高级抽取

pip install semantica
# 或安装所有可选依赖：
pip install semantica[all]

# 安装 Semantica
!pip install -q semantica

# 导入高级语义抽取所需的全部组件
from semantica.semantic_extract import (
    EventDetector, CoreferenceResolver, TripletExtractor,
    SemanticAnalyzer, SemanticNetworkExtractor, LLMEnhancer, ExtractionValidator
)

# 示例文本：包含事件、共指与三元组信息
text = "Apple Inc. was founded by Steve Jobs in 1976. The company is now led by Tim Cook."

# 步骤 1：事件检测
event_detector = EventDetector()
events = event_detector.detect_events(text)

print(f"Detected {len(events)} events")
for event in events[:3]:
    print(f"  Event: {event.event_type} - {event.text[:50]}")

# 步骤 2：共指消解——将指向同一实体的不同表述归并
coreference_resolver = CoreferenceResolver()

coreferences = coreference_resolver.resolve(text)

print(f"Resolved {len(coreferences)} coreference chains")

# 步骤 3：抽取 RDF 三元组（主语-谓词-宾语）
triplet_extractor = TripletExtractor()

triplets = triplet_extractor.extract_triplets(text)

print(f"Extracted {len(triplets)} triplets")
for triplet in triplets[:3]:
    print(f"  ({triplet.get('subject', '')}, {triplet.get('predicate', '')}, {triplet.get('object', '')})")

# 步骤 4：语义分析——标注句子中的语义角色
semantic_analyzer = SemanticAnalyzer()

semantic_roles = semantic_analyzer.analyze_semantic_roles(text)

print(f"Analyzed semantic roles: {len(semantic_roles)}")

# 步骤 5：抽取语义网络（节点与边）
semantic_network_extractor = SemanticNetworkExtractor()

semantic_network = semantic_network_extractor.extract_network(text)

print(f"Extracted semantic network with {len(semantic_network.get('nodes', []))} nodes")
print(f"Edges: {len(semantic_network.get('edges', []))}")

# 步骤 6：使用 LLM 增强抽取结果
llm_enhancer = LLMEnhancer()

enhanced_extractions = llm_enhancer.enhance_extractions(events, text)

print(f"Enhanced {len(enhanced_extractions)} extractions")

# 步骤 7：验证抽取结果并输出置信度
extraction_validator = ExtractionValidator()

validation_result = extraction_validator.validate(events, text)

print(f"Extraction validation:")
print(f"  Valid: {validation_result.valid}")
print(f"  Confidence: {validation_result.confidence:.3f}")