Publications

Scientific publications

  • Ander Barrena, Aitor Soroa, Eneko Agirre. Learning text representations for 500K classification tasks on Named Entity Disambiguation. Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL 2018), pages 171–180. 2018.

  • Alvaro Rodrigo, Anselmo Peñas, Yusuke Miyao, Noriko Kando. Do systems pass university entrance exams? Information Processing & Management, Volume 54, Issue 4, 2018, Pages 564-575, ISSN 0306-4573. 2018.

  • Alvaro Rodrigo, Jesús Herrera, Anselmo Peñas. The effect of answer validation on the performance of Question-Answering systems. Expert Systems with Applications, Volume 116, 2019, Pages 351-363, ISSN 0957-4174. 2019.

  • Mathilde Veron, Sahar Ghannay, Anne-Laure Ligozat, Sophie Rosset.  Lifelong learning and task-oriented dialogue system: what does it mean? Dialogue Systems and Lifelong Learning special session at Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS). 2019.

  • Mark Cieliebak, Olivier Galibert, Jan Deriu. Towards Understanding Lifelong Learning for Dialogue Systems. Dialogue Systems and Lifelong Learning special session at Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS). 2019.

  • Anselmo Peñas, Mathilde Veron, Camille Pradel, Arantxa Otegi, Guillermo Echegoyen, Alvaro Rodrigo. Continuous Learning for Question Answering. Dialogue Systems and Lifelong Learning special session at Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS). 2019.

  • Eneko Agirre, Anders Jonsson, Anthony Larcher. Framing Lifelong Learning as Autonomous Deployment: Tune Once Live Forever. Dialogue Systems and Lifelong Learning special session at Tenth International Workshop on Spoken Dialogue Systems Technology (IWSDS). 2019.

  • Jan Deriu, Alvaro Rodrigo, Arantxa Otegi, Guillermo Echegoyen, Sophie Rosset, Eneko Agirre, Mark Cieliebak. Survey on Evaluation Methods for Dialogue Systems. Pre-print available at arXiv:1905.04071. 2019.

  • Eneko Agirre, Arantxa Otegi, Camille Pradel, Sophie Rosset, Anselmo Peñas, Mark Cieliebak. LIHLITH: Learning to Interact with Humans by Lifelong Interaction with Humans. SEPLN 2019 (accepted)

 

Project deliverables

  • D1.1 - Report on evaluation methods for dialogue systems
  • D1.2 - Report on the evaluation of lifelong learning for dialogue systems
  • D3.1 - System for knowledge induction and generation of low-dimensional representations
  • D3.2 - Baseline Question Answering system
  • D4.1 - Baseline chatbot for community question answering

 

Press releases