Related papers: An Automatic and Efficient BERT Pruning for Edge A…
Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both…
We propose BERMo, an architectural modification to BERT, which makes predictions based on a hierarchy of surface, syntactic and semantic language features. We use linear combination scheme proposed in Embeddings from Language Models (ELMo)…
Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of…
Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural…
We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and…
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…
Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve…
Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even…
Dynamic early exiting has been proven to improve the inference speed of the pre-trained language model like BERT. However, all samples must go through all consecutive layers before early exiting and more complex samples usually go through…
Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…
We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…
Transformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks.However, these models are both computation and memory expensive, hindering their deployment to…
Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various…
Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach…
Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This…
Machine question answering is an essential yet challenging task in natural language processing. Recently, Pre-trained Contextual Embeddings (PCE) models like Bidirectional Encoder Representations from Transformers (BERT) and A Lite BERT…
Ad relevance modeling plays a critical role in online advertising systems including Microsoft Bing. To leverage powerful transformers like BERT in this low-latency setting, many existing approaches perform ad-side computations offline.…
The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…
Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…
Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…