Opinion Mining with Deep Recurrent Neural Networks. Irsoy, O. & Cardie, C. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 720–728, Doha, Qatar, 2014. Association for Computational Linguistics. ![Opinion Mining with Deep Recurrent Neural Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Recurrent neural networks (RNNs) are connectionist models of sequential data that are naturally applicable to the analysis of natural language. Recently, “depth in space” — as an orthogonal notion to “depth in time” — in RNNs has been investigated by stacking multiple layers of RNNs and shown empirically to bring a temporal hierarchy to the architecture. In this work we apply these deep RNNs to the task of opinion expression extraction formulated as a token-level sequence-labeling task. Experimental results show that deep, narrow RNNs outperform traditional shallow, wide RNNs with the same number of parameters. Furthermore, our approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.
@inproceedings{irsoy_opinion_2014,
address = {Doha, Qatar},
title = {Opinion {Mining} with {Deep} {Recurrent} {Neural} {Networks}},
url = {http://aclweb.org/anthology/D14-1080},
doi = {10.3115/v1/D14-1080},
abstract = {Recurrent neural networks (RNNs) are connectionist models of sequential data that are naturally applicable to the analysis of natural language. Recently, “depth in space” — as an orthogonal notion to “depth in time” — in RNNs has been investigated by stacking multiple layers of RNNs and shown empirically to bring a temporal hierarchy to the architecture. In this work we apply these deep RNNs to the task of opinion expression extraction formulated as a token-level sequence-labeling task. Experimental results show that deep, narrow RNNs outperform traditional shallow, wide RNNs with the same number of parameters. Furthermore, our approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.},
language = {en},
urldate = {2024-01-23},
booktitle = {Proceedings of the 2014 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing} ({EMNLP})},
publisher = {Association for Computational Linguistics},
author = {Irsoy, Ozan and Cardie, Claire},
year = {2014},
pages = {720--728},
}
Downloads: 0
{"_id":"GB2iGNKQ9YRtJ2dg7","bibbaseid":"irsoy-cardie-opinionminingwithdeeprecurrentneuralnetworks-2014","author_short":["Irsoy, O.","Cardie, C."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Doha, Qatar","title":"Opinion Mining with Deep Recurrent Neural Networks","url":"http://aclweb.org/anthology/D14-1080","doi":"10.3115/v1/D14-1080","abstract":"Recurrent neural networks (RNNs) are connectionist models of sequential data that are naturally applicable to the analysis of natural language. Recently, “depth in space” — as an orthogonal notion to “depth in time” — in RNNs has been investigated by stacking multiple layers of RNNs and shown empirically to bring a temporal hierarchy to the architecture. In this work we apply these deep RNNs to the task of opinion expression extraction formulated as a token-level sequence-labeling task. Experimental results show that deep, narrow RNNs outperform traditional shallow, wide RNNs with the same number of parameters. Furthermore, our approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.","language":"en","urldate":"2024-01-23","booktitle":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","publisher":"Association for Computational Linguistics","author":[{"propositions":[],"lastnames":["Irsoy"],"firstnames":["Ozan"],"suffixes":[]},{"propositions":[],"lastnames":["Cardie"],"firstnames":["Claire"],"suffixes":[]}],"year":"2014","pages":"720–728","bibtex":"@inproceedings{irsoy_opinion_2014,\n\taddress = {Doha, Qatar},\n\ttitle = {Opinion {Mining} with {Deep} {Recurrent} {Neural} {Networks}},\n\turl = {http://aclweb.org/anthology/D14-1080},\n\tdoi = {10.3115/v1/D14-1080},\n\tabstract = {Recurrent neural networks (RNNs) are connectionist models of sequential data that are naturally applicable to the analysis of natural language. Recently, “depth in space” — as an orthogonal notion to “depth in time” — in RNNs has been investigated by stacking multiple layers of RNNs and shown empirically to bring a temporal hierarchy to the architecture. In this work we apply these deep RNNs to the task of opinion expression extraction formulated as a token-level sequence-labeling task. Experimental results show that deep, narrow RNNs outperform traditional shallow, wide RNNs with the same number of parameters. Furthermore, our approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.},\n\tlanguage = {en},\n\turldate = {2024-01-23},\n\tbooktitle = {Proceedings of the 2014 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing} ({EMNLP})},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Irsoy, Ozan and Cardie, Claire},\n\tyear = {2014},\n\tpages = {720--728},\n}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Irsoy, O.","Cardie, C."],"key":"irsoy_opinion_2014-1","id":"irsoy_opinion_2014-1","bibbaseid":"irsoy-cardie-opinionminingwithdeeprecurrentneuralnetworks-2014","role":"author","urls":{"Paper":"http://aclweb.org/anthology/D14-1080"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/abhishek-p","dataSources":["h7kKWXpJh2iaX92T5"],"keywords":[],"search_terms":["opinion","mining","deep","recurrent","neural","networks","irsoy","cardie"],"title":"Opinion Mining with Deep Recurrent Neural Networks","year":2014}