loading
Papers

Research.Publish.Connect.

Paper

Authors: Gianluca Moro ; Andrea Pagliarani ; Roberto Pasolini and Claudio Sartori

Affiliation: Department of Computer Science and Engineering (DISI), University of Bologna, Via Cesare Pavese, 47522 Cesena and Italy

ISBN: 978-989-758-330-8

Keyword(s): Sentiment Classification, Transfer Learning, Fine-tuning, Deep Learning, Big Data, Memory Networks.

Abstract: Cross-domain sentiment classifiers aim to predict the polarity, namely the sentiment orientation of target text documents, by reusing a knowledge model learned from a different source domain. Distinct domains are typically heterogeneous in language, so that transfer learning techniques are advisable to support knowledge transfer from source to target. Distributed word representations are able to capture hidden word relationships without supervision, even across domains. Deep neural networks with memory (MemDNN) have recently achieved the state-of-the-art performance in several NLP tasks, including cross-domain sentiment classification of large-scale data. The contribution of this work is the massive experimentations of novel outstanding MemDNN architectures, such as Gated Recurrent Unit (GRU) and Differentiable Neural Computer (DNC) both in cross-domain and in-domain sentiment classification by using the GloVe word embeddings. As far as we know, only GRU neural networks have been appl ied in cross-domain sentiment classification. Sentiment classifiers based on these deep learning architectures are also assessed from the viewpoint of scalability and accuracy by gradually increasing the training set size, and showing also the effect of fine-tuning, an explicit transfer learning mechanism, on cross-domain tasks. This work shows that MemDNN based classifiers improve the state-of-the-art on Amazon Reviews corpus with reference to document-level cross-domain sentiment classification. On the same corpus, DNC outperforms previous approaches in the analysis of a very large in-domain configuration in both binary and fine-grained document sentiment classification. Finally, DNC achieves accuracy comparable with the state-of-the-art approaches on the Stanford Sentiment Treebank dataset in both binary and fine-grained single-sentence sentiment classification. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.204.173.45

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Moro, G.; Pagliarani, A.; Pasolini, R. and Sartori, C. (2018). Cross-domain & In-domain Sentiment Analysis with Memory-based Deep Neural Networks.In Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, ISBN 978-989-758-330-8, pages 127-138. DOI: 10.5220/0007239101270138

@conference{kdir18,
author={Gianluca Moro. and Andrea Pagliarani. and Roberto Pasolini. and Claudio Sartori.},
title={Cross-domain & In-domain Sentiment Analysis with Memory-based Deep Neural Networks},
booktitle={Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR,},
year={2018},
pages={127-138},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007239101270138},
isbn={978-989-758-330-8},
}

TY - CONF

JO - Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR,
TI - Cross-domain & In-domain Sentiment Analysis with Memory-based Deep Neural Networks
SN - 978-989-758-330-8
AU - Moro, G.
AU - Pagliarani, A.
AU - Pasolini, R.
AU - Sartori, C.
PY - 2018
SP - 127
EP - 138
DO - 10.5220/0007239101270138

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.