用句子骨架相似度衡量叙事连贯性，发现句子级模型更优
Skeleton-based Coherence Modeling in Narratives
- 提出骨架相似度网络(SSN)，量化相邻句骨架相似性
- SSN优于余弦/欧氏距离等基线方法，但整体仍弱于句子级模型
- 表明当前连贯性建模应聚焦句子而非子结构，适合文本生成研究者
文本连贯性建模一直是自然语言处理领域的长期课题，对检测不连贯结构并辅助作者修正具有重要意义。近期工作尝试用神经网络从单个句子中提取骨架，并基于骨架生成下一句以实现连贯叙事生成。本研究旨在探究连续句子间骨架的一致性是否可作为文本连贯性的有效指标。为此，我们提出一种新的句子/骨架相似度网络（SSN），用于建模句子对间的连贯性。实验表明，该网络在性能上显著优于余弦相似度、欧氏距离等基线方法。尽管骨架看似是建模连贯性的有力候选，但我们的结果表明，句子级模型在评估文本连贯性方面仍优于骨架级模型，这说明当前最先进的连贯性建模技术正朝着正确方向发展——即处理完整句子而非其子部分。
原文摘要 · Abstract (English)
Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to extract a skeleton from one sentence, and then use that skeleton to generate the next sentence for coherent narrative story generation. In this project, we aim to study if the consistency of skeletons across subsequent sentences is a good metric to characterize the coherence of a given body of text. We propose a new Sentence/Skeleton Similarity Network (SSN) for modeling coherence across pairs of sentences, and show that this network performs much better than baseline similarity techniques like cosine similarity and Euclidean distance. Although skeletons appear to be promising candidates for modeling coherence, our results show that sentence-level models outperform those on skeletons for evaluating textual coherence, thus indicating that the current state-of-the-art coherence modeling techniques are going in the right direction by dealing with sentences rather than their sub-parts.
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。