Subword Representations Successfully Decode Brain Responses to Morphologically Complex Written Words

TL;DR

This study shows that brain responses to complex Finnish words can be decoded using subword segments, suggesting the brain processes both whole words and their morphological components.

Contribution

The study introduces morphologically aware subword representations for decoding brain responses to morphologically complex words in agglutinative languages.

Findings

Decoding accuracy exceeded significance thresholds for all segmentations at 350–500 ms after stimulus onset.

Only morphologically aware segmentations reached significance in the brain decoding task.

Neural decoding using subword segments is effective for multimorphemic words in languages with complex morphology.

Abstract

This study extends the idea of decoding word-evoked brain activations using a corpus-semantic vector space to multimorphemic words in the agglutinative Finnish language. The corpus-semantic models are trained on word segments, and decoding is carried out with word vectors that are composed of these segments. We tested several alternative vector-space models using different segmentations: no segmentation (whole word), linguistic morphemes, statistical morphemes, random segmentation, and character-level 1-, 2- and 3-grams, and paired them with recorded MEG responses to multimorphemic words in a visual word recognition task. For all variants, the decoding accuracy exceeded the standard word-label permutation-based significance thresholds at 350–500 ms after stimulus onset. However, the critical segment-label permutation test revealed that only those segmentations that were morphologically aware reached significance in the brain decoding task. The results suggest that both whole-word forms and morphemes are represented in the brain and show that neural decoding using corpus-semantic word representations derived from compositional subword segments is applicable also for multimorphemic word forms. This is especially relevant for languages with complex morphology, because a large proportion of word forms are rare and it can be difficult to find statistically reliable surface representations for them in any large corpus.

Figures