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 classifica- tion 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 applied in cross-domain sentiment classification. Senti- ment 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 ex- plicit 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 sen- timent 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.
Gianluca Moro, A.P. (2018). Cross-domain & In-domain Sentiment Analysis with Memory-based Deep Neural Networks. SciTePress [10.5220/0007239101270138].
Cross-domain & In-domain Sentiment Analysis with Memory-based Deep Neural Networks
Gianluca Moro
Membro del Collaboration Group
;Andrea PagliaraniMembro del Collaboration Group
;Roberto PasoliniMembro del Collaboration Group
;Claudio SartoriMembro del Collaboration Group
2018
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 classifica- tion 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 applied in cross-domain sentiment classification. Senti- ment 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 ex- plicit 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 sen- timent 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.File | Dimensione | Formato | |
---|---|---|---|
kdir_2018_camera_ready_deep_learning_cross_sentiment_analysis.pdf
accesso aperto
Tipo:
Preprint
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione
327.23 kB
Formato
Adobe PDF
|
327.23 kB | Adobe PDF | Visualizza/Apri |
KDIR_2018_55-1.pdf
accesso aperto
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione
360.33 kB
Formato
Adobe PDF
|
360.33 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.