umu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Persiani, Michele
Publications (1 of 1) Show all publications
Persiani, M. & Hellström, T. (2019). Unsupervised Inference of Object Affordance from Text Corpora. In: Mareike Hartmann, Barbara Plank (Ed.), Proceedings of the 22nd Nordic Conference on Computational Linguistics: . Paper presented at 22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19), September 30 – October 2, 2019, Turku, Finland. Association for Computational Linguistics, Article ID W19-6112.
Open this publication in new window or tab >>Unsupervised Inference of Object Affordance from Text Corpora
2019 (English)In: Proceedings of the 22nd Nordic Conference on Computational Linguistics / [ed] Mareike Hartmann, Barbara Plank, Association for Computational Linguistics, 2019, article id W19-6112Conference paper, Published paper (Refereed)
Abstract [en]

Affordances denote actions that can be performed in the presence of different objects, or possibility of action in an environment. In robotic systems, affordances and actions may suffer from poor semantic generalization capabilities due to the high amount of required hand-crafted specifications. To alleviate this issue, we propose a method to mine for object-action pairs in free text corpora, successively training and evaluating different prediction models of affordance based on word embeddings.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2019
Keywords
Affordance, Natural Language Processing, Robotics, Intention Recognition, Conditional Variational Autoencoder
National Category
Robotics
Identifiers
urn:nbn:se:umu:diva-163356 (URN)
Conference
22nd Nordic Conference on Computational Linguistics (NoDaLiDa’19), September 30 – October 2, 2019, Turku, Finland
Available from: 2019-09-16 Created: 2019-09-16 Last updated: 2019-10-23Bibliographically approved
Organisations

Search in DiVA

Show all publications