Log In Sign Up

A Generative Model for Relation Extraction and Classification

by   Jian Ni, et al.

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.


page 1

page 2

page 3

page 4


Relation Extraction with Contextualized Relation Embedding (CRE)

Relation extraction is the task of identifying relation instance between...

Investigations on Knowledge Base Embedding for Relation Prediction and Extraction

We report an evaluation of the effectiveness of the existing knowledge b...

A Question-answering Based Framework for Relation Extraction Validation

Relation extraction is an important task in knowledge acquisition and te...

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

Solving math word problems requires deductive reasoning over the quantit...

Relation Extraction as Two-way Span-Prediction

The current supervised relation classification (RC) task uses a single e...

Online Inference for Relation Extraction with a Reduced Feature Set

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