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

TL;DR

This paper presents a method for expanding lexical resources into new languages by projecting English senses onto target languages using a bilingual dictionary-enhanced aligner, improving precision and interpretability.

Contribution

The authors introduce a dictionary-augmented sense projection method that enhances cross-lingual lexical resource expansion with minimal external resources.

Findings

The method improves projection precision over prior approaches.

It remains interpretable and resource-efficient.

Evaluation across multiple languages demonstrates effectiveness.

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.