分离作者风格与内容，提升文本归属识别准确率
Isolating authorship from content with semantic embeddings and contrastive learning
- 用语义模型生成难样本，增强对比学习以解耦风格与内容
- 在高难度场景下，准确率最高提升10%
- 适合需要精准作者识别的文本分析任务
作者风格与内容长期混杂，导致难以区分不同作者。现有神经模型虽能通过对比学习捕捉细微风格差异，但仍存在内容泄露问题。本文提出一种新方法：利用语义相似性模型合成硬负样本，结合InfoNCE对比学习，实现风格与内容嵌入空间的解耦，使嵌入更聚焦于风格特征。在两个数据集上进行消融实验，并测试跨领域泛化能力。结果表明，在高难度评估中（如多产作者），准确率最高提升10%；同时保留零样本迁移能力，适用于微调场景。
原文摘要 · Abstract (English)
Authorship has entangled style and content inside. Authors frequently write about the same topics in the same style, so when different authors write about the exact same topic the easiest way out to distinguish them is by understanding the nuances of their style. Modern neural models for authorship can pick up these features using contrastive learning, however, some amount of content leakage is always present. Our aim is to reduce the inevitable impact and correlation between content and authorship. We present a technique to use contrastive learning (InfoNCE) with additional hard negatives synthetically created using a semantic similarity model. This disentanglement technique aims to distance the content embedding space from the style embedding space, leading to embeddings more informed by style. We demonstrate the performance with ablations on two different datasets and compare them on out-of-domain challenges. Improvements are clearly shown on challenging evaluations on prolific authors with up to a 10% increase in accuracy when the settings are particularly hard. Trials on challenges also demonstrate the preservation of zero-shot capabilities of this method as fine tuning.
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。