Weakly Supervised Multilingual Causality Extraction from Wikipedia

Hashimoto, Chikara

doi:10.18653/v1/d19-1296

Cited by 21 publications

(13 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first research line, early methods usually design various features tailored for causal expressions, such as lexical and syntactic patterns Girju, 2013, 2014a,b), causality cues or markers (Riaz and Girju, 2010;Do et al, 2011;Hidey and McKeown, 2016), statistical information (Beamer and Girju, 2009;Hashimoto et al, 2014), and temporal patterns (Riaz and Girju, 2014a;Ning et al, 2018). Then, researchers resort to a large amount of labeled data to mitigate the efforts of feature engineering and to learn diverse causal expressions (Hu et al, 2017;Hashimoto, 2019). To alleviate the annotation cost, recent methods leverage Pre-trained Language Models (PLMs, e.g., BERT (Devlin et al, 2019)) for the ECI task and have achieved SOTA performance (Kadowaki et al, 2019;Zuo et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

“…As shown in Figure 1, given the text "... the outage 2 was caused by a terrestrial break in the fiber in Egypt ...", an ECI model should predict if there is a causal relation between two events triggered by "outage 2 " and "break". Causality can reveal reliable structures of texts, which is beneficial to widespread applications, such as machine reading comprehension (Berant et al, 2014), question answering (Oh et al, 2016), and future event forecasting (Hashimoto, 2019).…”

Section: Introductionmentioning

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

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

show abstract

“…Event causality identification (ECI) is a very important task in natural language processing area, which has attracted extensive attention in the past few years. Early studies for the task are feature-based methods which utilize lexical and syntactic features (Riaz and Girju, 2013;Gao et al, 2019), explicit causal patterns (Beamer and Girju, 2009;Do et al, 2011;, and statistical causal associations (Riaz and Girju, 2014;Hashimoto et al, 2014;Hashimoto, 2019) for the task. With the development of deep learning, neural network-based methods have been proposed for the task and achieved the state-of-the-art performance (Kruengkrai et al, 2017;Kadowaki et al, 2019;Zuo et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

Cao¹,

Zuo²,

Chen³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Identifying causal relations of events is an important task in natural language processing area. However, the task is very challenging, because event causality is usually expressed in diverse forms that often lack explicit causal clues. Existing methods cannot handle well the problem, especially in the condition of lacking training data. Nonetheless, humans can make a correct judgement based on their background knowledge, including descriptive knowledge and relational knowledge. Inspired by it, we propose a novel Latent Structure Induction Network (LSIN) to incorporate the external structural knowledge into this task. Specifically, to make use of the descriptive knowledge, we devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge. To leverage the relational knowledge, we propose a Relational Graph Induction module which is able to automatically learn a reasoning structure for event causality reasoning. Experimental results on two widely used datasets indicate that our approach significantly outperforms previous state-of-the-art methods.

show abstract

“…There are a lot of work in temporal (D'Souza and Ng, 2013;Chambers et al, 2014;Ning et al, 2018b;Meng and Rumshisky, 2018;Han et al, 2019;Vashishtha et al, 2020;Wright-Bettner et al, 2020) and causal (Bethard and Martin, 2008;Do et al, 2011;Riaz and Girju, 2013;Roemmele and Gordon, 2018;Hashimoto, 2019) relation extraction. Mirza and Tonelli (2016) and Ning et al (2018a) extract both in a single framework.…”

Section: Extracting Causal and Temporal Relationsmentioning

confidence: 99%

ExcavatorCovid: Extracting Events and Relations from Text Corpora for Temporal and Causal Analysis for COVID-19

Min¹,

Rozonoyer²,

Qiu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Timely responses from policy makers to mitigate the impact of the COVID-19 pandemic rely on a comprehensive grasp of events, their causes, and their impacts. These events are reported at such a speed and scale as to be overwhelming. In this paper, we present Excava-torCovid, a machine reading system that ingests open-source text documents (e.g., news and scientific publications), extracts COVID-19 related events and relations between them, and builds a Temporal and Causal Analysis Graph (TCAG). Excavator will help government agencies alleviate the information overload, understand likely downstream effects of political and economic decisions and events related to the pandemic, and respond in a timely manner to mitigate the impact of COVID-19. We expect the utility of Excavator to outlive the COVID-19 pandemic: analysts and decision makers will be empowered by Excavator to better understand and solve complex problems in the future. An interactive TCAG visualization is available at http://afrl402. bbn.com:5050/index.html. We also released a demonstration video at https:// vimeo.com/528619007.

show abstract

Weakly Supervised Multilingual Causality Extraction from Wikipedia

Cited by 21 publications

References 49 publications

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

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

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

ExcavatorCovid: Extracting Events and Relations from Text Corpora for Temporal and Causal Analysis for COVID-19

Contact Info

Product

Resources

About