Evaluating the Representational Hub of Language and Vision Models
| Autor: | Shekhar, R., Takmaz, E., Fernández, R., Bernardi, R., Dobnik, S., Chatzikyriakidis, S., Demberg, V. |
|---|---|
| Přispěvatelé: | Language and Computation (ILLC, FNWI/FGw), ILLC (FNWI), Brain and Cognition, Faculty of Science |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Modalities Artificial neural network Computer science Intersection (set theory) Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Field (computer science) Task (computing) Human–computer interaction Question answering Computational linguistics Encoder Computation and Language (cs.CL) |
| Zdroj: | Proceedings of the 13th International Conference on Computational Semantics-Long Papers: IWCS 2019 : 23-27 May, 2019, University of Gothenburg, Gothenburg, Sweden, 211-222 STARTPAGE=211;ENDPAGE=222;TITLE=Proceedings of the 13th International Conference on Computational Semantics-Long Papers IWCS (1) Scopus-Elsevier |
| DOI: | 10.48550/arxiv.1904.06038 |
| Popis: | The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the brain processes and combines multi-sensory inputs. In particular, the Hub is implemented as a neural network encoder. We investigate the effect on this encoder of various vision-and-language tasks proposed in the literature: visual question answering, visual reference resolution, and visually grounded dialogue. To measure the quality of the representations learned by the encoder, we use two kinds of analyses. First, we evaluate the encoder pre-trained on the different vision-and-language tasks on an existing diagnostic task designed to assess multimodal semantic understanding. Second, we carry out a battery of analyses aimed at studying how the encoder merges and exploits the two modalities. Comment: Accepted to IWCS 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|