让句子脱离上下文也能被理解，靠智能选内容和排序
Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning
- 先拆句为语义独立单元，再选相关上下文补缺
- 在多个数据集上优于现有方法，语义完整性和连贯性更强
- 适合需要精准提取句子的推理与证据生成任务
从文档中提取句子作为证据或推理步骤是许多NLP任务的常见操作。然而，提取出的句子常因缺乏必要上下文（如指代关系、背景信息）而难以理解。为此，我们提出一种零样本去上下文化的内容选择与规划框架，旨在确定句子在无上下文时应包含哪些内容及其呈现顺序。具体而言，给定一个可能存在歧义的句子及其上下文，我们首先将其分割为基本语义独立单元；然后识别句子中潜在歧义的单元，并根据其话语关系从上下文中提取相关单元；最后生成内容计划，通过为每个歧义单元补充相关上下文单元来重写句子。实验结果表明，该方法在句子去上下文化任务中表现优异，生成的句子具有更好的语义完整性与话语连贯性，优于现有方法。
原文摘要 · Abstract (English)
Extracting individual sentences from a document as evidence or reasoning steps is commonly done in many NLP tasks. However, extracted sentences often lack context necessary to make them understood, e.g., coreference and background information. To this end, we propose a content selection and planning framework for zero-shot decontextualisation, which determines what content should be mentioned and in what order for a sentence to be understood out of context. Specifically, given a potentially ambiguous sentence and its context, we first segment it into basic semantically-independent units. We then identify potentially ambiguous units from the given sentence, and extract relevant units from the context based on their discourse relations. Finally, we generate a content plan to rewrite the sentence by enriching each ambiguous unit with its relevant units. Experimental results demonstrate that our approach is competitive for sentence decontextualisation, producing sentences that exhibit better semantic integrity and discourse coherence, outperforming existing methods.
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。