Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for a single sentence or document, cross-document RE has emerged to address relations across multiple long documents. Given the nature of long documents in cross-document RE, extracting document embeddings is challenging due to the length constraints of pre-trained language models. Therefore, we propose REward-based Input Construction (REIC), the first learning-based sentence selector for cross-document RE. REIC extracts sentences based on relational evidence, enabling the RE module to effectively infer relations. Since supervision of evidence sentences is generally unavailable, we train REIC using reinforcement learning with RE prediction scores as rewards. Experimental results demonstrate the superiority of our method over heuristic methods for different RE structures and backbones in cross-document RE. Our code is publicly available at https://github.com/aailabkaist/REIC.

翻译：关系抽取（RE）是自然语言处理中的一项基础任务，旨在识别文本中目标实体间的关系。尽管许多RE方法针对单一句子或单篇文档设计，跨文档RE已发展为处理多篇长文档间关系的重要方向。鉴于跨文档RE中长文档的特性，由于预训练语言模型的长度限制，提取文档嵌入表示面临挑战。为此，我们提出基于奖励的输入构建方法（REIC），这是首个基于学习的跨文档RE句子选择器。REIC依据关系证据抽取句子，使RE模块能够有效推断关系。由于证据句子的监督信号通常难以获取，我们采用强化学习训练REIC，并以RE预测分数作为奖励。实验结果表明，在跨文档RE任务中，针对不同RE架构和骨干模型，我们的方法均优于启发式方法。代码已公开于 https://github.com/aailabkaist/REIC。