Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection

2026-04-15

AI Summary

This study addresses the challenge of automatically extending lexical resources such as WordNet to new languages for cross-lingual word sense generation. To this end, the authors propose a projection–filtering framework: first, target-language tokens are projected into the source-language sense space using English texts and their parallel translations, leveraging pretrained alignment models and bilingual dictionaries; subsequently, a semantic filtering mechanism is introduced to refine projection accuracy and ensure interpretability. Requiring only minimal external resources, the method substantially outperforms existing dictionary construction approaches and large language model baselines across multiple languages, significantly improving the accuracy of cross-lingual word sense generation.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Multimodal Learning
• Computer Vision: Language and Vision

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation. We generate senses by associating target-language lemmas with existing lexical concepts via semantic projection. Given a sense-tagged English corpus and its translation, our method projects English synsets onto aligned target-language tokens and assigns the corresponding lemmas to those synsets. To generate these alignments and ensure their quality, we augment a pre-trained base aligner with a bilingual dictionary, which is also used to filter out incorrect sense projections. We evaluate the method on multiple languages, comparing it to prior methods, as well as dictionary-based and large language model baselines. Results show that the proposed project-and-filter strategy improves precision while remaining interpretable and requiring few external resources. We plan to make our code, documentation, and generated sense inventories accessible.

Problem

• lexical resource expansion
• cross-lingual sense projection
• WordNet
• sense generation
• bilingual lexical alignment

Innovation

• cross-lingual sense projection
• bilingual dictionary
• WordNet expansion
• sense generation
• alignment filtering