Mova0.5 pre-release⌕
☰
home / docs / papers / Modern Hebrew / Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew

Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew

What it is about

The paper studies how two input choices change neural sentiment analysis for Modern Hebrew: token-based or morpheme-based input (morphemes from the YAP parser), and string-based or character-based vocabulary. It introduces a 12,804-comment Hebrew sentiment set from political Facebook pages (8,512 positive, 3,922 negative, 370 neutral; Cohen's kappa 0.697 between two coders). Five architectures are compared: linear, MLP, CNN, LSTM and BiLSTM. With string-based vocabulary, token-based input is best for the linear, MLP and CNN models (CNN 89.2 vs 89.1); the recurrent models lean the other way (LSTM 85.2 token vs 86.2 morpheme; BiLSTM 87.4 vs 87.5). The best model is a token-based CNN at about 89.2% accuracy, against a 66.6% majority baseline. Half of the errors on a 50-comment sample come from cases where the human coders also disagreed, mostly mixed sentiment or sarcasm. Errors in each architecture follow its own weakness: negation and third-party reference for the MLP, "sorry, but" for the CNN, length for the LSTM.

Ideas

For Mova

I1 goes into the measurement scripts for any Hebrew polarity test, in 8. Lexicon and register where the register is discussed. I2 goes into 9. Pragmatics and politeness. I3 is a note for prag and for the held-out set rules in docs/. The neural models are not used by Mova.

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{amram2018representations,
  title = {{Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew}},
  author = {Amram, Adam and David, Anat Ben and Tsarfaty, Reut},
  booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},
  year = {2018},
  url = {https://aclanthology.org/C18-1190/}
}

