DeepAI
Log In Sign Up

A Generative Model for Relation Extraction and Classification

02/26/2022
by   Jian Ni, et al.
0

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model for relation extraction and classification (which we call GREC), where RE is modeled as a sequence-to-sequence generation task. We explore various encoding representations for the source and target sequences, and design effective schemes that enable GREC to achieve state-of-the-art performance on three benchmark RE datasets. In addition, we introduce negative sampling and decoding scaling techniques which provide a flexible tool to tune the precision and recall performance of the model. Our approach can be extended to extract all relation triples from a sentence in one pass. Although the one-pass approach incurs certain performance loss, it is much more computationally efficient.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/19/2020

Relation Extraction with Contextualized Relation Embedding (CRE)

Relation extraction is the task of identifying relation instance between...
02/06/2018

Investigations on Knowledge Base Embedding for Relation Prediction and Extraction

We report an evaluation of the effectiveness of the existing knowledge b...
04/07/2021

A Question-answering Based Framework for Relation Extraction Validation

Relation extraction is an important task in knowledge acquisition and te...
03/19/2022

Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction

Solving math word problems requires deductive reasoning over the quantit...
10/09/2020

Relation Extraction as Two-way Span-Prediction

The current supervised relation classification (RC) task uses a single e...
04/18/2015

Online Inference for Relation Extraction with a Reduced Feature Set

Access to web-scale corpora is gradually bringing robust automatic knowl...