论文标题
实体和证据指导的关系提取
Entity and Evidence Guided Relation Extraction for DocRED
论文作者
论文摘要
文档级别的关系提取是一项具有挑战性的任务，需要对多个句子进行推理才能预测文档中的关系。在本文中，我们为此任务提供了联合培训Frameworke2Gre（实体和证据指导的关系提取）。首先，我们将实体引导的序列作为预训练的语言模型（例如Bert，Roberta）引入。这些实体指导的序列帮助预先训练的语言模型（LM）专注于与实体相关的文档领域。其次，我们通过将其内部注意力概率用作证据预测的其他功能来指导预训练的语言模型的微调。我们的新方法鼓励预先训练的语言模型专注于实体和支持/证据句子。我们在DoCred上评估了我们的E2GRE方法，该方法是最近发布的大规模数据集，用于提取关系。我们的方法能够在所有指标上在公共排行榜上取得最新的结果，这表明我们的E2GRE既有效又对关系提取和证据预测有效。
Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task. First, we introduce entity-guided sequences as inputs to a pre-trained language model (e.g. BERT, RoBERTa). These entity-guided sequences help a pre-trained language model (LM) to focus on areas of the document related to the entity. Secondly, we guide the fine-tuning of the pre-trained language model by using its internal attention probabilities as additional features for evidence prediction.Our new approach encourages the pre-trained language model to focus on the entities and supporting/evidence sentences. We evaluate our E2GRE approach on DocRED, a recently released large-scale dataset for relation extraction. Our approach is able to achieve state-of-the-art results on the public leaderboard across all metrics, showing that our E2GRE is both effective and synergistic on relation extraction and evidence prediction.
