Research
– Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus. R. T. Lowe, N. Pow, I. V. Serban, L. Charlin, C.-W. Liu, J. Pineau. Dialogue & Discourse Journal, Vol 8, 2017.
– Towards an automatic Turing test: Learning to evaluate dialogue responses. R. Lowe, M. Noseworthy, I. V. Serban, N. Angelard-Gontier, Y. Bengio, J. Pineau. ICLR, 2017.
– Multi-modal Variational Encoder-Decoders. I. V. Serban, A. G. Ororbia II, J. Pineau, A. Courville. arXiv:1612.00377, 2016.
– Generative Deep Neural Networks for Dialogue: A Short Review. I. V. Serban, R. Lowe, L. Charlin, J. Pineau. NIPS Workshop on Learning Methods for Dialogue, 2016.
– Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation. I. V. Serban, T. Klinger, G. Tesauro, K. Talamadupula, B. Zhou, Y. Bengio, A. Courville. AAAI, 2017.
– A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues. I. V. Serban, A. Sordoni, R. Lowe, L. Charlin, J. Pineau, A. Courville, Y. Bengio. AAAI, 2017.
– How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation. C.-W. Liu, R. Lowe, I. V. Serban, M. Noseworthy, L. Charlin, J. Pineau. EMNLP, 2016.
– On the Evaluation of Dialogue Systems with Next Utterance Classification. R. Lowe, I. V. Serban, M. Noseworthy, L. Charlin, J. Pineau. SIGDIAL, 2016.
– Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus. I. V. Serban, A. García-Durán, C. Gulcehre, S. Ahn, S. Chandar, A. Courville, Y. Bengio. ACL, 2016.
– Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. I. V. Serban, A. Sordoni, Y. Bengio, A. Courville, J. Pineau. AAAI, 2016.
– A Survey of Available Corpora for Building Data-Driven Dialogue Systems. I. V. Serban, R. Lowe, L. Charlin, J. Pineau. Under review at the Dialogue & Discourse journal.
– Theano: A Python framework for fast computation of mathematical expressions. The Theano Development Team. 2016. arXiv:1605.02688.
– Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems. R. Lowe, N. Pow, I. V. Serban, L. Charlin and J. Pineau. NIPS, 2015. Workshop on Machine Learning for Spoken Language Understanding and Interaction.
– Text-Based Speaker Identification For Multi-Participant Open-Domain Dialogue Systems. I. V. Serban and J. Pineau. NIPS, 2015. Workshop on Machine Learning for Spoken Language Understanding and Interaction.
– The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems. R. Lowe, N. Pow, I. V. Serban, J. Pineau. SIGDIAL, 2015.
– Poverty in Denmark: A Socioeconomic Poverty Threshold. I. V. Serban, LIS Working Paper Series, No. 562, 2011. See also executive summary in English.
Technical Reports
– Learning to Play Chess from Scratch: Applying Deep Learning Models to Play Chess with Function Approximation based Reinforcement Learning. I. V. Serban. Master’s Thesis submitted at University College London, 2014. Supervised by David Barber and Peter Dayan.
– Seizure Detection Challenge: The Fitzgerald team solution. V. Adam, J. Soldado-Magraner, W. Jitkritum, H. Strathmann, B. Lakshminarayanan, A. D. Ialongo, G. Bohner, B. D. Huh, L. Goetz, S. Dowling, I. V. Serban, M. Louis. Technical report for seizure detection competition.
– Maximum Likelihood Learning and Inference In Conditional Random Fields. I. V. Serban, Bachelor’s Thesis submitted at Copenhagen University, 2012. See also accompanying source code.
– Prediction of changes in the stock market using twitter and sentiment analysis. I. V. Serban, D. Gonzalez and X. Wu, Research project submitted at University College London, 2014. See also accompanying source code.
– Implicit Affective Tagging, I. V. Serban, Research project submitted at University College London, 2014.