2026-09-20T08:52:52Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/115461 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Han, Jiawei 2022-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms The student, Yiqing Xie, accepted the attached license on 2022-04-15 at 15:03. The student, Yiqing Xie, submitted this Thesis for approval on 2022-04-15 at 15:08. This Thesis was approved for publication on 2022-04-15 at 15:19. DSpace SAF Submission Ingestion Package generated from Vireo submission #17691 on 2022-11-11 at 13:15:18 Evidence-enhanced document-level relation extraction Xie, Yiqing 2022-04-15 document-level relation extraction relation extraction information extraction Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the evidence, are often sufficient for humans to predict the relation of an entity pair. In this paper, we propose an evidence-enhanced framework, Eider, that empowers DocRE by efficiently extracting evidence and effectively fusing the extracted evidence in inference. We first jointly train an RE model with a lightweight evidence extraction model, which is efficient in both memory and runtime. Empirically, even training the evidence model on silver labels constructed by our heuristic rules can lead to better RE performance. We further design a simple yet effective inference process that makes RE predictions on both extracted evidence and the full document, then fuses the predictions through a blending layer. This allows Eider to focus on important sentences while still having access to the complete information in the document. Extensive experiments show that Eider outperforms state-of-the-art methods on three benchmark datasets (e.g., by 1.37/1.26 Ign F1/F1 on DocRED). Thesis eng https://hdl.handle.net/2142/115461 Copyright 2022 Yiqing Xie M.S. Thesis Computer Science University of Illinois at Urbana-Champaign Computer Science