Distantly Supervised Relation Extraction in Federated Settings

08/12/2020
by   Dianbo Sui, et al.
0

This paper investigates distantly supervised relation extraction in federated settings. Previous studies focus on distant supervision under the assumption of centralized training, which requires collecting texts from different platforms and storing them on one machine. However, centralized training is challenged by two issues, namely, data barriers and privacy protection, which make it almost impossible or cost-prohibitive to centralize data from multiple platforms. Therefore, it is worthy to investigate distant supervision in the federated learning paradigm, which decouples the model training from the need for direct access to the raw data. Overcoming label noise of distant supervision, however, becomes more difficult in federated settings, since the sentences containing the same entity pair may scatter around different platforms. In this paper, we propose a federated denoising framework to suppress label noise in federated settings. The core of this framework is a multiple instance learning based denoising method that is able to select reliable instances via cross-platform collaboration. Various experimental results on New York Times dataset and miRNA gene regulation relation dataset demonstrate the effectiveness of the proposed method.

READ FULL TEXT
research
05/28/2018

Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training

Existing neural relation extraction (NRE) models rely on distant supervi...
research
08/22/2021

Improving Distantly Supervised Relation Extraction with Self-Ensemble Noise Filtering

Distantly supervised models are very popular for relation extraction sin...
research
12/07/2020

H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction

Although distant supervision automatically generates training data for r...
research
05/11/2017

Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix

Distant supervision significantly reduces human efforts in building trai...
research
09/13/2019

Leveraging 2-hop Distant Supervision from Table Entity Pairs for Relation Extraction

Distant supervision (DS) has been widely used to automatically construct...
research
05/24/2018

Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning

Distant supervision has become the standard method for relation extracti...
research
06/21/2021

Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

With recent advances in distantly supervised (DS) relation extraction (R...

Please sign up or login with your details

Forgot password? Click here to reset