About: Partial Domain Adaptation for Relation Extraction Based on Adversarial Learning

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

About: Partial Domain Adaptation for Relation Extraction Based on Adversarial Learning Goto Sponge NotDistinct Permalink

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

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Partial Domain Adaptation for Relation Extraction Based on Adversarial Learning
Creator	Yang, Juan Cao, Xiaofei Meng, Xiangbin
Source	PMC
abstract	Relation extraction methods based on domain adaptation have begun to be extensively applied in specific domains to alleviate the pressure of insufficient annotated corpus, which enables learning by utilizing the training data set of a related domain. However, the negative transfer may occur during the adaptive process due to differences in data distribution between domains. Besides, it is difficult to achieve a fine-grained alignment of relation category without fully mining the multi-mode data structure. Furthermore, as a common application scenario, partial domain adaptation (PDA) refers to domain adaptive behavior when the relation class set of a specific domain is a subset of the related domain. In this case, some outliers belonging to the related domain will reduce the performance of the model. To solve these problems, a novel model based on a multi-adversarial module for partial domain adaptation (MAPDA) is proposed in this study. We design a weight mechanism to mitigate the impact of noise samples and outlier categories, and embed several adversarial networks to realize various category alignments between domains. Experimental results demonstrate that our proposed model significantly improves the state-of-the-art performance of relation extraction implemented in domain adaptation.
has issue date	2020-05-07(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49461-2_6
has license	no-cc
sha1sum (hex)	15605173bf3349312e4eb10e57b331c0156addac
schema:url	https://doi.org/10.1007/978-3-030-49461-2_6
resource representing a document's title	Partial Domain Adaptation for Relation Extraction Based on Adversarial Learning
has PubMed Central identifier	PMC7250590
schema:publication	The Semantic Web
resource representing a document's body	covid:15605173bf3349312e4eb10e57b331c0156addac#body_text
is schema:about of	named entity 'outliers' named entity 'Relation' named entity 'impact' named entity 'Partial' named entity 'TRAINING' named entity 'study' named entity 'model' named entity 'domain' named entity 'based' named entity 'subset' named entity 'negative' named entity 'case' named entity 'belonging' named entity 'specific' named entity 'data structure' named entity 'domain adaptation' named entity 'neural networks' named entity 'Relation extraction' named entity 'information extraction' named entity 'pre-trained' named entity 'feature space' named entity 'Relation extraction' named entity 'syntactic' named entity 'neural network' named entity 'semantic relationship' named entity 'probability' named entity 'semantic network' named entity 'validation set' named entity 'sparsity' named entity 'recurrent neural network' named entity 'CNN' named entity 'PDA' named entity 'deep learning' named entity 'CNN' named entity 'relation extraction' named entity 'classification model' named entity 'machine-readable' named entity 'word2vec' named entity 'feature extraction' named entity 'New York' named entity 'objective function' named entity 'CNN' named entity 'domain adaptation' named entity 'probability' named entity 'data set' named entity 'CNN' named entity 'prior knowledge' named entity 'CNN' named entity 'Freebase' named entity 'neural network' named entity 'type of data' named entity 'feature vectors' named entity 'domain adaptation' named entity 'Freebase' named entity 'adversarial learning' named entity 'domain adaptation' named entity 'adaptive learning' named entity 'CNN' named entity 'ellipse' named entity 'Relation extraction' named entity 'grid search' named entity 'cross-entropy' named entity 'automatic content extraction' named entity 'NA class' named entity 'symbolic representation' named entity 'Relation extraction' named entity 'CNN' named entity 'Wikipedia' named entity 'RNN' named entity 'adversarial learning' named entity 'domain adaptation' named entity 'CNN' named entity 'neural networks' named entity 'microphone' named entity 'adversarial learning' named entity 'Relation extraction' named entity 'probability' named entity 'probability' named entity 'CNN' named entity 'probability' named entity 'data sets'

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