Я пытаюсь обучить новый тип сущности «HE INST» - распознавать колледжи.
Это единственный новый лейбл. У меня есть длинный документ в виде необработанного текста. Я запустил NER и сохранил сущности в TRAIN DATA, а затем добавил новые метки сущностей в TRAIN_DATA (я заменил их в местах, где было перекрытие).
Обучающий цикл постоянен при значении потерь (~ 4000 для всех 15 текстов) и (~ 300) для отдельных данных. Почему это происходит, как правильно тренировать модель. У меня есть около 18 текстов с 40 новыми аннотированными объектами. Даже после всех итераций модель все еще не может правильно предсказать вывод.
Я не сильно изменил сценарий. Просто добавил en_core_web_lg, новый ярлык и мой TRAIN_DATA
Я пытаюсь отметить институты по данным резюме (C.V):
Это будет один из моих текстов в TRAIN_DATA: (расскажу про длинный текст)
У меня есть около 18 таких текстов, которые были добавлены в форму TRAIN_DATA
[("To perform better in my work each day. To increase my knowledge. To bring out my best by hardworking and improving my skills. To serve my parents and my family. To contribute my skills to my country. Marital ; Single Status Nationality \xe2\x80\x94: Indian Known . Parr . English, Malayalam, Hindi, Tamil Languages Hobby Playing cricket and football, Listening to music, Movies, Games. Father's ; V.N. Balappan Nair Name Mother's ; Saraswathy B Nair Name Believers Church Caarmel Engineering College R-Perunad Btech Electronics and communication engineering 6.09(Upto S6) 2015 - 2019 Marthoma Senior Secondary School Kozhencherry All India Senior School Certificate Examination 75% 2014 - 2015 Marthoma Senior Secondary School Kozhencherry Secondary School Examination 8.2 2012 - 2013 s@ INTERESTS Electronics, Sports s@ PERSONAL STRENGTHS Hardworking Loyal Good Team Spirit Good in mathematics ees IAA eM LANL NUL e (2 Problem Solving Skills rg DUS \\ TRAININGS completed the Vocational Industrial Training on Long Distance Communication Systems conducted by Southern Telecom Region, Bharat Sanchar Nigam Limited. Completed the internship training in Power Electronics Group(PEG), Tool Room, Fabrication Shop, Transform Winding, Electro Plating, Security And Surveillance Group(SSG), Special Products Group(SPG), Search And Rescue Beacon(SRB), Intelligent Tracking and Communication Project and Technology Development Center of Keltron Equipment Complex, Thiruvananthapuram. PROJECTS Final Year Project: Life Detection Using Quadcopter This project is useful at the time of natural calamities like flood earthquake etc... And can also be used in military applications as this device detects life signals using a PIR sensor and a thermal sensor. The components used in this are: PIR sensor, Thermal sensor, Arduino Nano, BEC, ESC, Quadcopter. Design project: Wireless Power Bank Wireless Power Bank enables us to charge our phone wordlessly. It can charge a device which is kept 10m(maximum) away from the adaptor without any obstacles in between. It uses the IR technology for power transmission. ACHIEVEMENTS & AWARDS Participated in Pecardio Debugging Conducted as a part of NAKSHATRA 2019, The Annual National Level Techno Cultural Fest held at Saingits College of Engineering, kottayam. Volunteered in Alexa One day workshop on Artificial intelligence. Completed a period of two year tenue with a total of 240 hours in the National Service Scheme activities and has attended NSS Annual Special Camp. Participant in Cricket and football at the Annual Sports Meets. DECLARATION do here by confirm that the information given in this form is true to the best of my knowledge and belief.", {'entities': [(29, 37, 'DATE'), (210, 223, 'ORG'), (241, 247, 'NORP'), (256, 260, 'PERSON'), (263, 270, 'LANGUAGE'), (272, 281, 