KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision

Zuo, Xinyu; Chen, Yubo; Liu, Kang; Zhao, Jun

doi:10.48550/arxiv.2010.10833

Cited by 2 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the largest widely used public ECI dataset is the EventStoryLine Corpus (Caselli and Vossen 2017), which contains 258 documents consisting of 4,316 sentences, and only 1,770 out of 7,805 event pairs are annotated as causal relations. This situation poses challenges to existing data-hungry deep learning-based approaches for ECI tasks (Zuo et al 2020;Cao et al 2021;, which mainly utilize language models to model sentence context and treat the ECI task as a binary classification problem. Therefore, how to efficiently utilize limited data is one essential problem to be solved for ECI.…”

Section: Intra-sentence Causalitymentioning

confidence: 99%

“…Such approaches rely on the domain knowledge of human. Deep learning-based approaches for ECI (Kadowaki et al 2019;Zuo et al 2020) leverage pretrained language models (e.g., BERT (Devlin et al 2018)) and commonsense knowledge sources (e.g., ConceptNet (Speer, Chin, and Havasi 2017)) to improve the performance. To deal with implicit causal relations, Cao et al (2021) conducts a descriptive graph induction module combining external knowledge and achieves promising results.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Identify Event Causality with Knowledge and Analogy

Zhao

Zheng

et al. 2023

AAAI

View full text Add to dashboard Cite

Event causality identification (ECI) aims to identify the causal relationship between events, which plays a crucial role in deep text understanding. Due to the diversity of real-world causality events and difficulty in obtaining sufficient training data, existing ECI approaches have poor generalizability and struggle to identify the relation between seldom seen events. In this paper, we propose to utilize both external knowledge and internal analogy to improve ECI. On the one hand, we utilize a commonsense knowledge graph called ConceptNet to enrich the description of an event sample and reveal the commonalities or associations between different events. On the other hand, we retrieve similar events as analogy exam- ples and glean useful experiences from such analogous neigh- bors to better identify the relationship between a new event pair. By better understanding different events through exter- nal knowledge and making an analogy with similar events, we can alleviate the data sparsity issue and improve model gener- alizability. Extensive evaluations on two benchmark datasets show that our model outperforms other baseline methods by around 18% on the F1-value on average

show abstract

Section: Intra-sentence Causalitymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Identify Event Causality with Knowledge and Analogy

Zhao

Zheng

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…These methods involve the generation of supplementary training data through knowledge graph supervision or the direct incorporation of knowledge graph triplets associated with events into textual contexts. Additionally, knowledge bases like FrameNet [18], WordNet [19], and VerbNet [20] have also been employed to extract external causal knowledge for the Event Causality Identification (ECI) task [21,22]. These lexical knowledge bases contribute to augmenting the understanding of causal relationships in ECI through their diverse information structures.…”

Section: Introductionmentioning

confidence: 99%

PTEKC: Pre-training with Event knowledge of ConceptNet for Cross-lingual Event Causality Identification

Zhu,

Yu,

Huang

et al. 2024

Preprint

View full text Add to dashboard Cite

Event Causality Identification (ECI) task aims to identify causal relations between events in texts, which is beneficial to understanding the precise logic meaning expressed by a text. Although existing event causality identification works based on fine-tuned PLMs have achieved promising results, they suffer from prohibitive computation costs, catastrophic forgetting of distributional knowledge, as well as poor interpretability. Particularly in low-resource and cross-linguistic scenarios, existing multilingual models are generally confronted with the so-called curse of multilinguality, language bias, and hence result in low accuracy and generalization ability. In this paper, we propose a paradigm, termed Pre-training with Event Knowledge of ConceptNet (PTEKC), to couple Multilingual Pre-trained Language Models (MPLMs) with external event knowledge for Cross-lingual Event Causality Identification. Specifically, we have developed a parameter-sharing adapter plugin that facilitates the integration of event knowledge into the frozen Pretrained Language Model (PLM). This approach significantly diminishes the number of trainable parameters and greatly reduces the risk of catastrophic forgetting. Our Adapter integrates multilingual-aligned event knowledge into the MPLMs through two designed pre-training tasks, namely span masking and self-supervised link prediction. Extensive experiments on the benchmark dataset MECI show that PTEKC is parameter-efficient and can effectively incorporate knowledge for improving cross-lingual event causality identification.

show abstract

KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision

Cited by 2 publications

References 23 publications

Identify Event Causality with Knowledge and Analogy

Identify Event Causality with Knowledge and Analogy

PTEKC: Pre-training with Event knowledge of ConceptNet for Cross-lingual Event Causality Identification

Contact Info

Product

Resources

About