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

Personal information

My name is Marten Postma and I’m a PhD student supervised by professor Piek Vossen and assistant professor Jacopo Urbani.

My interest lies in Semantics, with an emphasis on Word Sense Disambiguation. Aside from the system aspect, I like investigating the strengths and weaknesses of current disambiguation approaches and to carefully think about how we evaluate.

My programming language of choice is Python. For a number of years now, I’m been involved in a Python course, geared towards those who want to get some hands-on experience working with language data.

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.

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

Research Output 2013 2018

Deep Dive into Word Sense Disambiguation with LSTM

Le, M. N., Postma, M. C., Urbani, J. & Vossen, P. T. J. M., 2018, Proceedings of the International Conference on Computational Linguistics (COLING 2018).

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

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 contributionAcademicpeer-review

Violence

ReferenceNet: A semantic-pragmatic network for capturing reference relations

Vossen, P., Postma, M. & Ilievski, F., Jan 2018

Research output: Contribution to ConferencePaperAcademic

Semantics
Violence

SemEval-2018 Task 5: Counting Events and Participants in the Long Tail

Postma, M. C., Ilievski, F. & Vossen, P. T. J. M., 2018

Research output: Contribution to ConferencePaperAcademic

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 JournalArticleAcademic

Activities 2016 2018

  • 2 Lecture / Presentation
  • 1 Workshop

SemEval-2018 Task: Counting Events and Participants in the Long Tail at SemEval-2018

Vossen, P. T. J. M. (Organiser), Postma, M. C. (Organiser), Ilievski, F. (Organiser)
2018

Activity: Participating in or organising an eventWorkshopAcademic

Moving away from semantic overfitting in disambiguation datasets

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

Activity: Lecture / PresentationAcademic

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

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

Activity: Lecture / PresentationAcademic