, 89, 'حيث'), (90, 94, 'أنني'), (95, 99, 'سائح'), (100, 105, 'تونسي'), (106, 111, 'وأريد'), (112, 121, 'الإستعلام'), (122, 124, 'عن'), (125, 128, 'بعض'), (129, 138, 'المعلومات'), (139, 141, 'مع'), (142, 149, 'الإدارة'), (150, 156, 'العليا')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'لدي موعد حالي ، يرجى التحقق من رمز المقابلة الخاص بي' with intent 'Appointment'. Make sure the start and end values of entities ([(0, 9, 'existing')]) in the training data match the token boundaries ([(0, 3, 'لدي'), (4, 8, 'موعد'), (9, 13, 'حالي'), (16, 20, 'يرجى'), (21, 27, 'التحقق'), (28, 30, 'من'), (31, 34, 'رمز'), (35, 43, 'المقابلة'), (44, 49, 'الخاص'), (50, 52, 'بي')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'لقد حجزت بالفعل ولدي موعد حالي مع الموارد البشرية' with intent 'Appointment'. Make sure the start and end values of entities ([(17, 30, 'existing'), (34, 49, 'إدارة الموارد البشرية')]) in the training data match the token boundaries ([(0, 3, 'لقد'), (4, 8, 'حجزت'), (9, 15, 'بالفعل'), (16, 20, 'ولدي'), (21, 25, 'موعد'), (26, 30, 'حالي'), (31, 33, 'مع'), (34, 41, 'الموارد'), (42, 49, 'البشرية')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'لمقابلة موظف الموارد البشرية ، لدي موعد الآن معهم ، يرجى مسح الكود الخاص بي' with intent 'Appointment'. Make sure the start and end values of entities ([(8, 13, 'employee'), (31, 45, 'existing')]) in the training data match the token boundaries ([(0, 7, 'لمقابلة'), (8, 12, 'موظف'), (13, 20, 'الموارد'), (21, 28, 'البشرية'), (31, 34, 'لدي'), (35, 39, 'موعد'), (40, 44, 'الآن'), (45, 49, 'معهم'), (52, 56, 'يرجى'), (57, 60, 'مسح'), (61, 66, 'الكود'), (67, 72, 'الخاص'), (73, 75, 'بي')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'محتاج احدد موعد اجتماع مع محمود الذي يعمل هنا' with intent 'Appointment'. Make sure the start and end values of entities ([(6, 15, 'new'), (26, 32, 'محمود ')]) in the training data match the token boundaries ([(0, 5, 'محتاج'), (6, 10, 'احدد'), (11, 15, 'موعد'), (16, 22, 'اجتماع'), (23, 25, 'مع'), (26, 31, 'محمود'), (33, 37, 'الذي'), (38, 42, 'يعمل'), (43, 46, 'هنا')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'مرحبا ابغى احجز موعد جديد من فضلك' with intent 'Appointment'. Make sure the start and end values of entities ([(21, 26, 'new')]) in the training data match the token boundaries ([(0, 5, 'مرحبا'), (6, 10, 'ابغى'), (11, 15, 'احجز'), (16, 20, 'موعد'), (21, 25, 'جديد'), (26, 28, 'من'), (29, 33, 'فضلك')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'مرحبا لدي مشكله واريد الاجتماع بقسم الموارد البشرية وهذا رقمي الوظيفي 5165468498668' with intent 'Appointment'. Make sure the start and end values of entities ([(17, 30, 'new'), (31, 51, 'إدارة الموارد البشرية'), (70, 83, '5165468498668')]) in the training data match the token boundaries ([(0, 5, 'مرحبا'), (6, 9, 'لدي'), (10, 15, 'مشكله'), (16, 21, 'واريد'), (22, 30, 'الاجتماع'), (31, 35, 'بقسم'), (36, 43, 'الموارد'), (44, 51, 'البشرية'), (52, 56, 'وهذا'), (57, 61, 'رقمي'), (62, 69, 'الوظيفي'), (70, 83, '5165468498668')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'مسؤل الضرائب من الحكومة السعوديه يريد مقابلة مدير الحسابات فى الشركة' with intent 'Appointment'. Make sure the start and end values of entities ([(33, 44, 'new'), (50, 59, 'إدارة الحسابات')]) in the training data match the token boundaries ([(0, 4, 'مسؤل'), (5, 12, 'الضرائب'), (13, 15, 'من'), (16, 23, 'الحكومة'), (24, 32, 'السعوديه'), (33, 37, 'يريد'), (38, 44, 'مقابلة'), (45, 49, 'مدير'), (50, 58, 'الحسابات'), (59, 61, 'فى'), (62, 68, 'الشركة')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هذا الرقم 1245789582 يخص رقم الهوية الوطنية حقي وانا هنا لتحديد موعد مع عبد القادر رفعت' with intent 'Appointment'. Make