Fatma Deniz


pdf bib
Attention weights accurately predict language representations in the brain
Mathis Lamarre | Catherine Chen | Fatma Deniz
Findings of the Association for Computational Linguistics: EMNLP 2022

In Transformer-based language models (LMs) the attention mechanism converts token embeddings into contextual embeddings that incorporate information from neighboring words. The resulting contextual hidden state embeddings have enabled highly accurate models of brain responses, suggesting that the attention mechanism constructs contextual embeddings that carry information reflected in language-related brain representations. However, it is unclear whether the attention weights that are used to integrate information across words are themselves related to language representations in the brain. To address this question we analyzed functional magnetic resonance imaging (fMRI) recordings of participants reading English language narratives. We provided the narrative text as input to two LMs (BERT and GPT-2) and extracted their corresponding attention weights. We then used encoding models to determine how well attention weights can predict recorded brain responses. We find that attention weights accurately predict brain responses in much of the frontal and temporal cortices. Our results suggest that the attention mechanism itself carries information that is reflected in brain representations. Moreover, these results indicate cortical areas in which context integration may occur.


pdf bib
Non-Complementarity of Information in Word-Embedding and Brain Representations in Distinguishing between Concrete and Abstract Words
Kalyan Ramakrishnan | Fatma Deniz
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

Word concreteness and imageability have proven crucial in understanding how humans process and represent language in the brain. While word-embeddings do not explicitly incorporate the concreteness of words into their computations, they have been shown to accurately predict human judgments of concreteness and imageability. Inspired by the recent interest in using neural activity patterns to analyze distributed meaning representations, we first show that brain responses acquired while human subjects passively comprehend natural stories can significantly distinguish the concreteness levels of the words encountered. We then examine for the same task whether the additional perceptual information in the brain representations can complement the contextual information in the word-embeddings. However, the results of our predictive models and residual analyses indicate the contrary. We find that the relevant information in the brain representations is a subset of the relevant information in the contextualized word-embeddings, providing new insight into the existing state of natural language processing models.