About: EMOVA: A Semi-supervised End-to-End Moving-Window Attentive Framework for Aspect Mining

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

About: EMOVA: A Semi-supervised End-to-End Moving-Window Attentive Framework for Aspect Mining 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	EMOVA: A Semi-supervised End-to-End Moving-Window Attentive Framework for Aspect Mining
Creator	Li, Ning Chow, Chi-Yin Zhang, Jia-Dong
Source	PMC
abstract	Aspect mining or extraction is one of the most challenging problems in aspect-level analysis on customer reviews; it aims to extract terms from a review describing aspects of a reviewed entity, e.g., a product or service. As aspect mining can be formulated as the sequence labeling problem, supervised deep sequence learning models have recently achieved the best performance. However, these supervised models require a large amount of labeled data which are usually very costly or unavailable. To this end, we propose a semi-supervised End-to-end MOVing-window Attentive framework (called EMOVA) that has three key features for aspect mining. (1) Two neural layers with Bidirectional Long Short-Term Memory (BiLSTM) are employed to learn representations of reviews. (2) Cross-View Training (CVT) is used to improve the representation learning over a small set of labeled reviews and a large set of unlabeled reviews from the same domain in a unified end-to-end architecture. (3) Since past nearby information in a text provides important semantic contexts for a prediction task in aspect mining, a moving-window attention component is proposed in EMOVA to enhance prediction accuracy. Experimental results over four review datasets from the SemEval workshops show that EMOVA outperforms the state-of-the-art models for aspect mining.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47436-2_61
has license	no-cc
sha1sum (hex)	3d59ed503c51753962e42cc46cec8b7f8b66600b
schema:url	https://doi.org/10.1007/978-3-030-47436-2_61
resource representing a document's title	EMOVA: A Semi-supervised End-to-End Moving-Window Attentive Framework for Aspect Mining
has PubMed Central identifier	PMC7206239
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:3d59ed503c51753962e42cc46cec8b7f8b66600b#body_text
is schema:about of	named entity 'reviews' named entity 'semi-supervised' named entity 'architecture' named entity 'STATE' named entity 'ENHANCE' named entity 'SEMANTIC' named entity 'REVIEWS' named entity 'TEXT' named entity 'service' named entity 'models' named entity 'Two' named entity 'mining' named entity 'customer' named entity 'aspect' named entity 'attention' named entity 'SemEval' named entity 'enhance' named entity 'SemEval' named entity 'semantic' named entity 'representation learning' named entity 'semi-supervised' named entity 'End-to-End' named entity 'CVT' named entity 'word embeddings' named entity 'CVT' named entity 'semi-supervised' named entity 'LDA' named entity 'neural network' named entity 'neural networks' named entity 'topic modeling' named entity 'pre-trained' named entity 'domain knowledge' named entity 'word embeddings' named entity 'deep learning' named entity 'end-to-end' named entity 'CVT' named entity 'Long Short-Term Memory' named entity 'pre-trained' named entity 'CVT' named entity 'semisupervised learning' named entity 'uniform distribution' named entity 'word embeddings' named entity 'stochastic gradient descent' named entity 'deep learning' named entity 'semantic' named entity 'special cases' named entity 'representation learning' named entity 'CMLA' named entity 'word embeddings' named entity 'Convolutional Neural Network' named entity 'CVT' named entity 'probability distribution' named entity 'CVT' named entity 'end-to-end' named entity 'HMM' named entity 'semi-supervised' named entity 'Kullback-Leibler' named entity 'labeled data' named entity 'CVT' named entity 'word embeddings' named entity 'sequence labeling' named entity 'Long Short-Term Memory' named entity 'recurrent neural networks' named entity 'GloVe' named entity 'training data' named entity 'LSTM' named entity 'Training Data' named entity 'CVT' named entity 'pre-trained' named entity 'semi-supervised learning' named entity 'Sequence labeling' named entity 'semi-supervised learning' named entity 'semi-supervised' named entity 'multi-task learning' named entity 'CVT' named entity 'BiLSTM network' named entity 'training data' named entity 'CRF' named entity 'GloVe' named entity 'Conditional Random Fields' named entity 'labeled data'

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