sure the start and end values of entities ([(10, 20, '1245789582'), (29, 43, 'بطاقة الهوية'), (58, 68, 'new'), (72, 87, 'عبد القادر رفعت')]) in the training data match the token boundaries ([(0, 3, 'هذا'), (4, 9, 'الرقم'), (10, 20, '1245789582'), (21, 24, 'يخص'), (25, 28, 'رقم'), (29, 35, 'الهوية'), (36, 43, 'الوطنية'), (44, 47, 'حقي'), (48, 52, 'وانا'), (53, 56, 'هنا'), (57, 63, 'لتحديد'), (64, 68, 'موعد'), (69, 71, 'مع'), (72, 75, 'عبد'), (76, 82, 'القادر'), (83, 87, 'رفعت')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هذا هو رمز زيارتي ولدي موعد اليوم' with intent 'Appointment'. Make sure the start and end values of entities ([(19, 27, 'existing')]) in the training data match the token boundaries ([(0, 3, 'هذا'), (4, 6, 'هو'), (7, 10, 'رمز'), (11, 17, 'زيارتي'), (18, 22, 'ولدي'), (23, 27, 'موعد'), (28, 33, 'اليوم')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هل التقويم الخاص بك متاح لحجز موعد جديد؟' with intent 'Appointment'. Make sure the start and end values of entities ([(26, 39, 'new')]) in the training data match the token boundaries ([(0, 2, 'هل'), (3, 10, 'التقويم'), (11, 16, 'الخاص'), (17, 19, 'بك'), (20, 24, 'متاح'), (25, 29, 'لحجز'), (30, 34, 'موعد'), (35, 39, 'جديد')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هل يمكنني حجز موعد مع رجب أحمد من إدارة المخازن\n وأنا زائر مصري رقم تأشيرة \n هو 14563978' with intent 'Appointment'. Make sure the start and end values of entities ([(9, 19, 'new'), (22, 30, 'رجب أحمد'), (34, 47, 'إدارة المخازن'), (57, 62, 'visitor'), (63, 67, 'مصري'), (73, 83, 'تأشيرة \\n '), (86, 94, '14563978')]) in the training data match the token boundaries ([(0, 2, 'هل'), (3, 9, 'يمكنني'), (10, 13, 'حجز'), (14, 18, 'موعد'), (19, 21, 'مع'), (22, 25, 'رجب'), (26, 30, 'أحمد'), (31, 33, 'من'), (34, 39, 'إدارة'), (40, 47, 'المخازن'), (48, 49, 'n'), (52, 56, 'وأنا'), (57, 61, 'زائر'), (63, 67, 'مصري'), (69, 72, 'رقم'), (73, 79, 'تأشيرة'), (81, 82, 'n'), (83, 85, 'هو'), (86, 94, '14563978')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هل يمكنني حجز موعد مع رجب أحمد من إدارة تكنولوجيا المعلومات ورقم هاتفي 1453333378' with intent 'Appointment'. Make sure the start and end values of entities ([(9, 19, 'new'), (22, 30, 'رجب أحمد'), (34, 59, 'إدارة تكنولوجيا المعلومات'), (71, 81, '1453333378')]) in the training data match the token boundaries ([(0, 2, 'هل'), (3, 9, 'يمكنني'), (10, 13, 'حجز'), (14, 18, 'موعد'), (19, 21, 'مع'), (22, 25, 'رجب'), (26, 30, 'أحمد'), (31, 33, 'من'), (34, 39, 'إدارة'), (40, 49, 'تكنولوجيا'), (50, 59, 'المعلومات'), (60, 64, 'ورقم'), (65, 70, 'هاتفي'), (71, 81, '1453333378')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data
/opt/venv/lib/python3.7/site-packages/rasa/shared/utils/io.py:104: UserWarning: Misaligned entity annotation in message 'هلا اسمي سارة من أعمل فى إدارة المشتريات رقمى التعريفي هو 6565565 وأريد مقابلة هيا من إدارة المخازن' with intent 'Appointment'. Make sure the start and end values of entities ([(58, 65, '6565565'), (67, 78, 'new'), (79, 82, 'هيا'), (86, 99, 'إدارة المخازن')]) in the training data match the token boundaries ([(0, 3, 'هلا'), (4, 8, 'اسمي'), (9, 13, 'سارة'), (14, 16, 'من'), (17, 21, 'أعمل'), (22, 24, 'فى'), (25, 30, 'إدارة'), (31, 40, 'المشتريات'), (41, 45, 'رقمى'), (46, 54, 'التعريفي'), (55, 57, 'هو'), (58, 65, '6565565'), (66, 71, 'وأريد'), (72, 78, 'مقابلة'), (79, 82, 'هيا'), (83, 85, 'من'), (86, 91, 'إدارة'), (92, 99, 'المخازن')]). Common causes:
1) entities include trailing whitespaces or punctuation
2) the tokenizer gives an unexpected result, due to languages such as Chinese that don't use whitespace for word separation
More info at https://rasa.com/docs/rasa/training-data-format#nlu-training-data