starmen1265
d039537f1d
Add requirement for improving SRT semantic segmentation: - Current rule-based approach cannot identify topic transitions - Document 4 potential solutions with trade-offs - Recommended approach: two-stage with optional LLM Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.9 KiB
1.9 KiB
Semantic Segmentation for SRT Processing
Status: Backlog Priority: Medium Source: User feedback during v1.5 testing
Problem
Current SemanticSegmenter uses simple heuristic rules:
- Time gap > 3 seconds
- Paragraph length > 500 characters
This approach cannot identify semantic topic transitions.
Example Case
Video: BV1MiPSz2ErY (科学透镜 - 5 topics in one video)
- 银河系中心的超大黑洞人马座A*其实不是黑洞
- 银河系和仙女座星系等构成的本星系群陷入巨大物质薄片
- 科学家为世界上97%的建筑生成3D模型
- 雷暴的形成
- 闪电的形成
Current segmentation mixes these topics together.
Potential Solutions
Option 1: Transition Keyword Detection (Simple)
- Detect common transition phrases: "接下来", "另外", "第二个", etc.
- Pros: Fast, no API calls
- Cons: Low accuracy, many videos lack explicit transitions
Option 2: LLM-Based Segmentation (Accurate)
- Ask LLM to analyze entire subtitle and identify topic boundaries
- Pros: Highest accuracy, understands semantics
- Cons: Extra API cost, token limits for long videos
Option 3: Two-Stage Approach (Balanced)
- Stage 1: Simple rule-based segmentation (current)
- Stage 2: LLM checks paragraph beginnings for new topics
- Pros: Most cases use simple rules, LLM only for key decisions
- Cons: More complex implementation
Option 4: Embedding-Based Similarity
- Calculate semantic similarity between adjacent paragraphs
- Low similarity = topic boundary
- Pros: No LLM API calls, runs locally
- Cons: Requires embedding model, implementation complexity
Recommendation
Phase 1 (Quick Win): Transition keyword detection + improve prompt
Phase 2 (Full Solution): Two-stage approach with optional LLM semantic segmentation
Success Criteria
- Topics are separated correctly
- Each paragraph covers a single coherent topic
- No false splits within a topic