'PERSON'), (283, 288, 'PERSON'), (290, 295, 'NORP'), (362, 375, 'EVENT'), (388, 401, 'PERSON'), (402, 420, 'PERSON'), (423, 445, 'PERSON'), (446, 490, 'HE INST'), (563, 574, 'DATE'), (575, 620, 'ORG'), (625, 668, 'ORG'), (669, 672, 'PERCENT'), (673, 684, 'DATE'), (685, 717, 'ORG'), (764, 775, 'DATE'), (779, 800, 'ORG'), (890, 893, 'ORG'), (909, 910, 'CARDINAL'), (963, 997, 'ORG'), (1001, 1036, 'ORG'), (1050, 1073, 'ORG'), (1075, 1103, 'ORG'), (1142, 1169, 'ORG'), (1172, 1181, 'ORG'), (1183, 1199, 'ORG'), (1201, 1218, 'ORG'), (1220, 1235, 'ORG'), (1275, 1301, 'ORG'), (1304, 1332, 'ORG'), (1335, 1355, 'ORG'), (1360, 1415, 'ORG'), (1419, 1444, 'ORG'), (1446, 1464, 'LOC'), (1475, 1494, 'EVENT'), (1797, 1809, 'GPE'), (1811, 1814, 'GPE'), (1816, 1819, 'ORG'), (1821, 1831, 'ORG'), (1849, 1888, 'ORG'), (1969, 1980, 'CARDINAL'), (2050, 2052, 'ORG'), (2088, 2122, 'ORG'), (2126, 2154, 'ORG'), (2168, 2182, 'EVENT'), (2188, 2194, 'DATE'), (2239, 2270, 'HE INST'), (2297, 2302, 'GPE'), (2303, 2310, 'DATE'), (2358, 2369, 'DATE'), (2370, 2378, 'DATE'), (2401, 2410, 'TIME'), (2414, 2441, 'ORG'), (2470, 2493, 'ORG'), (2534, 2557, 'EVENT')]})]
Сценарий приведен ниже: (Примечание: - функция eval используется для анализа TRAIN_DATA в списке после чтения его в виде строки из текстового файла ----- вы, скорее всего, знаете это, но на всякий случай)
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
import en_core_web_lg
from spacy.util import minibatch, compounding
# new entity label
LABEL = "HE INST"
with open('train_dump-backup.txt', 'r') as i_file:
t_data = i_file.read()
TRAIN_DATA=eval(t_data)
@plac.annotations(
model=("en_core_web_lg", "option", "m", str),
new_model_name=("NLP_INST", "option", "nm", str),
output_dir=("/home/drbinu/Downloads/NLP_INST", "option", "o", Path),
n_iter=("30", "option", "n", int),
)
def main(model=None, new_model_name="animal", output_dir=None, n_iter=30):
"""Set up the pipeline and entity recognizer, and train the new entity."""
random.seed(0)
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank("en") # create blank Language class
print("Created blank 'en' model")
# Add entity recognizer to model if it's not in the pipeline
# nlp.create_pipe works for built-ins that are registered with spaCy
if "ner" not in nlp.pipe_names:
ner = nlp.create_pipe("ner")
nlp.add_pipe(ner)
# otherwise, get it, so we can add labels to it
else:
ner = nlp.get_pipe("ner")
ner.add_label(LABEL) # add new entity label to entity recognizer
# Adding extraneous labels shouldn't mess anything up
ner.add_label("VEGETABLE")
if model is None:
optimizer = nlp.begin_training()
else:
optimizer = nlp.resume_training()
move_names = list(ner.move_names)
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
with nlp.disable_pipes(*other_pipes): # only train NER
sizes = compounding(1.0, 4.0, 1.001)
# batch up the examples using spaCy's minibatch
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
batches = minibatch(TRAIN_DATA, size=sizes)
losses = {}
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(texts, annotations, sgd=optimizer, drop=0.35, losses=losses)
print("Losses", losses)
# test the trained model
test_text = "B.Tech from Believers Church Caarmel Engineering College CGPA of 8.9"
doc = nlp(test_text)
print("Entities in '%s'" % test_text)
for ent in doc.ents:
print(ent.label_, ent.text)
# save model to output directory
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
nlp.meta["name"] = new_model_name # rename model
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
# Check the classes have loaded back consistently
assert nlp2.get_pipe("ner").move_names == move_names
doc2 = nlp2(test_text)
for ent in doc2.ents:
print(ent.label_, ent.text)
if __name__ == "__main__":
plac.call(main)