References

35 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Martı́n Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org. find
  2. Muhammad Abdul-Mageed, Mona Diab, and Sandra Kübler. 2014. Samar: Subjectivity and sentiment analysis for arabic social media. Computer Speech & Language, 28(1):20–37. find
  3. N. A. Abdulla, N. A. Ahmed, M. A. Shehab, and M. Al-Ayyoub. 2013. Arabic sentiment analysis: Lexicon-based and corpus-based. In 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), pages 1–6, Dec. find
  4. Ahmad A Al Sallab, Ramy Baly, Gilbert Badaro, Hazem Hajj, Wassim El Hajj, and Khaled B Shaban. 2015. Deep learning models for sentiment analysis in arabic. In ANLP Workshop 2015, page 9. find
  5. Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2015. Improved transition-based parsing by modeling characters instead of words with lstms. CoRR. find
  6. Andrea Ceron, Luigi Curini, Stefano M Iacus, and Giuseppe Porro. 2014. Every tweet counts? how sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to italy and france. New Media & Society, 16(2):340–358. find
  7. Danqi Chen and Christopher Manning. 2014. A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 740–750, Doha, Qatar, October. Association for Computational Linguistics. find our card
  8. Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, and Jun Zhao. 2015. Event extraction via dynamic multi-pooling convolutional neural networks. In ACL, pages 167–176. The Association for Computer Linguistics. find
  9. François Chollet. 2015. Keras. https://github.com/fchollet/keras. ↗
  10. Li Dong, Furu Wei, Chuanqi Tan, Duyu Tang, Ming Zhou, and Ke Xu. 2014. Adaptive recursive neural network for target-dependent twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 49–54, Baltimore, Maryland, June. Association for Computational Linguistics. find
  11. Cı́cero Nogueira Dos Santos and Maira Gatti. 2014. Deep convolutional neural networks for sentiment analysis of short texts. In COLING, pages 69–78. find
  12. Cı́cero Nogueira Dos Santos and Bianca Zadrozny. 2014. Learning character-level representations for part-of-speech tagging. In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32, ICML’14, pages II–1818–II–1826. JMLR.org. find
  13. Cı́cero Nogueira dos Santos, Bing Xiang, and Bowen Zhou. 2015. Classifying relations by ranking with convolutional neural networks. CoRR, abs/1504.06580. ↗
  14. Greg Durrett and Dan Klein. 2015. Neural CRF parsing. CoRR, abs/1507.03641. ↗
  15. Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, and Noah A. Smith. 2015. Transition-based dependency parsing with stack long short-term memory. CoRR, abs/1505.08075. ↗ our card
  16. Michael Etter, Elanor Colleoni, Laura Illia, Katia Meggiorin, and Antonino D’Eugenio. 2017. Measuring organizational legitimacy in social media: Assessing citizens’ judgments with sentiment analysis. Business & Society, page 0007650316683926. find
  17. Yoav Goldberg. 2015. abs/1510.00726. A primer on neural network models for natural language processing. ↗
  18. CoRR, Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning. find
  19. Alex Grave. 2008. Supervised Sequence Labelling with Recurrent Neural Networks. Ph.D. thesis. find
  20. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. find
  21. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. CoRR, abs/1412.6980. ↗
  22. Efthymios Kouloumpis, Theresa Wilson, and Johanna D Moore. 2011. Twitter sentiment analysis: The good the bad and the omg! Icwsm, 11(538-541):164. find
  23. Siwei Lai, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Recurrent convolutional neural networks for text classification. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, pages 2267–2273. AAAI Press. find
  24. Wang Ling, Tiago Luı́s, Luı́s Marujo, Ramón Fernández Astudillo, Silvio Amir, Chris Dyer, Alan W. Black, and Isabel Trancoso. 2015. Finding function in form: Compositional character models for open vocabulary word representation. CoRR, abs/1508.02096. ↗
  25. Bing Liu. 2012. Sentiment analysis and opinion mining. find
  26. Amir More and Reut Tsarfaty. 2016. Data-driven morphological analysis and disambiguation for morphologically rich languages and universal dependencies. In Proceedings of COLING 2016, december. find
  27. Georgios Paltoglou and Mike Thelwall. 2012. Twitter, myspace, digg: Unsupervised sentiment analysis in social media. ACM Transactions on Intelligent Systems and Technology (TIST), 3(4):66. find
  28. Bo Pang and Lillian Lee. 2008. Opinion mining and sentiment analysis. Found. Trends Inf. Retr., 2(1-2):1–135, January. find
  29. Bernhard Rieder. 2013. Studying facebook via data extraction: the netvizz application. In Proceedings of the 5th annual ACM web science conference, pages 346–355. ACM. find
  30. Khalil Sima’an, Alon Itai, Yoad Winter, Alon Altman, and Noa Nativ. 2001. Building a tree-bank of modern hebrew text. find
  31. Reut Tsarfaty, Djamé Seddah, Yoav Goldberg, Sandra Kübler, Yannick Versley, Marie Candito, Jennifer Foster, Ines Rehbein, and Lamia Tounsi. 2010. Statistical parsing of morphologically rich languages (spmrl) what, how and whither. In Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages, pages 1–12, Los Angeles, CA, USA, June. Association for Computational Linguistics. find
  32. Reut Tsarfaty. 2006. The interplay of syntax and morphology in building parsing models for modern hebrew. In Proceedings of ESSLLI. find
  33. Andranik Tumasjan, Timm Oliver Sprenger, Philipp G Sandner, and Isabell M Welpe. 2010. Predicting elections with twitter: What 140 characters reveal about political sentiment. ICWSM, 10(1):178–185. find
  34. Wenpeng Yin, Katharina Kann, Mo Yu, and Hinrich Schütze. 2017. Comparative study of CNN and RNN for natural language processing. CoRR, abs/1702.01923. ↗
  35. Xiang Zhang, Junbo Jake Zhao, and Yann LeCun. 2015. Character-level convolutional networks for text classification. CoRR, abs/1509.01626. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/coling-2018-amram-representations-architectures-neural-sentiment-analysis/