用语义向量压缩文档，生成可控制的摘要
Vec2Summ: Text Summarization via Probabilistic Sentence Embeddings
- 将文档集压缩为一个语义均值向量，再通过生成模型还原
- 在主流数据集上摘要质量接近大模型，且更高效
- 适合需要大规模抽象和可控生成的场景
我们提出Vec2Summ，一种新颖的抽象摘要方法，将摘要任务视为语义压缩。该方法在语义嵌入空间中用单个均值向量表示文档集合，捕捉语料库的核心含义。为生成流畅摘要，采用嵌入反演——利用生成语言模型将该均值向量解码为自然语言。为提升重建质量并捕捉一定程度的主题多样性，引入以均值为中心的高斯分布采样，类似集成学习中的袋装（bagging），通过可控随机性增强输出鲁棒性与多样性。Vec2Summ解决了基于大模型摘要方法的关键局限：规避上下文长度限制，通过语义参数实现可解释且可控生成，并随语料规模线性扩展，仅需$O(d + d^2)$参数。实验表明，对于主题聚焦、顺序无关的语料，Vec2Summ能生成连贯摘要，主题覆盖与效率方面媲美直接使用大模型的摘要方法，尽管细节粒度稍弱。这些结果凸显其在强调可扩展性、语义控制与语料级抽象场景中的潜力。
原文摘要 · Abstract (English)
We propose Vec2Summ, a novel method for abstractive summarization that frames the task as semantic compression. Vec2Summ represents a document collection using a single mean vector in the semantic embedding space, capturing the central meaning of the corpus. To reconstruct fluent summaries, we perform embedding inversion -- decoding this mean vector into natural language using a generative language model. To improve reconstruction quality and capture some degree of topical variability, we introduce stochasticity by sampling from a Gaussian distribution centered on the mean. This approach is loosely analogous to bagging in ensemble learning, where controlled randomness encourages more robust and varied outputs. Vec2Summ addresses key limitations of LLM-based summarization methods. It avoids context-length constraints, enables interpretable and controllable generation via semantic parameters, and scales efficiently with corpus size -- requiring only $O(d + d^2)$ parameters. Empirical results show that Vec2Summ produces coherent summaries for topically focused, order-invariant corpora, with performance comparable to direct LLM summarization in terms of thematic coverage and efficiency, albeit with less fine-grained detail. These results underscore Vec2Summ's potential in settings where scalability, semantic control, and corpus-level abstraction are prioritized.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。