paper-with-me

홈 › Papers

Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models

2024-03-07 · Changjiang Gao, Jixing Li, Jiajun Chen, ShuJian Huang

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.

📄 PDF Abstract BibTeX arXiv:2403.04325

Code (1)

rivergao/ffn_composition_analysis 공식 구현 pytorch

Tasks

Sentence

Similar Papers 제목 키워드 기반

Decoding Brain Activity Associated with Literal and Metaphoric Sentence Comprehension Using Distributional Semantic Models

2020-01-01 · TACL 2020 1 · Vesna G. Djokic, Jean Maillard, Luana Bulat, Ekaterina Shutova

Recent years have seen a growing interest within the natural language processing (NLP) community in evaluating the ability of semantic models to capture human meaning representation in the brain. Existing research has ma…

SentenceWord Embeddings

Investigating Inner Properties of Multimodal Representation and Semantic Compositionality with Brain-based Componential Semantics

2017-11-15 · Shaonan Wang, Jiajun Zhang, Nan Lin, Cheng-qing Zong

Multimodal models have been proven to outperform text-based approaches on learning semantic representations. However, it still remains unclear what properties are encoded in multimodal representations, in what aspects do…

Learning Semantic RepresentationsNatural Language Understanding

Measuring non-trivial compositionality in emergent communication

2020-10-28 · Tomasz Korbak, Julian Zubek, Joanna Rączaszek-Leonardi

Compositionality is an important explanatory target in emergent communication and language evolution. The vast majority of computational models of communication account for the emergence of only a very basic form of comp…

Modeling Affirmative and Negated Action Processing in the Brain with Lexical and Compositional Semantic Models

2019-07-01 · ACL 2019 7 · Vesna Djokic, Jean Maillard, Luana Bulat, Ekaterina Shutova

Recent work shows that distributional semantic models can be used to decode patterns of brain activity associated with individual words and sentence meanings. However, it is yet unclear to what extent such models can be …

NegationSemantic CompositionSentence

What Meaning-Form Correlation Has to Compose With

2020-12-07 · Timothee Mickus, Timothée Bernard, Denis Paperno

Compositionality is a widely discussed property of natural languages, although its exact definition has been elusive. We focus on the proposal that compositionality can be assessed by measuring meaning-form correlation. …

Form