Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929415379746816 |
|---|---|
| author | Gao, Changjiang Li, Jixing Chen, Jiajun Huang, Shujian |
| author_facet | Gao, Changjiang Li, Jixing Chen, Jiajun Huang, Shujian |
| contents | The process of meaning composition, wherein smaller units like morphemes or words combine to form the meaning of phrases and sentences, is essential for human sentence comprehension. Despite extensive neurolinguistic research into the brain regions involved in meaning composition, a computational metric to quantify the extent of composition is still lacking. Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension. Experimental findings show that this metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting the multifaceted nature of meaning composition during human sentence comprehension. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04325 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models Gao, Changjiang Li, Jixing Chen, Jiajun Huang, Shujian Computation and Language Artificial Intelligence The process of meaning composition, wherein smaller units like morphemes or words combine to form the meaning of phrases and sentences, is essential for human sentence comprehension. Despite extensive neurolinguistic research into the brain regions involved in meaning composition, a computational metric to quantify the extent of composition is still lacking. Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension. Experimental findings show that this metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting the multifaceted nature of meaning composition during human sentence comprehension. |
| title | Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.04325 |