About: HIN: Hierarchical Inference Network for Document-Level Relation Extraction

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: HIN: Hierarchical Inference Network for Document-Level Relation Extraction Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	HIN: Hierarchical Inference Network for Document-Level Relation Extraction
Creator	Fang, Fang Cao, Yanan Zhang, Zhenyu Yin, Pengfei Cao, Jiangxia Tang, Hengzhu Wang, Shi
Source	PMC
abstract	Document-level RE requires reading, inferring and aggregating over multiple sentences. From our point of view, it is necessary for document-level RE to take advantage of multi-granularity inference information: entity level, sentence level and document level. Thus, how to obtain and aggregate the inference information with different granularity is challenging for document-level RE, which has not been considered by previous work. In this paper, we propose a Hierarchical Inference Network (HIN) to make full use of the abundant information from entity level, sentence level and document level. Translation constraint and bilinear transformation are applied to target entity pair in multiple subspaces to get entity-level inference information. Next, we model the inference between entity-level information and sentence representation to achieve sentence-level inference information. Finally, a hierarchical aggregation approach is adopted to obtain the document-level inference information. In this way, our model can effectively aggregate inference information from these three different granularities. Experimental results show that our method achieves state-of-the-art performance on the large-scale DocRED dataset. We also demonstrate that using BERT representations can further substantially boost the performance.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47426-3_16
has license	no-cc
sha1sum (hex)	992c791664998635bfe6fb0a3042cdb09f737383
schema:url	https://doi.org/10.1007/978-3-030-47426-3_16
resource representing a document's title	HIN: Hierarchical Inference Network for Document-Level Relation Extraction
has PubMed Central identifier	PMC7206265
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:992c791664998635bfe6fb0a3042cdb09f737383#body_text
is schema:about of	named entity 'Inference' named entity 'AGGREGATING' named entity 'TO TAKE' named entity 'EXPERIMENTAL RESULTS' named entity 'SENTENCE' named entity 'HIERARCHICAL' named entity 'TRANSFORMATION' named entity 'DOCUMENT' named entity 'USING' named entity 'ADVANTAGE' named entity 'boost' named entity 'sentences' named entity 'entity' named entity 'Translation' named entity 'performance' named entity 'aggregate' named entity 'aggregate' named entity 'abundant' named entity 'latent space' named entity 'Word Embeddings' named entity 'LSTM' named entity 'semantic' named entity 'bilinear function' named entity 'probability' named entity 'learning rate' named entity 'Chris Carter' named entity 'semantic relation' named entity 'vanilla' named entity 'Nisei' named entity 'Fox Mulder' named entity 'vanilla' named entity 'LSTM' named entity 'Fox Mulder' named entity '0.9' named entity 'CNN' named entity 'Galaxy S series' named entity 'Ign' named entity 'Samsung Galaxy S9' named entity 'natural language' named entity 'hidden units' named entity 'Galaxy S series' named entity 'FFNN' named entity 'bilinear function' named entity 'cross entropy' named entity 'F1 score' named entity 'hierarchical aggregation' named entity 'probability' named entity 'knowledge base' named entity 'CNN' named entity 'Chris Carter' named entity 'Samsung' named entity 'GloVe' named entity 'BCE' named entity 'feed-forward neural network' named entity 'GloVe' named entity 'hierarchical aggregation' named entity 'plain text' named entity 'deep learning' named entity 'semantic' named entity 'CNN' named entity 'hierarchical aggregation' named entity 'el al' named entity 'semantic' named entity 'Context-Aware' named entity 'linear projection' named entity 'word embeddings' named entity 'Robert Kingsbury Huntington' named entity 'CNN' named entity 'coreference' named entity 'latent space' named entity 'linear transformation' named entity 'el al' named entity 'hierarchical aggregation' named entity 'science fiction television' named entity 'F1 score' named entity 'natural language understanding' named entity 'commonsense knowledge'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software