Imagen de Portada

AfroXLMR-Comet: Multilingual Knowledge Distillation with Attention Matching for Low-Resource languages

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Raju, Joshua Sakthivel, S, Sanjay, Walia, Jaskaran Singh, Raghav, Srinivas, Marivate, Vukosi
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Information Retrieval Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification
por: Vashisht, Varun, et al.
Publicado: (2025)

Cross-lingual transfer of multilingual models on low resource African Languages
por: Thangaraj, Harish, et al.
Publicado: (2024)

HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps
por: Huang, Jizhou, et al.
Publicado: (2024)

The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraints
por: Marivate, Vukosi
Publicado: (2026)

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text
por: Belay, Tadesse Destaw, et al.
Publicado: (2025)

Distillation for Multilingual Information Retrieval
por: Yang, Eugene, et al.
Publicado: (2024)

Preference-Consistent Knowledge Distillation for Recommender System
por: Zhu, Zhangchi, et al.
Publicado: (2023)

Analysing Public Transport User Sentiment on Low Resource Multilingual Data
por: Myoya, Rozina L., et al.
Publicado: (2024)

Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model
por: Cui, Yu, et al.
Publicado: (2024)

Knowledge Graph Reasoning Based on Attention GCN
por: Gupta, Meera, et al.
Publicado: (2023)

PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning
por: Wei, Wei, et al.
Publicado: (2024)

Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP
por: Tan, Zhiyin, et al.
Publicado: (2026)

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval
por: Jang, Youngjoon, et al.
Publicado: (2026)

WSDM Cup 2026 Multilingual Retrieval: A Low-Cost Multi-Stage Retrieval Pipeline
por: Hao, Chentong, et al.
Publicado: (2026)

Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprise
por: Ahmad, Syed Rameel
Publicado: (2024)

Integrating Structure-Aware Attention and Knowledge Graphs in Explainable Recommendation Systems
por: Lyu, Shuangquan, et al.
Publicado: (2025)

RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance
por: Jiang, Hengjun, et al.
Publicado: (2026)

Zero-shot Cross-domain Knowledge Distillation: A Case study on YouTube Music
por: Ranganathan, Srivaths, et al.
Publicado: (2026)

Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation
por: Tamber, Manveer Singh, et al.
Publicado: (2025)

Model-Free Approximate Bayesian Learning for Large-Scale Conversion Funnel Optimization
por: Iyengar, Garud, et al.
Publicado: (2024)

From N-grams to Pre-trained Multilingual Models For Language Identification
por: Sindane, Thapelo, et al.
Publicado: (2024)

SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
por: Kang, Inwon, et al.
Publicado: (2026)

Spatial-Temporal Knowledge Distillation for Takeaway Recommendation
por: Zhao, Shuyuan, et al.
Publicado: (2024)

Curriculum-scheduled Knowledge Distillation from Multiple Pre-trained Teachers for Multi-domain Sequential Recommendation
por: Sun, Wenqi, et al.
Publicado: (2024)

Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation
por: Li, Zizhong, et al.
Publicado: (2024)

Knowledge Distillation Approaches for Accurate and Efficient Recommender System
por: Kang, SeongKu
Publicado: (2024)

CSRM-LLM: Embracing Multilingual LLMs for Cold-Start Relevance Matching in Emerging E-commerce Markets
por: Wang, Yujing, et al.
Publicado: (2025)

Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
por: Tamber, Manveer Singh, et al.
Publicado: (2025)

Improving Low-Resource Retrieval Effectiveness using Zero-Shot Linguistic Similarity Transfer
por: Chari, Andreas, et al.
Publicado: (2025)

Food Data in the Semantic Web: A Review of Nutritional Resources, Knowledge Graphs, and Emerging Applications
por: Sasanski, Darko, et al.
Publicado: (2025)

Distillation-based Scenario-Adaptive Mixture-of-Experts for the Matching Stage of Multi-scenario Recommendation
por: Wang, Ruibing, et al.
Publicado: (2025)

Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
por: Zhu, Zhangchi, et al.
Publicado: (2025)

MLSA4Rec: Mamba Combined with Low-Rank Decomposed Self-Attention for Sequential Recommendation
por: Su, Jinzhao, et al.
Publicado: (2024)

LREA: Low-Rank Efficient Attention on Modeling Long-Term User Behaviors for CTR Prediction
por: Song, Xin, et al.
Publicado: (2025)

SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
por: Wang, Binhao, et al.
Publicado: (2025)

Boosting Data Utilization for Multilingual Dense Retrieval
por: Huang, Chao, et al.
Publicado: (2025)

Granite Embedding Multilingual R2 Models
por: Awasthy, Parul, et al.
Publicado: (2026)

Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillation
por: Choubey, Prafulla Kumar, et al.
Publicado: (2024)

Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation
por: Cheng, Kai, et al.
Publicado: (2026)

Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models
por: Wu, Jiongran, et al.
Publicado: (2025)