About: Multi-level Memory Network with CRFs for Keyphrase Extraction

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

About: Multi-level Memory Network with CRFs for Keyphrase 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	Multi-level Memory Network with CRFs for Keyphrase Extraction
Creator	Zhang, Yuxiang Zhou, Tao Zhu, Haoxiang
Source	PMC
abstract	Keyphrase, that concisely describe the high-level topics discussed in a document, are very useful for a wide range of natural language processing (NLP) tasks. Current popular supervised methods for keyphrase extraction commonly cannot effectively utilize the long-range contextual information in text. In this paper, we focus on how to effectively exploit the long-range contextual information to improve the keyphrase extraction performance. Specifically, we propose a multi-level memory network with the conditional random fields (CRFs), which allows to have unrestricted access to the long-range and local contextual information in text. We first design the multi-level memory network with sentence level and document level to enhance the text representation. Then, we integrate the multi-level memory network with the CRFs, which has an advantage in modeling the local contextual information. Compared with the recent state-of-the-art methods, our model can achieve better results through experiments on two datasets.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47426-3_56
has license	no-cc
sha1sum (hex)	d565e47fb1fbec8f99d0b63476317caa72d62e04
schema:url	https://doi.org/10.1007/978-3-030-47426-3_56
resource representing a document's title	Multi-level Memory Network with CRFs for Keyphrase Extraction
has PubMed Central identifier	PMC7206171
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:d565e47fb1fbec8f99d0b63476317caa72d62e04#body_text
is schema:about of	named entity 'memory' named entity 'memory' named entity 'commonly' named entity 'enhance' named entity 'wide range' named entity 'describe' named entity 'extraction' named entity 'document' named entity 'modeling' named entity 'contextual' named entity 'Current' named entity 'NLP' named entity 'n-gram' named entity 'contextual information' named entity 'sequence labeling' named entity 'Science area' named entity 'cross-validation' named entity 'long-term memory' named entity 'contextual information' named entity 'KDD' named entity 'Naïve Bayes' named entity 'citation network' named entity 'Keyphrase extraction' named entity 'Experimental results' named entity 'Supervised methods' named entity 'over-fitting' named entity 'semantic information' named entity 'Data Mining' named entity 'RNNs' named entity 'internal memory' named entity 'recurrent neural networks' named entity 'CeKE' named entity 'TF-IDF' named entity 'feature engineering' named entity 'WWW' named entity 'Naïve Bayes' named entity 'cross-validation' named entity 'RNNs' named entity 'sequence labeling' named entity 'sequence labeling' named entity 'graph-based' named entity 'classifier' named entity 'KDD' named entity 'computing' named entity 'contextual information' named entity 'degree centrality' named entity 'n-grams' named entity 'prior knowledge' named entity 'research papers' named entity 'corpora' named entity 'classifiers' named entity 'KDD' named entity 'long-distance dependencies' named entity 'Naïve Bayes' named entity 'feature engineering' named entity 'GloVe' named entity 'term frequency-inverse document frequency' named entity 'term frequency-inverse document frequency' named entity 'internal memory' named entity 'research papers' named entity 'n-gram' named entity 'word embedding' named entity 'CeKE' named entity 'WWW' named entity 'research papers' named entity 'contextual information' named entity 'RNNs' named entity 'LSTM' named entity 'pre-trained' named entity 'linearly transformed' named entity 'recurrent neural networks' named entity 'KDD' named entity 'contextual information' named entity 'data pre-processing' named entity 'WWW' named entity 'NLP' named entity 'WWW' named entity 'machine learning' named entity 'inference' named entity 'classifier' named entity 'part-of-speech'

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