SpaceRefNet: a neural approach to spatial reference resolution in a real city environment

Dmytro Kalpakchi, Johan Boye


Abstract
Adding interactive capabilities to pedestrian wayfinding systems in the form of spoken dialogue will make them more natural to humans. Such an interactive wayfinding system needs to continuously understand and interpret pedestrian’s utterances referring to the spatial context. Achieving this requires the system to identify exophoric referring expressions in the utterances, and link these expressions to the geographic entities in the vicinity. This exophoric spatial reference resolution problem is difficult, as there are often several dozens of candidate referents. We present a neural network-based approach for identifying pedestrian’s references (using a network called RefNet) and resolving them to appropriate geographic objects (using a network called SpaceRefNet). Both methods show promising results beating the respective baselines and earlier reported results in the literature.
Anthology ID:
W19-5949
Volume:
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Month:
September
Year:
2019
Address:
Stockholm, Sweden
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
422–431
Language:
URL:
https://aclanthology.org/W19-5949
DOI:
10.18653/v1/W19-5949
Bibkey:
Cite (ACL):
Dmytro Kalpakchi and Johan Boye. 2019. SpaceRefNet: a neural approach to spatial reference resolution in a real city environment. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 422–431, Stockholm, Sweden. Association for Computational Linguistics.
Cite (Informal):
SpaceRefNet: a neural approach to spatial reference resolution in a real city environment (Kalpakchi & Boye, SIGDIAL 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-5949.pdf