6 accepted papers
Training large AI models such as LLMs and DLRMs costs massive GPUs and computing time. The high training cost has become only affordable to big tech companies, meanwhile also causing increasing concerns about the environmental impact. This paper presents CoMERA, a **Co**mputing- and **M**emory-**E**…
This paper describes Distill-Quantize-Tune (DQT), a pipeline to create viable small-footprint multilingual models that can perform NLU on extremely resource-constrained Edge devices. We distill semantic knowledge from a large-sized teacher (transformer-based), that has been trained on huge amount of…
Transformer-based models demonstrate state of the art results on several natural language understanding tasks. However, their deployment comes at the cost of increased footprint and inference latency, limiting their adoption to real-time applications. Early exit strategies are designed to speed-up t…
End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we consider an E2E system as a mul…
In this paper, we propose and experiment with techniques for extreme compression of neural natural language understanding (NLU) models, making them suitable for execution on resource-constrained devices. We propose a task-aware, end-to-end compression approach that performs word-embedding compressio…
Grapheme-to-phoneme (G2P) models convert a written word into its corresponding pronunciation and are essential components in automatic-speech-recognition and text-to-speech systems. Recently, the use of neural encoder-decoder architectures has substantially improved G2P accuracy for mono- and multi-…