即使词序发生变化，我如何能够一致地将一个单词映射到句子中的另一个单词，例如将症状映射到受影响的器官？

Question

例句：

“胸部因呼吸困难而受到影响”

和

“呼吸困难影响胸部”

所需关系：

“呼吸困难 -> 胸部”

我通过查看句子的依存树尝试了依存匹配，但仍然无法实现关系。

Answer 1

您应该根据您的具体情况使用

Relation Extraction

技术

Casual Relation Extraction

。主要目标是识别检测到的实体/事件之间是否存在随意关系。 SpaCy 中的简单实现如下所示：

import spacy

# Load spaCy's transformer-based model
nlp = spacy.load("en_core_web_sm")

# Define a sample text for relationship extraction
text = "Chest is affected due to breathlessness"
# Process the text with spaCy
doc = nlp(text)

# Create a list to store extracted relationships
relationships = []

# Iterate through the sentences in the document
for sent in doc.sents:
    # Iterate through the named entities (people, organizations etc.) in the sentence
    for token in sent:
        if token.dep_ in ["attr", "nsubj", "dobj"]:
            relationships.append((ent.text, token.text))

for named_entities, relation in relationships:
    print(f"{named_entities} --> {relation}")

您可以根据您的特定上下文/问题进一步提取 NER 实体，并应用过滤器以确保仅分析您所需的 NER 的标记的关系。