Abstract
Recent work in cognitive neuroscience has introduced models for predicting distributional word meaning representations from brain imaging data. Such models have great potential, but the quality of their predictions has not yet been thoroughly evaluated from a computational linguistics point of view. Due to the limited size of available brain imaging datasets, standard quality metrics (e.g. similarity judgments and analogies) cannot be used. Instead, we investigate the use of several alternative measures for evaluating the predicted distributional space against a corpus-derived distributional space. We show that a state-of-the-art decoder, while performing impressively on metrics that are commonly used in cognitive neuroscience, performs unexpectedly poorly on our metrics. To address this, we propose strategies for improving the model’s performance. Despite returning promising results, our experiments also demonstrate that much work remains to be done before distributional representations can reliably be predicted from brain data.- Anthology ID:
- P19-2021
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 155–161
- Language:
- URL:
- https://aclanthology.org/P19-2021
- DOI:
- 10.18653/v1/P19-2021
- Cite (ACL):
- Gosse Minnema and Aurélie Herbelot. 2019. From Brain Space to Distributional Space: The Perilous Journeys of fMRI Decoding. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 155–161, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- From Brain Space to Distributional Space: The Perilous Journeys of fMRI Decoding (Minnema & Herbelot, ACL 2019)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/P19-2021.pdf
- Code
- gosseminnema/ds-brain-decoding