import requests
import pdf2image
import pytesseract pdf = requests.get('https://arxiv.org/pdf/2110.03526.pdf')
doc = pdf2image.convert_from_bytes(pdf.content) # Get the article text
article = []
for page_number, page_data in enumerate(doc): txt = pytesseract.image_to_string(page_data).encode("utf-8") # Sixth page are only references if page_number < 6: article.append(txt.decode("utf-8"))
article_txt = " ".join(article)
import nltk
nltk.download('punkt') def clean_text(text): """Remove section titles and figure descriptions from text""" clean = "n".join([row for row in text.split("n") if (len(row.split(" "))) > 3 and not (row.startswith("(a)")) and not row.startswith("Figure")]) return clean text = article_txt.split("INTRODUCTION")[1]
ctext = clean_text(text)
sentences = nltk.tokenize.sent_tokenize(ctext)
import hashlib def query_raw(text, url="https://bern.korea.ac.kr/plain"): """Biomedical entity linking API""" return requests.post(url, data={'sample_text': text}).json() entity_list = []
# The last sentence is invalid
for s in sentences[:-1]: entity_list.append(query_raw(s)) parsed_entities = []
for entities in entity_list: e = [] # If there are not entities in the text if not entities.get('denotations'): parsed_entities.append({'text':entities['text'], 'text_sha256': hashlib.sha256(entities['text'].encode('utf-8')).hexdigest()}) continue for entity in entities['denotations']: other_ids = [id for id in entity['id'] if not id.startswith("BERN")] entity_type = entity['obj'] entity_name = entities['text'][entity['span']['begin']:entity['span']['end']] try: entity_id = [id for id in entity['id'] if id.startswith("BERN")][0] except IndexError: entity_id = entity_name e.append({'entity_id': entity_id, 'other_ids': other_ids, 'entity_type': entity_type, 'entity': entity_name}) parsed_entities.append({'entities':e, 'text':entities['text'], 'text_sha256': hashlib.sha256(entities['text'].encode('utf-8')).hexdigest()})
from neo4j import GraphDatabase
import pandas as pd host = 'bolt://3.236.182.55:7687'
user = 'neo4j'
password = 'hydrometer-ditches-windings'
driver = GraphDatabase.driver(host,auth=(user, password)) def neo4j_query(query, params=None): with driver.session() as session: result = session.run(query, params) return pd.DataFrame([r.values() for r in result], columns=result.keys())
neo4j_query("""
MATCH (a:Article)
UNWIND $data as row
MERGE (s:Sentence{id:row.text_sha256})
SET s.text = row.text
MERGE (a)-[:HAS_SENTENCE]->(s)
WITH s, row.entities as entities
UNWIND entities as entity
MERGE (e:Entity{id:entity.entity_id})
ON CREATE SET e.other_ids = entity.other_ids, e.name = entity.entity, e.type = entity.entity_type
MERGE (s)-[m:MENTIONS]->(e)
ON CREATE SET m.count = 1
ON MATCH SET m.count = m.count + 1
""", {'data': parsed_entities})
您可以执行以下 Cypher 查询来检查构造的图：
MATCH p=(a:Article)-[:HAS_SENTENCE]->()-[:MENTIONS]->(e:Entity)
RETURN p LIMIT 25
MATCH (e1:Entity)<-[:MENTIONS]-()-[:MENTIONS]->(e2:Entity)
MATCH (e1:Entity)<-[:MENTIONS]-()-[:MENTIONS]->(e2:Entity)
WHERE id(e1) < id(e2)
RETURN e1.name as entity1, e2.name as entity2, count(*) as cooccurrence
ORDER BY cooccurrence
DESC LIMIT 3
MATCH (a:Author)-[:WROTE]->()-[:HAS_SENTENCE]->()-[:MENTIONS]->(e:Entity)
RETURN a.name as author, e.name as entity,
MATCH (a:Author)-[:WROTE]->()-[:HAS_SENTENCE]->()-[:MENTIONS]->(e:Entity)
RETURN a.name as author, e.name as entity, count(*) as count
ORDER BY count DESC
LIMIT 5
import itertools
# Candidate sentence where there is more than a single entity present
candidates = [s for s in parsed_entities if (s.get('entities')) and (len(s['entities']) > 1)]
predicted_rels = []
for c in candidates: combinations = itertools.combinations([{'name':x['entity'], 'id':x['entity_id']} for x in c['entities']], 2) for combination in list(combinations): try: ranked_rels = extractor.rank(text=c['text'].replace(",", " "), head=combination[0]['name'], tail=combination[1]['name']) # Define threshold for the most probable relation if ranked_rels[0][1] > 0.85: predicted_rels.append({'head': combination[0]['id'], 'tail': combination[1]['id'], 'type':ranked_rels[0][0], 'source': c['text_sha256']}) except: pass # Store relations to Neo4j
neo4j_query("""
UNWIND $data as row
MATCH (source:Entity {id: row.head})
MATCH (target:Entity {id: row.tail})
MATCH (text:Sentence {id: row.source})
MERGE (source)-[:REL]->(r:Relation {type: row.type})-[:REL]->(target)
MERGE (text)-[:MENTIONS]->(r)
""", {'data': predicted_rels})
我们存储关系以及用于在图中提取该关系的源文本。
提取的关系存储在图中。 图片由作者提供。
您可以使用以下 Cypher 查询检查提取的实体与源文本之间的关系：
MATCH (s:Entity)-[:REL]->(r:Relation)-[:REL]->(t:Entity), (r)<-[:MENTIONS]-(st:Sentence)
RETURN s.name as source_entity, t.name as target_entity, r.type as type, st.text as source_text
MATCH (e:Entity)
WHERE e.name = "Epidermolysis bullosa"
WITH e, [id in e.other_ids WHERE id contains "MESH" | split(id,":")[1]][0] as meshId
CALL apoc.load.json("https://id.nlm.nih.gov/mesh/lookup/details?descriptor=" + meshId) YIELD value
RETURN value
