Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement

Zuo, Xinyu; Cao, Pengfei; Chen, Yubo; Liu, Kang; Zhao, Jun; Peng, Weihua; Chen, Yuguang

doi:10.18653/v1/2021.findings-acl.190

Cited by 24 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing models generally complete classification under the premise of supervision, the key point is how to extract clues and how to represent the semantics of causality. Extracting effective clues of contextual event causality requires the use of various text features, including syntactic features [4], lexical features, explicit causal patterns [5], statistical causality, etc.…”

Section: Event Relation Extractionmentioning

confidence: 99%

Learning Event Logic Graph Knowledge for Credit Risk Forecast

Wang,

Shang

et al. 2023

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

With the development of event knowledge graph technology, researchers have solved the singleness problem of event graph based on temporal relationship by constructing event logic graph, but have not integrated the multiple relationships among events with time series data for trend prediction. In addition, due to the impact of COVID-19, corporate credit risks have been gradually exposed in recent years, and defaults have occurred frequently. The technology of event graph and event logic graph is mostly used for event schema induction, script induction, etc., but abundant graph knowledge is not well exploited for forecast task.To fill this gap, we construct an event logic graph by extracting various types of event relationships, such as causal relationship, sequential relationship, parallel relationship, and reversal relationship. Different types of edges among events are used to represent different relationships. Combined with the time series of corporate credit bonds, a temporal convolutional network driven by event logic graph is built, and applied to forecast corporate credit risk.We extract structured events from financial news, construct event logic graph and learn the graph knowledge. Then, the event logic graph embedding is combined with time series of bonds to forecast whether the corporate will default. Experiments show that the proposed method outperforms baseline methods in forecasting credit risk.

show abstract

Section: Event Relation Extractionmentioning

confidence: 99%

Learning Event Logic Graph Knowledge for Credit Risk Forecast

Wang,

Shang

et al. 2023

International Conferences on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…To deal with implicit causal relations, Cao et al (2021) incorporate the external knowledge from ConceptNet (Speer et al, 2017) for reasoning, which achieves promising results. Zuo et al (2021a) learn contextspecific causal patterns from external causal statements and incorporate them into a target ECI model. Zuo et al (2021b) propose a data augmentation method to further solve the data lacking problem.…”

Section: Related Workmentioning

confidence: 99%

“…( 4) LearnDA (Zuo et al, 2021b), which uses knowledge bases to augment training data. ( 5) CauSeRL (Zuo et al, 2021a), which learns context-specific causal patterns from external causal statements for ECI.…”

Section: Baselinesmentioning

confidence: 99%

See 1 more Smart Citation

ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification

Chen¹,

Cao²,

Deng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Document-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. It poses a great challenge of across-sentence reasoning without clear causal indicators. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-theart (SOTA) methods upon two aspects. First, we formulate DECI as a node classification problem by constructing an event relational graph, without the needs of prior knowledge or tools. Second, ERGO seamlessly integrates event-pair relation classification and global inference, which leverages a Relational Graph Transformer (RGT) to capture the potential causal chain. Besides, we introduce edgebuilding strategies and adaptive focal loss to deal with the massive false positives caused by common spurious correlation. Extensive experiments on two benchmark datasets show that ERGO significantly outperforms previous SOTA methods (13.1% F1 gains on average). We have conducted extensive quantitative analysis and case studies to provide insights for future research directions (Section 4.8).

show abstract

“…In many papers about Event Causality Identification (ECI) (Gao et al, 2019;Zuo et al, 2021b;Cao et al, 2021;Zuo et al, 2021a, the two datasets used for benchmarking are CausalTime-Bank and EventStoryLine (Caselli and Vossen, 2017). These datasets are unsuitable for span detection since their arguments are event headwords only.…”

Section: Related Workmentioning

confidence: 99%

Event Causality Identification with Causal News Corpus - Shared Task 3, CASE 2022

Tan¹,

Hettiarachchi²,

Hürriyetoğlu³

et al. 2022

Proceedings of the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events From Text (CAS

View full text Add to dashboard Cite

The Event Causality Identification Shared Task of CASE 2022 involved two subtasks working on the Causal News Corpus. Subtask 1 required participants to predict if a sentence contains a causal relation or not. This is a supervised binary classification task. Subtask 2 required participants to identify the Cause, Effect and Signal spans per causal sentence. This could be seen as a supervised sequence labeling task. For both subtasks, participants uploaded their predictions for a held-out test set, and ranking was done based on binary F1 and macro F1 scores for Subtask 1 and 2, respectively. This paper summarizes the work of the 17 teams that submitted their results to our competition and 12 system description papers that were received. The best F1 scores achieved for Subtask 1 and 2 were 86.19% and 54.15%, respectively. All the top-performing approaches involved pretrained language models fine-tuned to the targeted task. We further discuss these approaches and analyze errors across participants' systems in this paper.

show abstract

Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement

Cited by 24 publications

References 28 publications

Learning Event Logic Graph Knowledge for Credit Risk Forecast

Learning Event Logic Graph Knowledge for Credit Risk Forecast

ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification

Event Causality Identification with Causal News Corpus - Shared Task 3, CASE 2022

Contact Info

Product

Resources

About