Skip to main content

vi-core-nlp is a library that supports Vietnamese NER by pattern matching .

Project description

NER for Vietnamese Medical Appointment Chatbot

Usage

Extract person name

text = "tôi cần đặt bác sĩ tạ biên cương"
print(extractor.extract_person_name(text)
{'entities': [{'start': 19, 'end': 32, 'entity': 'person_name', 'value': 'Tạ Biên Cương', 'confidence': 1.0, 'extractor': 'pattern'}]}

Extract Date
the value is the timestamp value

text = "tôi sinh vào ngày 21-3-1997"
extractor.extract_date(text)
{'entities': [{'start': 0, 'end': 5, 'entity': 'time', 'value': 1628562600.0, 'confidence': 1.0, 'extractor': 'absolute_pattern'}]}

Extract Time

text = '14:50 ngày 7 tháng 6'
print(extractor.extract_time(text,return_value=True)) #return value only
{'entities': [{'start': 7, 'end': 9, 'entity': 'time', 'value': 1628560800.0, 'confidence': 1.0, 'extractor': 'absolute_pattern'}]}

Map department/gender to keys

text = 'rai'
res = extractor.map_gender_to_key(text)
print(res)
# {'key': 'GEN01', 'text': 'rai', 'value': 'trai'}
text = 'tiêu hóa'
res = extractor.map_dep_to_key(text)
print(res)
# {'key': 'SP008', 'text': 'tiêu hóa', 'value': 'tiêu hóa'}

From symptoms to Department

text = "dạo này tôi thấy trong người mệt mỏi, thần kinh căng thẳng do cách ly covid quá lâu"
res = extractor.extract_symptoms(text)
{'entities': [{'start': 29, 'end': 32, 'entity': 'symptom', 'value': 'mệt', 'confidence': 1.0, 'extractor': 'fuzzy_matching'}, {'start': 39, 'end': 48, 'entity': 'symptom', 'value': 'thần kinh', 'confidence': 1.0, 'extractor': 'fuzzy_matching'}, {'start': 49, 'end': 59, 'entity': 'symptom', 'value': 'căng thẳng', 'confidence': 1.0, 'extractor': 'fuzzy_matching'}]}

Extract Department Keys directly

res = extractor.extract_symptoms(text,get_dep_keys=True,top_k=3) 
[('SP012', 1.0), ('SP001', 0.0), ('SP002', 0.0)]

Search department from list of symptoms

text = ['ho', 'sổ mũi', 'đau họng', 'đau đầu', 'nghẹt mũi']
res = extractor.get_department_from_symptoms(text,top_k=3)
[('SP018', 1.0), ('SP006', 0.6), ('SP009', 0.4)]

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vi_nlp_core-1.1.8.tar.gz (120.6 kB view hashes)

Uploaded Source

Built Distribution

vi_nlp_core-1.1.8-py3-none-any.whl (126.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page