About: Document Network Projection in Pretrained Word Embedding Space

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

About: Document Network Projection in Pretrained Word Embedding Space 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	Document Network Projection in Pretrained Word Embedding Space
Creator	Gourru, Antoine Guille, Adrien Jacques, Julien Velcin, Julien
Source	PMC
abstract	We present Regularized Linear Embedding (RLE), a novel method that projects a collection of linked documents (e.g., citation network) into a pretrained word embedding space. In addition to the textual content, we leverage a matrix of pairwise similarities providing complementary information (e.g., the network proximity of two documents in a citation graph). We first build a simple word vector average for each document, and we use the similarities to alter this average representation. The document representations can help to solve many information retrieval tasks, such as recommendation, classification and clustering. We demonstrate that our approach outperforms or matches existing document network embedding methods on node classification and link prediction tasks. Furthermore, we show that it helps identifying relevant keywords to describe document classes.
has issue date	2020-03-24(xsd:dateTime)
bibo:doi	10.1007/978-3-030-45442-5_19
has license	no-cc
sha1sum (hex)	446604047a6e634f4914b4af487f5af1f58e3960
schema:url	https://doi.org/10.1007/978-3-030-45442-5_19
resource representing a document's title	Document Network Projection in Pretrained Word Embedding Space
has PubMed Central identifier	PMC7148102
schema:publication	Advances in Information Retrieval
resource representing a document's body	covid:446604047a6e634f4914b4af487f5af1f58e3960#body_text
is schema:about of	named entity 'document' named entity 'documents' named entity 'The' named entity 'REPRESENTATION' named entity 'IDENTIFYING' covid:arg/446604047a6e634f4914b4af487f5af1f58e3960 named entity 'RLE' named entity 'citation graph' named entity 'space' named entity 'information retrieval' named entity 'RLE' named entity 'RLE' named entity 'Regularized' named entity 'vector representations' named entity 'contextual information' named entity 'LSA' named entity 'transition matrix' named entity 'semantic' named entity 'centroid' named entity 'information retrieval' named entity 'Matrices' named entity 'LSA' named entity 'RLE' named entity 'word embedding' named entity 'vector representations' named entity 'deep-learning' named entity 'matrix multiplication' named entity 'Dblp' named entity 'LSA' named entity 'GloVe' named entity 'semantic space' named entity 'centroid' named entity 'Roc Curve' named entity 'Dblp' named entity 'word vectors' named entity 'SVD' named entity 'term frequency' named entity 'Dblp' named entity 'word embeddings' named entity 'information retrieval' named entity 'document classification' named entity 'matrix multiplication' named entity 'vector' named entity 'Dblp' named entity 'Singular Value Decomposition' named entity 'Dblp' named entity 'vector space' named entity 'L2 regularization' named entity 'DBLP' named entity 'similarity matrix' named entity 'gensim' named entity 'semantic' named entity 'New York Times' named entity 'cosine similarity' named entity 'Information retrieval' named entity 'vector' named entity 'bag of words' named entity 'query expansion' named entity 'stop words' named entity 'training examples' named entity 'RLE' named entity 'Representation Learning' named entity 'DBLP' named entity 'P U' named entity 'vector' named entity 'regularization' named entity 'RLE' named entity 'semantics' named entity 'Skip-gram' named entity 'ReTweet' named entity 'weighted average' named entity 'Dblp' named entity 'seq2seq' named entity 'New York Times' named entity 'computing' named entity 'neural networks' named entity 'semantic information' named entity 'word vector space' named entity 'query expansion' named entity 'similarity matrix'

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