Publications

  • Cristina Gârbacea, “Neural Language Generation for Content Adaptation: Explainable, Efficient Low-Resource Text Simplification and Evaluation”, PhD thesis, University of Michigan, 2023 [pdf]
  • Cristina Gârbacea and Qiaozhu Mei, “Adapting Pre-trained Language Models to Low-Resource Text Simplification: The Path Matters”, In Proceedings of the 1st Conference on Lifelong Learning Agents (CoLLAs).  2022, Montreal, Canada.
  • Cristina Gârbacea and Qiaozhu Mei: “Why is constrained neural language generation particularly challenging?”, ArXiv [pdf]
  • Cristina Gârbacea and Qiaozhu Mei: “Neural language generation: Formulation, methods, and evaluation”,  ArXiv [pdf]
  • Cristina Gârbacea, Mengtian Guo, Samuel Carton, and Qiaozhu Mei, “Explainable Prediction of Text Complexity: The Missing Preliminaries for Text Simplification”, In Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP).  2021, Bangkok, Thailand.
  • Cristina Gârbacea, Samuel Carton, Shiyan Yan, and Qiaozhu Mei, “Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation“, In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).  2019, Hong Kong, China.
  • Cristina Gârbacea, Aäron van den Oord, Yazhe Li, Felicia SC Lim, Alejandro Luebs, Oriol Vinyals, and Thomas C. Walters, “Low bit-rate speech coding with VQ-VAE and a WaveNet decoder”, In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.
  • Cristina Gârbacea and Evangelos Kanoulas. “A Systematic Analysis of Sentence Update Detection for Temporal Summarization.” In Proceedings of the 39th Conference on Information Retrieval ECIR 2017, Aberdeen, UK.
  • Cristina Gârbacea and Evangelos Kanoulas. “The University of Amsterdam (ILPS.UvA) at TREC 2015 Temporal Summarization Track.”, In Proceedings of the 24th Text REtrieval Conference (TREC 2015). 2015, NIST Gaithersburg, Maryland, USA.
  • Daan Odijk, Cristina Gârbacea, Thomas Schoegje, Laura Hollink, Victor de Boer, Kees Ribbens, and Jacco van Ossenbruggen. “Supporting Exploration of Historical Perspectives Across Collections.”, In Research and Advanced Technology for Digital Libraries, pp. 238-251. Springer International Publishing, 2015, Poznan, Poland.
  • Cristina Gârbacea, Daan Odijk, David Graus, Isaac Sijaranamual, and Maarten de Rijke. “Combining Multiple Signals for Semanticizing Tweets: University of Amsterdam at #Microposts2015.”, In Proceedings of the 5th Workshop on Making Sense of Microposts at the 24th International World Wide Web Conference, WWW 2015, Florence, Italy.
  • Cristina Gârbacea, Manos Tsagkias, and Maarten de Rijke. “Feature Selection and Data Sampling Methods for Learning Reputation Dimensions: The University of Amsterdam at RepLab 2014.”, In Proceedings of CLEF 2014 Conference and Labs of the Evaluation Forum, no. 1180, pp. 1479-1490. CLEF, 2014, Sheffield, UK.
  • Cristina Gârbacea, Manos Tsagkias, and Maarten de Rijke. “Detecting the Reputation Polarity of Microblog Posts.”, In ECAI 2014: 21st European Conference on Artificial Intelligence, 18-22 August 2014, Prague, Czech Republic: including Prestigious Applications of Intelligent Systems (PAIS 2014): proceedings Vol. 263. Frontiers in Artificial Intelligence and Applications (pp. 339-334). IOS Press, 2014.