Lamba, a novel adaptation of the Mamba State Space Model for semantic retrieval in Latin texts, is presented, highlighting Mamba’s potential for advancing semantic tools in Digital Humanities and open perspectives for extending the methodology to other historical languages.
MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish, is presented, providing both a foundation for Yiddish NLP and a practical template for language model development in historically rich but digitally underrepresented languages.
Uri Katz, Omer Goldman, Tomasz Limisiewicz et al.· 0 citations
This paper proposes a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol for MNMT models, and reduces the vocabulary size from over 128,000 to approximately 10,000 tokens, enabling a 60% memory saving without any loss in performance.
Introduction Abstractive text summarization remains a fundamental challenge in Natural Language Processing (NLP), particularly for long documents that require models to preserve long-range dependencies and maintain semantic coherence. Although Transformer-based architectures have achieved strong summarization performan...
K. Katti, K. Katti, Amanul Islam· Frontiers in Artificial Inte...· 0 citations
Pretrained language models (PLMs) have established state-of-the-art performance across diverse natural language understanding (NLU) tasks. This study reveals that seman-tic-rich explanations of lexical units can effectively guide PLM learning processes. We propose a novel language understanding enhancement method with...
Tianyi Chen, Yashen Wang, Huan Chang et al.· IEEE/CAA Journal of Automati...· 0 citations
The given paper introduces a very effective Bidirectional Encoder design using the monolingual model named “Bidirectional Encoder Representation from Transformers for Uzbek language” and optimized to provide scalable semantic search.
B. Muminov, N. Allaberganova, Olimjon Mamadiyorov et al.· International Conference on...· 0 citations
AssistEM, a framework for efficient LLM adaptation to EM via principled data selection, demonstrates that selective fine-tuning not only accelerates adaptation but also improves training efficiency (requiring fewer GPU hours), enabling open-source LLMs to rival–and in some cases outperform–closed-source models.
John Bosco Mugeni, Steven J. Lynden, Toshiyuki Amagasa et al.· International Journal of Dat...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
