Guardado en:
Detalles Bibliográficos
Autores principales: Rezaabad, Ali Lotfi, Khanal, Bikram, Chaurasia, Shashwat, Zeng, Lu, Hong, Dezhi, Bashashati, Hossein, Butler, Thomas, Ganji, Megan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.08143
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908704201244672
author Rezaabad, Ali Lotfi
Khanal, Bikram
Chaurasia, Shashwat
Zeng, Lu
Hong, Dezhi
Bashashati, Hossein
Butler, Thomas
Ganji, Megan
author_facet Rezaabad, Ali Lotfi
Khanal, Bikram
Chaurasia, Shashwat
Zeng, Lu
Hong, Dezhi
Bashashati, Hossein
Butler, Thomas
Ganji, Megan
contents Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases -- such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets -- Amazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching) -- PolyLingua achieves 99.25% F1 and 98.15% F1, respectively, surpassing Sonnet 3.5 while using 10x fewer parameters, making it ideal for compute- and latency-constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08143
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection
Rezaabad, Ali Lotfi
Khanal, Bikram
Chaurasia, Shashwat
Zeng, Lu
Hong, Dezhi
Bashashati, Hossein
Butler, Thomas
Ganji, Megan
Machine Learning
Language identification is a crucial first step in multilingual systems such as chatbots and virtual assistants, enabling linguistically and culturally accurate user experiences. Errors at this stage can cascade into downstream failures, setting a high bar for accuracy. Yet, existing language identification tools struggle with key cases -- such as music requests where the song title and user language differ. Open-source tools like LangDetect, FastText are fast but less accurate, while large language models, though effective, are often too costly for low-latency or low-resource settings. We introduce PolyLingua, a lightweight Transformer-based model for in-domain language detection and fine-grained language classification. It employs a two-level contrastive learning framework combining instance-level separation and class-level alignment with adaptive margins, yielding compact and well-separated embeddings even for closely related languages. Evaluated on two challenging datasets -- Amazon Massive (multilingual digital assistant utterances) and a Song dataset (music requests with frequent code-switching) -- PolyLingua achieves 99.25% F1 and 98.15% F1, respectively, surpassing Sonnet 3.5 while using 10x fewer parameters, making it ideal for compute- and latency-constrained environments.
title PolyLingua: Margin-based Inter-class Transformer for Robust Cross-domain Language Detection
topic Machine Learning
url https://arxiv.org/abs/2512.08143