CLAIFeb 27, 2022

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

arXiv:2202.13352v1640 citations
Originality Incremental advance
AI Analysis

This work addresses noise reduction in relation extraction for natural language processing, presenting an incremental improvement by integrating cross-level interactions.

The paper tackled the problem of noisy sentences in distantly supervised relation extraction by proposing a hierarchical contrastive learning framework, resulting in significant performance improvements over strong baselines on various mainstream datasets.

Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level de-noising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a hierarchical contrastive learning Framework for Distantly Supervised relation extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multi-head self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes