2026-09-21T00:29:35Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/114027 2023-07-11 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Ji, Heng 2022-04-29T21:47:48Z 2024-04-29T21:47:53Z 2021-12 Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-12-01 The student, Qi Zeng, accepted the attached license on 2021-12-09 at 10:50. The student, Qi Zeng, submitted this Thesis for approval on 2021-12-09 at 10:57. This Thesis was approved for publication on 2021-12-09 at 13:26. DSpace SAF Submission Ingestion Package generated from Vireo submission #17432 on 2022-04-06 at 17:18:05 Made available in DSpace on 2022-04-29T21:47:48Z (GMT). No. of bitstreams: 2 ZENG-THESIS-2021.pdf: 1376324 bytes, checksum: 8ef3728b5e032cb6b2d3b7451c93dce3 (MD5) LICENSE.txt: 4204 bytes, checksum: 02f6f03cd1403ec2d84926fa98beaba3 (MD5) Previous issue date: 2021-12-09 Embargo set by: Seth Robbins for item 123392 Lift date: 2024-04-29T21:47:53Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system U of I Only application/pdf en text Event network embedding Zeng, Qi 2021-12-09 Computer science 2022-04-29T21:47:48Z Current methods for event representation ignore related events in a corpus-level global context. For a deep and comprehensive understanding of complex events, we introduce a new task, Event Network Embedding, which aims to represent events by capturing the connections among events. We propose a novel framework, Global Event Network Embedding (GENE), that encodes the event network with a multi-view graph encoder while preserving the graph topology and node semantics. The graph encoder is trained by minimizing both structural and semantic losses. We develop a new series of structured probing tasks, and show that our approach effectively outperforms baseline models on node typing, argument role classification, and event coreference resolution. As a direct application, We introduce a new task, Unsupervised Event Schema Graph Matching, which aims to align event instance graphs and event schema graphs by finding node correspondence. We develop the first benchmark and collect a dataset of 3,740 event instance graphs from IED-scenario news articles, 75 of which are paired with 4 event schema graphs by human annotation. Our analysis on this task sheds light on the shortcomings of current state-of-the-art models on this event understanding task. Thesis eng http://hdl.handle.net/2142/114027 Copyright 2021 Qi Zeng Computer Science Computer Science University of Illinois at Urbana-Champaign Thesis M.S.