CUFE at SemEval-2016 Task 4: A Gated Recurrent Model for Sentiment Classification

Handle URI:
http://hdl.handle.net/10754/618210
Title:
CUFE at SemEval-2016 Task 4: A Gated Recurrent Model for Sentiment Classification
Authors:
Nabil, Mahmoud; Atyia, Amir; Aly, Mohamed ( 0000-0002-5828-9148 )
Abstract:
In this paper we describe a deep learning system that has been built for SemEval 2016 Task4 (Subtask A and B). In this work we trained a Gated Recurrent Unit (GRU) neural network model on top of two sets of word embeddings: (a) general word embeddings generated from unsupervised neural language model; and (b) task specific word embeddings generated from supervised neural language model that was trained to classify tweets into positive and negative categories. We also added a method for analyzing and splitting multi-words hashtags and appending them to the tweet body before feeding it to our model. Our models achieved 0.58 F1-measure for Subtask A (ranked 12/34) and 0.679 Recall for Subtask B (ranked 12/19).
KAUST Department:
Visual Computing Center (VCC)
Publisher:
Association for Computational Linguistics (ACL)
Journal:
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)
Conference/Event name:
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)
Issue Date:
16-Jun-2016
DOI:
10.18653/v1/S16-1005
Type:
Conference Paper
Sponsors:
This work has been funded by ITIDA’s ITAC project number CFP65.
Additional Links:
http://aclweb.org/anthology/S16-1005
Appears in Collections:
Conference Papers

Full metadata record

DC FieldValue Language
dc.contributor.authorNabil, Mahmouden
dc.contributor.authorAtyia, Amiren
dc.contributor.authorAly, Mohameden
dc.date.accessioned2016-08-10T12:22:39Z-
dc.date.available2016-08-10T12:22:39Z-
dc.date.issued2016-06-16-
dc.identifier.doi10.18653/v1/S16-1005-
dc.identifier.urihttp://hdl.handle.net/10754/618210-
dc.description.abstractIn this paper we describe a deep learning system that has been built for SemEval 2016 Task4 (Subtask A and B). In this work we trained a Gated Recurrent Unit (GRU) neural network model on top of two sets of word embeddings: (a) general word embeddings generated from unsupervised neural language model; and (b) task specific word embeddings generated from supervised neural language model that was trained to classify tweets into positive and negative categories. We also added a method for analyzing and splitting multi-words hashtags and appending them to the tweet body before feeding it to our model. Our models achieved 0.58 F1-measure for Subtask A (ranked 12/34) and 0.679 Recall for Subtask B (ranked 12/19).en
dc.description.sponsorshipThis work has been funded by ITIDA’s ITAC project number CFP65.en
dc.publisherAssociation for Computational Linguistics (ACL)en
dc.relation.urlhttp://aclweb.org/anthology/S16-1005en
dc.rightsMaterials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 License. http://creativecommons.org/licenses/by/4.0/en
dc.titleCUFE at SemEval-2016 Task 4: A Gated Recurrent Model for Sentiment Classificationen
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalProceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)en
dc.conference.dateJune 16-17, 2016en
dc.conference.nameProceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)en
dc.conference.locationSan Diego, Californiaen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionComputer Engineering, Cairo University, Egypten
kaust.authorAly, Mohameden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.