<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Metaphorical information is prevalent in literary texts, and understanding the cultural and historical contexts of Japanese literature can significantly enhance the translation of its metaphors. This paper introduces a knowledge graph specifically designed for translating metaphorical content in Japanese literary works. This graph facilitates the categorization, extraction, and storage of symbolic information. To refine the knowledge graph further, the RAEA model is employed, coupled with a distinct attention mechanism assigned to each node of symbolic information. This approach significantly improves the entity alignment in translations, thereby enhancing translational accuracy. In constructing a dataset that includes background symbolic information, the knowledge graph demonstrated a precision of 0.9256 and a recall of 0.9136. Additionally, the graph achieved an average Mean Reciprocal Rank (MRR) index of 0.810, markedly surpassing traditional translation models. This paper’s knowledge graph thus offers an effective methodology for the precise translation and interpretation of symbolic information in Japanese literature, aiding in the deeper comprehension and accurate representation of such content.</p>
</abstract>

Metaphorical information is prevalent in literary texts, and understanding the cultural and historical contexts of Japanese literature can significantly enhance the translation of its metaphors. This paper introduces a knowledge graph specifically designed for translating metaphorical content in Japanese literary works. This graph facilitates the categorization, extraction, and storage of symbolic information. To refine the knowledge graph further, the RAEA model is employed, coupled with a distinct attention mechanism assigned to each node of symbolic information. This approach significantly improves the entity alignment in translations, thereby enhancing translational accuracy. In constructing a dataset that includes background symbolic information, the knowledge graph demonstrated a precision of 0.9256 and a recall of 0.9136. Additionally, the graph achieved an average Mean Reciprocal Rank (MRR) index of 0.810, markedly surpassing traditional translation models. This paper’s knowledge graph thus offers an effective methodology for the precise translation and interpretation of symbolic information in Japanese literature, aiding in the deeper comprehension and accurate representation of such content.

Applying Knowledge Mapping Techniques to Enhance Contextual Understanding and Accurate Correspondence in Translating Metaphorical Information in Japanese Literature

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Metaphorical information is prevalent in literary texts, and understanding the cultural and historical contexts of Japanese literature can significantly...

Applying Knowledge Mapping Techniques to Enhance Contextual Understanding and Accurate Correspondence in Translating Metaphorical Information in Japanese Literature

Publié en ligne: 03 juin 2024

Pages: -

Reçu: 15 févr. 2024

Accepté: 16 avr. 2024

DOI: https://doi.org/10.2478/amns-2024-1348

Mots clés
Knowledge graph, Entity alignment, RAEA model, Attention mechanism, Metaphorical information translation

© 2024 Shengting Yue, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Applying Knowledge Mapping Techniques to Enhance Contextual Understanding and Accurate Correspondence in Translating Metaphorical Information in Japanese Literature

Publié en ligne: 03 juin 2024

Pages: -

Reçu: 15 févr. 2024

Accepté: 16 avr. 2024

DOI: https://doi.org/10.2478/amns-2024-1348

Mots clésKnowledge graph, Entity alignment, RAEA model, Attention mechanism, Metaphorical information translation

© 2024 Shengting Yue, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Knowledge graph, Entity alignment, RAEA model, Attention mechanism, Metaphorical information translation