Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction

Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, Heuiseok Lim

Submission Type: Regular Short Paper

Submission Track: Information Extraction

Submission Track 2: Information Retrieval and Text Mining

Keywords: Cross-document relation extraction, Document relation extraction, Reasoning Path Construction

Abstract: Cross-document relation extraction (CodRED) task aims to infer the relation between two entities mentioned in different documents within a reasoning path. Previous studies have concentrated on merely capturing implicit relations between the entities. However, humans usually utilize explicit information chains such as hyperlinks or additional searches to find the relations between two entities. Inspired by this, we propose Path wIth expLOraTion (PILOT) that provides the enhanced reasoning path by exploring the explicit clue information within the documents. PILOT finds the bridging entities which directly guide the paths between the entities and then employs them as stepstones to navigate desirable paths. We show that models with PILOT outperform the baselines in the CodRED task. Furthermore, we offer a variety of analyses to verify the validity of the reasoning paths constructed through PILOT, including evaluations using large language models such as ChatGPT.

Submission Number: 2816