Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Chao, Xiang, Wei, Wang, Bang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.10512
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929516575719424
author Liang, Chao
Xiang, Wei
Wang, Bang
author_facet Liang, Chao
Xiang, Wei
Wang, Bang
contents Event Causality Identification (ECI) aims at determining the existence of a causal relation between two events. Although recent prompt learning-based approaches have shown promising improvements on the ECI task, their performance are often subject to the delicate design of multiple prompts and the positive correlations between the main task and derivate tasks. The in-context learning paradigm provides explicit guidance for label prediction in the prompt learning paradigm, alleviating its reliance on complex prompts and derivative tasks. However, it does not distinguish between positive and negative demonstrations for analogy learning. Motivated from such considerations, this paper proposes an In-Context Contrastive Learning (ICCL) model that utilizes contrastive learning to enhance the effectiveness of both positive and negative demonstrations. Additionally, we apply contrastive learning to event pairs to better facilitate event causality identification. Our ICCL is evaluated on the widely used corpora, including the EventStoryLine and Causal-TimeBank, and results show significant performance improvements over the state-of-the-art algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10512
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle In-context Contrastive Learning for Event Causality Identification
Liang, Chao
Xiang, Wei
Wang, Bang
Information Retrieval
Machine Learning
Event Causality Identification (ECI) aims at determining the existence of a causal relation between two events. Although recent prompt learning-based approaches have shown promising improvements on the ECI task, their performance are often subject to the delicate design of multiple prompts and the positive correlations between the main task and derivate tasks. The in-context learning paradigm provides explicit guidance for label prediction in the prompt learning paradigm, alleviating its reliance on complex prompts and derivative tasks. However, it does not distinguish between positive and negative demonstrations for analogy learning. Motivated from such considerations, this paper proposes an In-Context Contrastive Learning (ICCL) model that utilizes contrastive learning to enhance the effectiveness of both positive and negative demonstrations. Additionally, we apply contrastive learning to event pairs to better facilitate event causality identification. Our ICCL is evaluated on the widely used corpora, including the EventStoryLine and Causal-TimeBank, and results show significant performance improvements over the state-of-the-art algorithms.
title In-context Contrastive Learning for Event Causality Identification
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2405.10512