Sobre el efecto del orden de las palabras en el análisis de sentimiento crosslingüe

• Autores: Jeremy Claude Barnes, Àlex R. Atrio, Toni Badia Cardús
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 63, 2019, págs. 23-30
• Idioma: español
• Títulos paralelos:
  • On the Effect of Word Order on Cross-lingual Sentiment Analysis
• Enlaces
  • Texto completo
• Resumen
  • español

    Los modelos de análisis de sentimiento que actualmente representan el estado del arte utilizan el orden de las palabras, ya sea explícitamente al preentrenar con un objetivo de modelización del lenguaje, ya sea implícitamente al recurrir a redes neuronales recurrentes (RNR) o convolucionales (RNC). Esto es un problema para los acercamientos crosslingües que emplean vectores bilingües para entrenar, ya que la diferencia del orden de las palabras entre la lengua de origen y la de destino no se resuelve. En este trabajo, exploramos el reordenamiento de las palabras como etapa de procesamiento previa para la clasificación de sentimiento crosslingüe a nivel de frase, con dos combinaciones de idiomas (Inglés-Castellano, Inglés-Catalán). Descubrimos que aunque el reordenamiento ayuda a los dos modelos, los RNC son más sensibles al reordenamiento local, mientras un reordenamiento global beneficia a los RNR.

  • English

    Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNS) or convolutional networks (CNNS). This is a problem for cross-lingual models that use bilingual embeddings as features, as the difference in word order between source and target languages is not resolved. In this work, we explore reordering as a pre-processing step for sentence-level crosslingual sentiment classification with two language combinations (English-Spanish, English-Catalan). We find that while reordering helps both models, CNNS are more sensitive to local reorderings, while global reordering benefits RNNS.

• Referencias bibliográficas
  • Agerri, R., M. Cuadros, S. Gaines, and G. Rigau. 2013. OpeNER: Open polarity enhanced named entity recognition. Sociedad Española para...
  • Artetxe, M., G. Labaka, and E. Agirre. 2016. Learning principled bilingual mappings of word embeddings while preserving mono lingual invariance....
  • Artetxe, M., G. Labaka, and E. Agirre. 2017. Learning bilingual word embeddings with (almost) no bilingual data. In Proceedings of the 55th...
  • Artetxe, M., G. Labaka, and E. Agirre. 2018a. A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings....
  • Artetxe, M., G. Labaka, and E. Agirre. 2018b. Unsupervised statistical machine translation. In Proceedings of the 2018 Conference on Empirical...
  • Artetxe, M., G. Labaka, E. Agirre, and K. Cho. 2018. Unsupervised neural machine translation. In Proceedings of the Sixth International Conference...
  • Balahur, A. and M. Turchi. 2014. Comparative experiments using supervised learning and machine translation for multilingual sentiment analysis....
  • Banea, C., R. Mihalcea, J. Wiebe, and S. Hassan. 2008. Multilingual subjectivity analysis using machine translation. In Proceedings of the...
  • Barnes, J., T. Badia, and P. Lambert. 2018. MultiBooked: A Corpus of Basque and Catalan Hotel Reviews Annotated for Aspect-level Sentiment...
  • Barnes, J., R. Klinger, and S. Schulte im Walde. 2018. Bilingual sentiment embeddings: Joint projection of sentiment across languages. In...
  • Bisazza, A. and M. Federico. 2016. A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena....
  • Chen, X., B. Athiwaratkun, Y. Sun, K. Q. Weinberger, and C. Cardie. 2016. Adversarial deep averaging networks for crosslingual sentiment classification....
  • Collins, M., P. Koehn, and I. Kucerova. 2005. Clause restructuring for statistical machine translation. In Proceedings of the 43rd Annual...
  • Crego, J. M. and J. B. Mariño. 2006a. Improving statistical mt by coupling reordering and decoding. Machine Translation, 20(3):199–215.
  • Crego, J. M. and J. B. Mariño. 2006b. Integration of pos tag-based source reordering into smt decoding by an extended search graph. In Proceedings...
  • Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova. 2018. Bert: Pretraining of deep bidirectional transformers for language understanding....
  • dos Santos, C. N. and M. Gatti. 2014. Deep convolutional neural networks for sentiment analysis of short texts. In Proceedings of COLING 2014,...
  • Gojun, A. and A. Fraser. 2012. Determining the placement of german verbs in english– to–german smt. In Proceedings of the 13th Conference...
  • Hangya, V., F. Braune, A. Fraser, and H. Schultze. 2018. Two methods for do main adaptation of bilingual tasks: Delightfully simple and broadly...
  • Howard, J. and S. Ruder. 2018. Universal language model fine-tuning for text classification. In Proceedings of the 56th Annual Meeting of...
  • Hu, M. and B. Liu. 2004. Mining opinion features in customer reviews. In Proceedings of the 10th ACM SIGKDD International Conference on Knowledge...
  • Iyyer, M., V. Manjunatha, J. Boyd-Graber, and H. Daume III. 2015. Deep unordered composition rivals syntactic methods for text classification....
  • Kiritchenko, S., X. Zhu, C. Cherry, and S. M. Mohammad. 2014. NRC-Canada-2014: Detecting aspects and sentiment in customer reviews. Proceedings...
  • Klinger, R. and P. Cimiano. 2015. Instance selection improves cross-lingual model training for fine-grained sentiment analysis. In Proceedings...
  • Lample, G., A. Conneau, L. Denoyer, and M. Ranzato. 2018a. Unsupervised machine translation using monolingual corpora only. In International...
  • Lample, G., A. Conneau, M. Ranzato, L. Denoyer, and H. Jégou. 2018b. Word translation without parallel data. In International Conference...
  • Lample, G., M. Ott, A. Conneau, L. Denoyer, and M. Ranzato. 2018c. Phrase-based & neural unsupervised machine translation. In Proceedings...
  • Processing, pages 5039–5049, Brussels, Belgium, October-November.
  • Luong, T., H. Pham, and C. D. Manning. 2015. Bilingual word representations with monolingual quality in mind. In Proceedings of the 1st Workshop...
  • Meng, X., F. Wei, X. Liu, M. Zhou, G. Xu, and H. Wang. 2012. Cross-lingual mixture model for sentiment classification. In Proceedings of the...
  • Nakagawa, T. 2015. Efficient top-down btg parsing for machine translation preordering. In Proceedings of the 53rd Annual Meeting of the Association...
  • Neubig, G., T. Watanabe, and S. Mori. 2012. Inducing a discriminative parser to optimize machine translation reordering. In Proceedings of...
  • Peters, M., M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings...
  • Severyn, A. and A. Moschitti. 2015. Unitn: Training deep convolutional neural network for twitter sentiment classification. In Proceedings...
  • Socher, R., A. Perelygin, J. Wu, J. Chuang, C. Manning, A. Ng, and C. Potts. 2013. Recursive deep models for semantic compositionality over...