用注意力机制筛选关键句，再用NLI判断真假关系，高效定位文本中的支持与反驳。
A Straightforward Pipeline for Targeted Entailment and Contradiction Detection
- 先用注意力得分找与目标句相关的候选句
- 再用预训练NLI模型分类为支持或矛盾关系
- 结合注意力强度过滤，精准找出重要语义关系
文档中句子间关系的识别对事实核查、论点挖掘和文本摘要等任务至关重要。核心挑战在于确定哪些句子是特定主张的支持前提或矛盾句。现有方法存在权衡：Transformer注意力能捕捉显著文本关联，但缺乏明确语义标签；而自然语言推理（NLI）模型可分类句子对关系，却独立于上下文显著性。本文提出一种融合两者优势的直接流程：首先通过聚合词级注意力分数，识别与用户选定目标句具有上下文相关性的候选句；随后使用预训练NLI模型将每个候选句分类为前提（蕴含）或矛盾。通过注意力显著性分数对NLI结果进行过滤，该方法能高效提取任意给定主张在文本中的最重要语义关系。
原文摘要 · Abstract (English)
Finding the relationships between sentences in a document is crucial for tasks like fact-checking, argument mining, and text summarization. A key challenge is to identify which sentences act as premises or contradictions for a specific claim. Existing methods often face a trade-off: transformer attention mechanisms can identify salient textual connections but lack explicit semantic labels, while Natural Language Inference (NLI) models can classify relationships between sentence pairs but operate independently of contextual saliency. In this work, we introduce a method that combines the strengths of both approaches for a targeted analysis. Our pipeline first identifies candidate sentences that are contextually relevant to a user-selected target sentence by aggregating token-level attention scores. It then uses a pretrained NLI model to classify each candidate as a premise (entailment) or contradiction. By filtering NLI-identified relationships with attention-based saliency scores, our method efficiently isolates the most significant semantic relationships for any given claim in a text.
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。