“What does attention in neural machine translation pay attention to?” by ILPS-ers Hamidreza Ghader and Christof Monz was accepted at IJCNLP 2017, the 8th International Joint Conference on Natural Language Processing.
As part of the Vox-POL research exchange program, Mark Burdick (Bremen) visits ILPS for a period of three months.
All your favorite IR measures from trec_eval are now available in Python! Today, ILPS-er Christophe Van Gysel releases pytrec_eval, a Python interface to TREC’s evaluation tool, trec_eval. It is an attempt to stop the cultivation of custom implementations of Information Retrieval evaluation measures for the Python programming language. See https://github.com/cvangysel/pytrec_eval
The following papers by ILPS-ers were accepted at CIKM 2017:
- Active Sampling for Large-scale Information Retrieval Evaluation by Dan Li and Evangelos Kanoulas
- Balancing Speed and Quality in Online Learning to Rank for Information Retrieval by Harrie Oosterhuis and Maarten de Rijke
- Classy: A visual analytics environment for supervised text classification and model evaluation by Ilias Koutsakis, Evangelos Kanoulas, George Tsatsaronis and Eamonn Maguire
- Learning to Attend, Copy, and Generate for Session Based Query Suggestion by Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca and Pascal Fleury
- Online Expectation-Maximization for Click Models by Ilya Markov, Alexey Borisov, Maarten de Rijke
- Reply With: Proactive Recommendation of Email Attachments by Christophe Van Gysel, Bhaskar Mitra, Matteo Venanzi, Roy Rosemarin, Grzegorz Kukla, Piotr Grudzien and Nicola Cancedda
- Sensitive and Scalable Online Evaluation with Theoretical Guarantees by Harrie Oosterhuis and Maarten de Rijke
- Words are Malleable: Computing Semantic Shifts in Political and Media Discourse by Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, and Jaap Kamps
Four papers were accepted at Neu-IR 2017: The SIGIR 2017 Workshop on Neural Information Retrieval. They are “Share your model instead of your data: Privacy preserving mimic learning for ranking” by Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, and Maarten de Rijke; “Modeling label ambiguity for listwise neural learning to rank” by Rolf Jagerman, Julia Kiseleva, and Maarten de Rijke; “Thread reconstruction in conversational data using neural coherence models” by Dat Tien Nguyen, Shafiq Joty, Basma El Amel Boussaha, and Maarten de Rijke; and “Semantic entity retrieval toolkit” by Christophe Van Gysel, Maarten de Rijke, and Evangelos Kanoulas.