In-context Contrastive Learning for Event Causality Identification

• URL: http://arxiv.org/abs/2405.10512v2
• Date: Fri, 27 Sep 2024 08:00:07 GMT
• Title: In-context Contrastive Learning for Event Causality Identification
• Authors: Chao Liang, Wei Xiang, Bang Wang,
• Abstract summary: Event Causality Identification aims at determining the existence of a causal relation between two events. Recent prompt learning-based approaches have shown promising improvements on the ECI task. This paper proposes an In-Context Contrastive Learning model that utilizes contrastive learning to enhance the effectiveness of both positive and negative demonstrations.
• Score: 26.132189768472067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning [99.05401042153214]
  In-context learning (ICL) is potentially attributed to two major abilities: task recognition (TR) and task learning (TL) We take the first step by examining the pre-training dynamics of the emergence of ICL. We propose a simple yet effective method to better integrate these two abilities for ICL at inference time.
  arXiv  Detail & Related papers  (2024-06-20T06:37:47Z)
• Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification [48.81069245141415]
  We introduce a novel contrastive loss function for multi-label text classification. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions. It demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets.
  arXiv  Detail & Related papers  (2024-04-12T11:12:16Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• Time-Series Contrastive Learning against False Negatives and Class Imbalance [17.43801009251228]
  We conduct theoretical analysis and find they have overlooked the fundamental issues: false negatives and class imbalance inherent in the InfoNCE loss-based framework. We introduce a straightforward modification grounded in the SimCLR framework, universally to models engaged in the instance discrimination task. We perform semi-supervised consistency classification and enhance the representative ability of minority classes.
  arXiv  Detail & Related papers  (2023-12-19T08:38:03Z)
• Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs [15.87963432758696]
  Un-sentence relation extraction (URE) aims to extract relations between named entities from raw text. We propose AugURE with both within-sentence pairs augmentation and augmentation through cross-sentence pairs extraction. Experiments on NYT-FB and TACRED datasets demonstrate that the proposed relation representation learning and a simple K-Means clustering achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-12-01T12:59:32Z)
• Conditional Supervised Contrastive Learning for Fair Text Classification [59.813422435604025]
  We study learning fair representations that satisfy a notion of fairness known as equalized odds for text classification via contrastive learning. Specifically, we first theoretically analyze the connections between learning representations with a fairness constraint and conditional supervised contrastive objectives.
  arXiv  Detail & Related papers  (2022-05-23T17:38:30Z)
• Delayed Reinforcement Learning by Imitation [31.932677462399468]
  We present a novel algorithm that learns how to act in a delayed environment from undelayed demonstrations. We show that DIDA obtains high performances with a remarkable sample efficiency on a variety of tasks.
  arXiv  Detail & Related papers  (2022-05-11T15:27:33Z)
• Self-Regulated Learning for Egocentric Video Activity Anticipation [147.9783215348252]
  Self-Regulated Learning (SRL) aims to regulate the intermediate representation consecutively to produce representation that emphasizes the novel information in the frame of the current time-stamp. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets.
  arXiv  Detail & Related papers  (2021-11-23T03:29:18Z)
• Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement [17.77752074834281]
  We propose CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. We adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model.
  arXiv  Detail & Related papers  (2021-06-03T07:50:50Z)
• Spectrum-Guided Adversarial Disparity Learning [52.293230153385124]
  We propose a novel end-to-end knowledge directed adversarial learning framework. It portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art.
  arXiv  Detail & Related papers  (2020-07-14T05:46:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.