Lifelong Event Detection with Embedding Space Separation and Compaction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Qin, Chengwei, Chen, Ruirui, Zhao, Ruochen, Xia, Wenhan, Joty, Shafiq
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917629451567104
author Qin, Chengwei
Chen, Ruirui
Zhao, Ruochen
Xia, Wenhan
Joty, Shafiq
author_facet Qin, Chengwei
Chen, Ruirui
Zhao, Ruochen
Xia, Wenhan
Joty, Shafiq
contents To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples can still result in substantial forgetting of previously acquired knowledge, which may occur due to the potential overlap between the feature distribution of new data and the previously learned embedding space. Moreover, the model suffers from overfitting on the few memory samples rather than effectively remembering learned patterns. To address the challenges of forgetting and overfitting, we propose a novel method based on embedding space separation and compaction. Our method alleviates forgetting of previously learned tasks by forcing the feature distribution of new data away from the previous embedding space. It also mitigates overfitting by a memory calibration mechanism that encourages memory data to be close to its prototype to enhance intra-class compactness. In addition, the learnable parameters of the new task are initialized by drawing upon acquired knowledge from the previously learned task to facilitate forward knowledge transfer. With extensive experiments, we demonstrate that our method can significantly outperform previous state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lifelong Event Detection with Embedding Space Separation and Compaction
Qin, Chengwei
Chen, Ruirui
Zhao, Ruochen
Xia, Wenhan
Joty, Shafiq
Computation and Language
To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples can still result in substantial forgetting of previously acquired knowledge, which may occur due to the potential overlap between the feature distribution of new data and the previously learned embedding space. Moreover, the model suffers from overfitting on the few memory samples rather than effectively remembering learned patterns. To address the challenges of forgetting and overfitting, we propose a novel method based on embedding space separation and compaction. Our method alleviates forgetting of previously learned tasks by forcing the feature distribution of new data away from the previous embedding space. It also mitigates overfitting by a memory calibration mechanism that encourages memory data to be close to its prototype to enhance intra-class compactness. In addition, the learnable parameters of the new task are initialized by drawing upon acquired knowledge from the previously learned task to facilitate forward knowledge transfer. With extensive experiments, we demonstrate that our method can significantly outperform previous state-of-the-art approaches.
title Lifelong Event Detection with Embedding Space Separation and Compaction
topic Computation and Language
url https://arxiv.org/abs/2404.02507