My research interests are in natural language processing, machine translation, information retrieval, language and multimodal resources, and the evaluation of linguistic and interactive systems.

My current research projects include :

  • DOMAT (On-demand Knowledge for Document-level Machine Translation) supported by the SNSF
  • PLACAT (Plateforme d’agents conversationnels pour l’accès aux connaissances textuelles) supported by the HES-SO

Previously, I have been the leader of the MODERN SNSF Sinergia project (2013-2017) on Modeling Discourse Entities and Relations for Coherent Machine Translation, which followed the COMTIS Sinergia project (2010-2013), on Improving the Coherence of Machine Translation Output by Modeling Intersentential Relations. I have been involved in the IM2 NCCR from its start (2002-2013), working on dialogue processing, data management and HCI, as head or deputy head of two individual projects. I have contributed to the SUMMA EU project (2016-2017), as well as to the inEvent European project (2011-2014), and to the AMIDA European integrated project (2007-2010) as head of a work package on interfaces and evaluation.

Publication list | Google Scholar profile

Recent papers

  1. Popescu-Belis A. (2019) – Context in Neural Machine Translation: A Review of Models and Evaluations. arXiv:1901.09115, Jan. 2019, 16 p.
  2. Pu X., Pappas N., Henderson J., & Popescu-Belis A. (2018) – Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation. Transactions of the Association for Computational Linguistics (TACL), vol. 6, p. 635-649.
  3. Miculicich L., Pappas N., Ram D., & Popescu-Belis A. (2018) – Self-Attentive Residual Decoder for Neural Machine Translation. Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2018), New Orleans, LA, USA, June 2018.
  4. Honnet P.-E., Popescu-Belis A., Musat C., Baeriswyl M. (2018) – Machine Translation of Low-Resource Spoken Dialects: Strategies for Normalizing Swiss German. Proceedings of the 11th Language Resources and Evaluation Conference (LREC), Miyazaki, Japan, May 2018.
  5. Pappas N. & Popescu-Belis A. (2017) – Multilingual Hierarchical Attention Networks for Document Classification. Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), Taipei, Taiwan. Best paper award.
  6. Pappas N. & Popescu-Belis A. (2017) – Explicit Document Modeling through Weighted Multiple-Instance Learning. Journal of Artificial Intelligence Research (JAIR), vol. 58, p. 591-626.

Other recent communications

  1. Luthier G. and Popescu-Belis A. (2019) – PLACAT: A user-friendly question answering system for smart speaker devices. Talk at the 4th Swiss Text Analytics Conference (SwissText 2019), Winterthur, June 2019.
  2. Large contexts in neural machine translation. Talk at the 3rd Applied Machine Learning Days (AMLD 2019), EPFL, Lausanne, Switzerland, 29 January 2019.
  3. Intelligence artificielle et langage humain. Conférence Pro, Numerik Games, Yverdon-les-Bains, 23 August 2018.
  4. Les traducteurs en ligne se sont bien améliorés.  Interviewed for an article by C. Chevrolet, in the magazine Bon à Savoir, April 2018, pages 14-15.
  5. Popescu-Belis A. (2017) – Document-level Statistical MT: from Connectives to Pronouns. Invited talk to the Workshop on “Machine Translation meets Translators”, University of Zürich, 16 May 2017.
  6. Machine translation: going beyond sentence by sentence, press release by the SNSF on April 3, 2017, followed by articles in about 15 printed newspapers and 30 online media.