IR, Text Complexity, and Multingualism

Research agenda focused on automatically examining the level of complexity of texts in multiple languages. This requires leveraring feature engeneering, machine learning, and natural language processing. With readability being a major component of personalization of several information retrieval tasks, it is imperative that it can be estimated efficiently, regardless of the language, topic, and level of the corresponding resource.

Publications

Ion Madrazo Azpiazu and Maria Soledad Pera. 2020. “An Analysis of Transfer Learning Methods for Multilingual Readability Assessment”. Poster paper in Proceedings of the 2020 Conference on User Modeling, Adaptation and Personalization (UMAP ‘20). ACM, 95-100 pp. DOI:10.1145/3386392.3397605.

Ion Madrazo Azpiazu and Maria Soledad Pera. 2020. “A Framework for Hierarchical Multilingual Machine Translation”. In arXiv.

Ion Madrazo Azpiazu and Maria Soledad Pera. 2019. “Is cross‐lingual readability assessment possible?”. In Journal of the Association for Information Science and Technology (JASIST 2019).

Ion Madrazo Azpiazu and Maria Soledad Pera. 2019. “Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment”. In Transactions of the Association for Computational Linguistics (TACL 2019).

Oghenemaro Anuyah, Ion Madrazo Azpiazu, David McNeill, Maria Soledad Pera. 2017. “Can Readability Enhance Recommendations on Community Question Answering Sites?”. In Proceedings of the 11th ACM Conference on Recommender Systems (RecSys 2017 Poster Proceedings).

Ion Madrazo Azpiazu and Maria Soledad Pera. 2016. “Is Readability a Valuable Signal for Hashtag Recommendations?”. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys 2016 Poster Proceedings).