CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification
Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8287 https://ink.library.smu.edu.sg/context/sis_research/article/9290/viewcontent/2023.acl_long.604__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9290 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-92902023-11-10T08:26:28Z CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification CHEN, Meiqi CAO, Yixin ZHANG, Yan LIU, Zhiwei Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail throughout the document, with most other events serving as either their cause or consequence. In this paper, we manually annotate central events for a systematical investigation and propose a novel DECI model, CHEER, which performs high-order reasoning while considering event centrality. First, we summarize a general GNN-based DECI model and provide a unified view for better understanding. Second, we design an Event Interaction Graph (EIG) involving the interactions among events (e.g., coreference) and event pairs, e.g., causal transitivity, cause(A, B) AND cause(B, C) → cause(A, C). Finally, we incorporate event centrality information into the EIG reasoning network via well-designed features and multi-task learning. We have conducted extensive experiments on two benchmark datasets. The results present great improvements (5.9% F1 gains on average) and demonstrate the effectiveness of each main component. 2023-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8287 info:doi/10.18653/v1/2023.acl-long.604 https://ink.library.smu.edu.sg/context/sis_research/article/9290/viewcontent/2023.acl_long.604__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University benchmark datasets; causal relations; coreference; high-order; higher-order; identification modeling; interaction graphs; level graphs; multitask learning; ordering events Computer Sciences OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
benchmark datasets; causal relations; coreference; high-order; higher-order; identification modeling; interaction graphs; level graphs; multitask learning; ordering events Computer Sciences OS and Networks |
spellingShingle |
benchmark datasets; causal relations; coreference; high-order; higher-order; identification modeling; interaction graphs; level graphs; multitask learning; ordering events Computer Sciences OS and Networks CHEN, Meiqi CAO, Yixin ZHANG, Yan LIU, Zhiwei CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
description |
Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail throughout the document, with most other events serving as either their cause or consequence. In this paper, we manually annotate central events for a systematical investigation and propose a novel DECI model, CHEER, which performs high-order reasoning while considering event centrality. First, we summarize a general GNN-based DECI model and provide a unified view for better understanding. Second, we design an Event Interaction Graph (EIG) involving the interactions among events (e.g., coreference) and event pairs, e.g., causal transitivity, cause(A, B) AND cause(B, C) → cause(A, C). Finally, we incorporate event centrality information into the EIG reasoning network via well-designed features and multi-task learning. We have conducted extensive experiments on two benchmark datasets. The results present great improvements (5.9% F1 gains on average) and demonstrate the effectiveness of each main component. |
format |
text |
author |
CHEN, Meiqi CAO, Yixin ZHANG, Yan LIU, Zhiwei |
author_facet |
CHEN, Meiqi CAO, Yixin ZHANG, Yan LIU, Zhiwei |
author_sort |
CHEN, Meiqi |
title |
CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
title_short |
CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
title_full |
CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
title_fullStr |
CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
title_full_unstemmed |
CHEER: Centrality-aware high-order event reasoning network for document-level event causality identification |
title_sort |
cheer: centrality-aware high-order event reasoning network for document-level event causality identification |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8287 https://ink.library.smu.edu.sg/context/sis_research/article/9290/viewcontent/2023.acl_long.604__1_.pdf |
_version_ |
1783955665807474688 |