DeepAI
Log In Sign Up

SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction

06/03/2021
by   Shuang Zeng, et al.
0

Document-level relation extraction has attracted much attention in recent years. It is usually formulated as a classification problem that predicts relations for all entity pairs in the document. However, previous works indiscriminately represent intra- and inter-sentential relations in the same way, confounding the different patterns for predicting them. Besides, they create a document graph and use paths between entities on the graph as clues for logical reasoning. However, not all entity pairs can be connected with a path and have the correct logical reasoning paths in their graph. Thus many cases of logical reasoning cannot be covered. This paper proposes an effective architecture, SIRE, to represent intra- and inter-sentential relations in different ways. We design a new and straightforward form of logical reasoning module that can cover more logical reasoning chains. Experiments on the public datasets show SIRE outperforms the previous state-of-the-art methods. Further analysis shows that our predictions are reliable and explainable. Our code is available at https://github.com/DreamInvoker/SIRE.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/03/2021

Discriminative Reasoning for Document-level Relation Extraction

Document-level relation extraction (DocRE) models generally use graph ne...
01/13/2022

Document-level Relation Extraction with Context Guided Mention Integration and Inter-pair Reasoning

Document-level Relation Extraction (DRE) aims to recognize the relations...
07/05/2016

Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

Our goal is to combine the rich multistep inference of symbolic logical ...
03/26/2022

A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction

Document-level relation extraction (RE) aims to identify relations betwe...
08/31/2019

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

Document-level relation extraction is a complex human process that requi...
06/13/2019

Cognitive Knowledge Graph Reasoning for One-shot Relational Learning

Inferring new facts from existing knowledge graphs (KG) with explainable...
11/26/2022

Towards Better Document-level Relation Extraction via Iterative Inference

Document-level relation extraction (RE) aims to extract the relations be...