Related papers: D-Nikud: Enhancing Hebrew Diacritization with LSTM…
Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge distillation (and its…
Many automatic translation works have been addressed between major European language pairs, by taking advantage of large scale parallel corpora, but very few research works are conducted on the Amharic-Arabic language pair due to its…
As a fundamental problem, numerous methods are dedicated to the optimization of signal-to-interference-plus-noise ratio (SINR), in a multi-user setting. Although traditional model-based optimization methods achieve strong performance, the…
Image based Deep Feature Quality Metrics (DFQMs) have been shown to better correlate with subjective perceptual scores over traditional metrics. The fundamental focus of these DFQMs is to exploit internal representations from a large scale…
We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achieving high accuracy performance, calibration of these compact…
Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate…
We describe an Arabic-Hebrew parallel corpus of TED talks built upon WIT3, the Web inventory that repurposes the original content of the TED website in a way which is more convenient for MT researchers. The benchmark consists of about 2,000…
Spatiotemporal forecasting often relies on computationally intensive models to capture complex dynamics. Knowledge distillation (KD) has emerged as a key technique for creating lightweight student models, with recent advances like…
Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful…
Knowledge Distillation (KD) is a well-known training paradigm in deep neural networks where knowledge acquired by a large teacher model is transferred to a small student. KD has proven to be an effective technique to significantly improve…
Pretrained language models (LLMs) are often constrained by their fixed tokenization schemes, leading to inefficiencies and performance limitations, particularly for multilingual or specialized applications. This tokenizer lock-in presents…
Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…
Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for the 72 million hearing-impaired people…
We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND…
Many existing studies on knowledge distillation have focused on methods in which a student model mimics a teacher model well. Simply imitating the teacher's knowledge, however, is not sufficient for the student to surpass that of the…
We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…
Named Entity Recognition (NER) is a critical component of Natural Language Processing (NLP) for extracting structured information from unstructured text. However, for low-resource languages like Catalan, the performance of NER systems often…
In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output…
In this paper, we address the persistent challenges that figurative language expressions pose for natural language processing (NLP) systems, particularly in low-resource languages such as Konkani. We present a hybrid model that integrates a…
In this paper, we fill in an existing gap in resources available to the Hebrew NLP community by providing it with the largest so far pre-train dataset HeDC4, a state-of-the-art pre-trained language model HeRo for standard length inputs and…