Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use
Kluth T, Schultheis H (2018)
In: Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing. Idiart M, Lenci A, Poibeau T, Villavicencio A (Eds); Melbourne, Australia: Association for Computational Linguistics: 47-55.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Autor*in
Kluth, ThomasUniBi;
Schultheis, Holger
Herausgeber*in
Idiart, Marco;
Lenci, Alessandro;
Poibeau, Thierry;
Villavicencio, Aline
Einrichtung
Abstract / Bemerkung
We present two methods that improve the assessment of cognitive models. The first method is applicable to models computing average acceptability ratings. For these models, we propose an extension that simulates a full rating distribution (instead of average ratings) and allows generating individual ratings. Our second method enables Bayesian inference for models generating individual data. To this end, we propose to use the cross-match test (Rosenbaum, 2005) as a likelihood function. We exemplarily present both methods using cognitive models from the domain of spatial language use. For spatial language use, determining linguistic acceptability judgments of a spatial preposition for a depicted spatial relation is assumed to be a crucial process (Logan and Sadler, 1996). Existing models of this process compute an average acceptability rating. We extend the models and – based on existing data – show that the extended models allow extracting more information from the empirical data and yield more readily interpretable information about model successes and failures. Applying Bayesian inference, we find that model performance relies less on mechanisms of capturing geometrical aspects than on mapping the captured geometry to a rating interval.
Stichworte
cognitive modeling;
linguistic judgments;
Bayesian inference;
spatial language
Erscheinungsjahr
2018
Titel des Konferenzbandes
Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing
Seite(n)
47 - 55
Konferenz
Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing, co-located with the 56th Annual Meeting of the Association for Computational Linguistics
Konferenzort
Melbourne, Australia
Konferenzdatum
2018-07-19 – 2018-07-19
Page URI
https://pub.uni-bielefeld.de/record/2920199
Zitieren
Kluth T, Schultheis H. Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use. In: Idiart M, Lenci A, Poibeau T, Villavicencio A, eds. Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing. Melbourne, Australia: Association for Computational Linguistics; 2018: 47-55.
Kluth, T., & Schultheis, H. (2018). Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use. In M. Idiart, A. Lenci, T. Poibeau, & A. Villavicencio (Eds.), Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing (pp. 47-55). Melbourne, Australia: Association for Computational Linguistics.
Kluth, Thomas, and Schultheis, Holger. 2018. “Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use”. In Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing, ed. Marco Idiart, Alessandro Lenci, Thierry Poibeau, and Aline Villavicencio, 47-55. Melbourne, Australia: Association for Computational Linguistics.
Kluth, T., and Schultheis, H. (2018). “Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use” in Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing, Idiart, M., Lenci, A., Poibeau, T., and Villavicencio, A. eds. (Melbourne, Australia: Association for Computational Linguistics), 47-55.
Kluth, T., & Schultheis, H., 2018. Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use. In M. Idiart, et al., eds. Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing. Melbourne, Australia: Association for Computational Linguistics, pp. 47-55.
T. Kluth and H. Schultheis, “Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use”, Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing, M. Idiart, et al., eds., Melbourne, Australia: Association for Computational Linguistics, 2018, pp.47-55.
Kluth, T., Schultheis, H.: Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use. In: Idiart, M., Lenci, A., Poibeau, T., and Villavicencio, A. (eds.) Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing. p. 47-55. Association for Computational Linguistics, Melbourne, Australia (2018).
Kluth, Thomas, and Schultheis, Holger. “Rating Distributions and Bayesian Inference. Enhancing Cognitive Models of Spatial Language Use”. Proceedings of the Eighth Workshop on Cognitive Aspects of Computational Language Learning and Processing. Ed. Marco Idiart, Alessandro Lenci, Thierry Poibeau, and Aline Villavicencio. Melbourne, Australia: Association for Computational Linguistics, 2018. 47-55.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Name
acl2018_workshop_long.pdf
365.78 KB
Access Level
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Zuletzt Hochgeladen
2019-09-25T06:51:48Z
MD5 Prüfsumme
aa8e62b1d008b22f536969636a239674
Link(s) zu Volltext(en)
Access Level
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Material in PUB:
In sonstiger Relation
A C++ implementation of cognitive models of spatial language understanding as well as pertinent empirical data and analyses.
Kluth T (2018)
Bielefeld University.
Kluth T (2018)
Bielefeld University.