Skip to content

Aligning Embedding Spaces Across Languages to Identify Word Level Equivalents in the Context of Concreteness and Emotion

· 0 citations · 34 references

TL;DR

A neural network is used to model a bilingual mapping within an English-Mandarin semantic space and indicates interesting possibilities for using quantitative word-level modeling as a tool to analyze the overlapping impacts of bilingualism, emotionality, and abstraction on each other.

View source

Similar papers

Open access Aug 2026

The integration of prosody and semantics in non-literal speech: A voxel-wise encoding model approach using large language models

Irony and sarcasm are complex forms of non-literal language that hinge on a misalignment between surface meaning and speaker intent, requiring listeners to integrate contextual, semantic, and prosodic cues. While prior neuroimaging studies have implicated a broad network—including the temporal cortex, the inferior fron...

Wittmann Adrien, Ceravolo Leonardo, Grandjean Didier · 0 citations
Open access Sep 2026

The Shortcomings of Natural Language Processing (NLP) Models and Their Applications in Achieving Accuracy in Translating from Arabic to English

This study highlights the importance of integrating in-depth linguistic analysis, contextual semantic modelling, and cultural awareness into natural language processing-based translation systems by combining traditional linguistic insights with computational methods.

Hilal Abdul-Raziq Sadiq, Zaxid Maxmudovich Islamov, R. Matibaeva et al. · 0 citations
Open access Aug 2026

Translation direction and word familiarity in word translation: an fNIRS study of intermediate Japanese learners of English

Introduction Many studies have examined the neural bases of word translation based on the revised hierarchical model (RHM). However, the findings reported thus far, mostly focusing on advanced or elementary second-language (L2) learners, have been diverse and often inconsistent. Thus, to explore possible neural bases f...

Wakana Kawai, Kiyomitsu Niioka, Hikari Tanaka et al. · 0 citations
Open access Sep 2026

The Structural Sources of Verb Meanings Revisited: Large Language Models Display Syntactic Bootstrapping

The results show that models’ verb representations degrade more when the authors perturb word order, which removes syntactic information, than when they perturb co-occurrence among content words, which removes semantic information.

Xiao-Meng Zhu, R. Thomas McCoy, Robert Frank · 0 citations
Open access Aug 2026

Linguistic frame switching in German–English bilinguals: implications for neuroscience

Introduction: Multilingual speakers frequently report that operating in a different language involves more than a change in grammatical system. The phenomenon at issue is linguistic frame switching (LFS): the involuntary reorganisation of cognitive, emotional, and identity-relevant schemas when a multilingual speaker m...

Judith Zangerle · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.