If you made any changes in Pure these will be visible here soon.

Personal profile

Ancillary activities

No ancillary activities

Ancillary activities are updated daily

Fingerprint Fingerprint is based on mining the text of the person's scientific documents to create an index of weighted terms, which defines the key subjects of each individual researcher.

  • 50 Similar Profiles
Semantics Engineering & Materials Science
Violence Engineering & Materials Science

Research Output 2013 2018

Don't Annotate, but Validate: a Data-to-Text Method for Capturing Event Data

Vossen, P., Ilievski, F., Postma, M. & Roxane, S. 2018 [Proceedings of the] Eleventh International Conference on Language Resources and Evaluation (LREC 2018). Miyazaki: LREC, p. 1-9 9 p.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Violence
Semantics
Violence

Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?

Le, M., Postma, M. & Urbani, J. 9 Dec 2017 In : arXiv.org.

Research output: Contribution to journalArticle

Addressing the MFS Bias in WSD systems

Postma, M. C., Izquierdo, R., Agirre, E., Rigau, G. & Vossen, P. T. J. M. 2016 LREC 2016.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

More is not always better: balancing sense distributions for all-words Word Sense Disambiguation

Postma, M. C., Izquierdo, R. & Vossen, P. T. J. M. 2016 COLING.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Activities 2016 2016

  • 2 Lecture / Presentation

Moving away from semantic overfitting in disambiguation datasets

Postma, M. (Speaker), Ilievski, F. (Speaker), Vossen, P. (Speaker), M. Van Erp (Speaker)
5 Nov 2016

Activity: ScientificLecture / Presentation

Semantic overfitting: what `world' do we consider when evaluating disambiguation of text?

Ilievski, F. (Speaker), Postma, M. (Speaker), Vossen, P. (Speaker)
14 Dec 2016

Activity: ScientificLecture / Presentation