.png){kind=icon}
.png){kind=icon}
Return
Interaction-and-Response Network for Distantly Supervised Relation Extraction
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3233971.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Distantly supervised relation extraction (DSRE) aims to identify semantic relations from massive plain texts. A broad range of the prior research has leveraged a series of selective attention mechanisms over sentences in a bag to extract relation features without considering dependencies among the relation features. As a result, potential discriminative information existed in the dependencies is ignored, causing a decline in the performance of extracting entity relations. In this article, we focus on going beyond the selective attention mechanisms and propose a new framework termed interaction-and-response network (IR-Net) that adaptively recalibrates the features of sentence, bag, and group levels by explicitly modeling interdependencies among the features on each level. The IR-Net consists of a series of interactive and responsive modules throughout feature hierarchy, seeking to strengthen its power of learning salient discriminative features for distinguishing entity relations. We conduct extensive experiments on three benchmark DSRE datasets, including NYT-10, NYT-16, and Wiki-20m. The experimental results demonstrate that the IR-Net brings obvious improvements in performance when comparing ten state-of-the-art DSRE methods for entity relation extraction.
Keywords:
Feature extraction
Task analysis
Knowledge based systems
Neural networks
Data mining
Training
Semantics
Distant supervision
interaction
relation extraction
response
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W