iKernels

Machine Learning and NLP group at Trento.

Iryna Haponchyk

Research Fellow
University of Trento
Department of Information Engineering and Computer Science
Italy, TN 38123
Email: iryna.haponchyk@unitn.it

Such complex prediction tasks like coreference resolution in NLP are tackled with learning algorithms making inference in structured output spaces. These algorithms produce a complex output object in question at once, globally. We aim at elaborating methods for consolidation of structured learning with the task specific knowledge, e.g., delving into devising inference procedures in the spaces of complex objects like trees, graphs and sequences, and developing optimization methods for the cost functions that are specific to the task in question. In particular, we have been investigating the structured output learning aspects in application to supervised clustering and structural ranking.

News and Activities

[February, 2019] Our paper entitled

A Study of Latent Structured Prediction Approaches to Passage Reranking.

was accepted to appear in NAACL-HLT 2019.

[August, 2018] Our paper entitled

Supervised Clustering of Questions into Intents for Dialog System Applications.

was accepted to appear in EMNLP 2018.

[April, 2018] Defended my PhD dissertation entitled

Advanced models of supervised structural clustering.

[April, 2017] Our paper entitled

Don’t understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures.

was accepted to appear in ACL 2017.

[September, 2016] Participation in the NetCla: The ECML-PKDD Network Classification Challenge to predict applications by the network traffic. The proposed model won the 1st place (among 25 competing teams).

Publications

  • Haponchyk, I., Moschitti, A. (2019) A Study of Latent Structured Prediction Approaches to Passage Reranking. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 1847-1857, Minneapolis, Minnesota, USA, 2019.

  • Haponchyk, I., Uva, A., Yu, S., Uryupina, O., and Moschitti, A. (2018) Supervised Clustering of Questions into Intents for Dialog System Applications. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2310--2321, Brussels, Belgium, 2018. pdf

  • Haponchyk, I. (2018) Advanced models of supervised structural clustering. PhD thesis, University of Trento, Italy, 2018.

  • Haponchyk, I., Moschitti, A. (2017) Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1018-1028, Vancouver, Canada, 2017.

  • Haponchyk, I., Moschitti, A. (2017) A Practical Perspective on Latent Structured Prediction for Coreference Resolution. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), pp. 143-149, Valencia, Spain, 2017. poster

  • Haponchyk, I., Moschitti, A. (2014) Making Latent SVMstruct Practical for Coreference Resolution. In Proceedings of the First Italian Conference on Computational Linguistics (CLiC-it 2014), pp. 203-207, Pisa, Italy, 2014. poster