LuxEmbedder: A Cross-Lingual Approach to Enhanced Luxembourgish Sentence Embeddings
This work addresses the scarcity of parallel data for low-resource languages in NLP, benefiting researchers and practitioners working with languages like Luxembourgish, though it is incremental as it builds on existing cross-lingual embedding methods.
The authors tackled the problem of suboptimal sentence embeddings for low-resource languages like Luxembourgish by compiling a small, high-quality cross-lingual parallel dataset to train LuxEmbedder, resulting in enhanced embeddings with strong cross-lingual capabilities, and they created a Luxembourgish paraphrase detection benchmark to promote further research.
Sentence embedding models play a key role in various Natural Language Processing tasks, such as in Topic Modeling, Document Clustering and Recommendation Systems. However, these models rely heavily on parallel data, which can be scarce for many low-resource languages, including Luxembourgish. This scarcity results in suboptimal performance of monolingual and cross-lingual sentence embedding models for these languages. To address this issue, we compile a relatively small but high-quality human-generated cross-lingual parallel dataset to train LuxEmbedder, an enhanced sentence embedding model for Luxembourgish with strong cross-lingual capabilities. Additionally, we present evidence suggesting that including low-resource languages in parallel training datasets can be more advantageous for other low-resource languages than relying solely on high-resource language pairs. Furthermore, recognizing the lack of sentence embedding benchmarks for low-resource languages, we create a paraphrase detection benchmark specifically for Luxembourgish, aiming to partially fill this gap and promote further research.