About: Innovative Deep Neural Network Fusion for Pairwise Translation Evaluation

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

About: Innovative Deep Neural Network Fusion for Pairwise Translation Evaluation 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	Innovative Deep Neural Network Fusion for Pairwise Translation Evaluation
Creator	Kermanidis, Katia Mouratidis, Despoina Sosoni, Vilelmini
Source	PMC
abstract	A language independent deep learning (DL) architecture for machine translation (MT) evaluation is presented. This DL architecture aims at the best choice between two MT (S1, S2) outputs, based on the reference translation (Sr) and the annotation score. The outputs were generated from a statistical machine translation (SMT) system and a neural machine translation (NMT) system. The model applied in two language pairs: English - Greek (EN-EL) and English - Italian (EN-IT). In this paper, a variety of experiments with different parameter configurations is presented. Moreover, linguistic features, embeddings representation and natural language processing (NLP) metrics (BLEU, METEOR, TER, WER) were tested. The best score was achieved when the proposed model used source segments (SSE) information and the NLP metrics set. Classification accuracy has increased up to 5% (compared to previous related work) and reached quite satisfactory results for the Kendall τ score.
has issue date	2020-05-06(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49186-4_7
has license	no-cc
sha1sum (hex)	20304e30fe18f123c7ece9028df100529870c872
schema:url	https://doi.org/10.1007/978-3-030-49186-4_7
resource representing a document's title	Innovative Deep Neural Network Fusion for Pairwise Translation Evaluation
has PubMed Central identifier	PMC7256585
schema:publication	Artificial Intelligence Applications and Innovations
resource representing a document's body	covid:20304e30fe18f123c7ece9028df100529870c872#body_text
is schema:about of	named entity 'machine translation' named entity 'model' named entity 'experiments' named entity 'MACHINE TRANSLATION' named entity 'ENGLISH' named entity 'DIFFERENT' named entity 'EVALUATION' named entity 'WER' named entity 'METEOR' named entity 'SOURCE' named entity 'REPRESENTATION' named entity 'TRANSLATION' named entity 'PAPER' named entity 'set' named entity 'features' named entity 'NLP' named entity 'SMT' named entity 'metrics' named entity 'system' named entity 'NLP' named entity 'BLEU' named entity 'SSE' named entity 'NLP' named entity 'SMT' named entity 'Deep Neural Network' named entity 'annotation' named entity 'SSE' named entity 'non-parametric test' named entity 'francise' named entity 'F-score' named entity 'matrices' named entity 'SSE' named entity 'transmedia' named entity 'NLP' named entity 'Python' named entity 'NLP' named entity 'proper noun' named entity 'SSE' named entity 'portmanteau' named entity 'word error rate' named entity 'SSE' named entity 'correlation' named entity 'transistor' named entity 'WER' named entity 'NLP' named entity 'WER' named entity 'GitHub' named entity 'feature set' named entity 'partially correct' named entity 'h1r' named entity 'WER' named entity 'NMT' named entity 'Moses' named entity 'learning rate' named entity 'NMT' named entity 'SVM' named entity 'transmedia' named entity 'pre-trained' named entity 'SSE' named entity 'syntactic' named entity 'SSE' named entity 'string similarity' named entity 'harmonic mean of precision and recall' named entity 'word embeddings' named entity 'NLP' named entity 'semantic information' named entity 'F1 score' named entity 'SVM' named entity 'classifier' named entity 'adverbial phrase' named entity 'transmedia' named entity 'sigmoid function' named entity 'feature set' named entity 'NLP' named entity 'linguistics' named entity 'SSE' named entity 'data set' named entity 'polysemous' named entity 'Moses' named entity 'Support Vector Machine' named entity 'transmedia'

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