通过点关系推断区间关系，提升细粒度时序关系分类性能
Looking for the Bottleneck in Fine-grained Temporal Relation Classification
- 先判断时间实体端点的点关系，再组合成区间关系
- 在TempEval-3上达到70.1%时序感知分数，刷新纪录
- 适合需要精准时序理解的任务，如事件链分析
时序关系分类旨在确定文本中两个时间实体之间的时序关系。尽管自然语言处理取得进展，该任务仍具挑战性。早期研究涵盖事件与时间表达之间的全面时序关系，但因任务复杂，数据集逐步简化，近年方法多聚焦事件对间关系并仅使用部分关系。本文重新审视完整时间区间间关系的分类目标，提出基于点关系推断区间关系的方法——Interval from Point。该方法首先识别时间实体端点间的点关系，再将这些点关系解码为区间关系。在TempEval-3数据集上的评估显示，该方法可取得有效结果，时序感知分数达70.1%，创下新基准记录。
原文摘要 · Abstract (English)
Temporal relation classification is the task of determining the temporal relation between pairs of temporal entities in a text. Despite recent advancements in natural language processing, temporal relation classification remains a considerable challenge. Early attempts framed this task using a comprehensive set of temporal relations between events and temporal expressions. However, due to the task complexity, datasets have been progressively simplified, leading recent approaches to focus on the relations between event pairs and to use only a subset of relations. In this work, we revisit the broader goal of classifying interval relations between temporal entities by considering the full set of relations that can hold between two time intervals. The proposed approach, Interval from Point, involves first classifying the point relations between the endpoints of the temporal entities and then decoding these point relations into an interval relation. Evaluation on the TempEval-3 dataset shows that this approach can yield effective results, achieving a temporal awareness score of $70.1$ percent, a new state-of-the-art on this benchmark.
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。