In this study, using k-means and UMAP, we verified that the sentence vectors generated by Sentence-BERT as distributed representations of sentences capture meaning well. To end, visualized generating images matching from Sentence-BERT. The results confirm although there were differences in information represented each dimension distributional features vector, overlapped substantially.

ions are being discussed in other chapters in this book (Barsalou & WiemerHastings, this volume; Gibbs, this volume; Prinz, this volume). 6.0 Conclusion and outlook We started this chapter by comparing two perspectives on cognition in general and on language comprehension in particular. According to the traditional perspective, language comprehension involves the activation and integration of d...

background: cerebrovascular disease leading to stroke is the most common cause of aphasia. speakers with agrammatic non-fluent aphasia have difficulties in production of movement-derived sentences such as passive sentences, topicalized constituents, and wh-questions. to assess the production of complex sentences, some passive, topicalized and focused sentences were designed for patients with no...