we also provide a IE tool based on ChatGPT, you can see in ChatIE
Note: we set a default openai key in the tool, you can tell us if the key reach the limit.
GPT4IE (GPT for Information Extraction) is a open-source and powerful IE tool demo. Enhanced by GPT3.5 and prompting, it aims to automatically extract structured information from a raw sentence and make a valuable in-depth analysis of the input sentence. Harnessing valuable structured information helps corporations make incisive and business–improving decisions.
We support the following functions:
Task | Name | Lauguages |
---|---|---|
RE | entity-relation joint extraction | Chinese, English |
NER | named entity recoginzation | Chinese, English |
EE | event extraction | Chinese, English |
This task aims to extract triples from plain texts, such as (China, capital, Beijing) , (《如懿传》,
- sentence: a plain text.
- relation type list (rtl)* : ['relation type 1', 'relation type 2', ...]
- subject type list (stl)* : ['subject type 1', 'subject type 2', ...]
- object type list (otl)* : ['object type 1', 'object type 2', ...]
PS: * denote optional, we set default value for them. But for better extraction, you should specify the three list according to application scenarios.
sentence: Bob worked for Google in Beijing, the capital of China.
rtl: ['location-located_in', 'administrative_division-country', 'person-place_lived', 'person-company', 'person-nationality', 'company-founders', 'country-administrative_divisions', 'person-children', 'country-capital', 'deceased_person-place_of_death', 'neighborhood-neighborhood_of', 'person-place_of_birth']
stl: ['organization', 'person', 'location', 'country']
otl: ['person', 'location', 'country', 'organization', 'city']
ouptut:
sentence:
rtl: ['
otl: ['
ouptut:
This task aims to extract entities from plain texts, such as (LOC, Beijing) , (
- sentence: a plain text.
- entity type list (etl)* : ['entity type 1', 'entity type 2', ...]
PS: * denote optional, we set default value for it. But for better extraction, you should specify the list according to application scenarios.
sentence: Bob worked for Google in Beijing, the capital of China.
etl: ['LOC', 'MISC', 'ORG', 'PER']
ouptut:
sentence:
etl: ['组织
ouptut:
This task aims to extract event from plain texts, such as {Life-Divorce: {Person: Bob, Time: today, Place: America}} , {竞赛
- sentence: a plain text.
- event type list (etl)* : {'event type 1': ['argument role 1', 'argument role 2', ...], ...}
PS: * denote optional, we set default value for it. But for better extraction, you should specify the list according to application scenarios.
sentence: Yesterday Bob and his wife got divorced in Guangzhou.
etl: {'Personnel:Elect': ['Person', 'Entity', 'Position', 'Time', 'Place'], 'Business:Declare-Bankruptcy': ['Org', 'Time', 'Place'], 'Justice:Arrest-Jail': ['Person', 'Agent', 'Crime', 'Time', 'Place'], 'Life:Divorce': ['Person', 'Time', 'Place'], 'Life:Injure': ['Agent', 'Victim', 'Instrument', 'Time', 'Place']}
ouptut:
sentence:
etl: {'组织
ouptut:
- Run
npm install
to download required dependencies. - Run
npm run start
. GPT4IE should open up in a new browser tab. - note: node-version v14.17.4 npm-version 9.6.0
- you need have an Open-AI key.