اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMarginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation
88
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teachers soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of BERT is conducive to the students performance. To better exploit the hidden knowledge, a common practice is to force the student to deeply mimic the teachers hidden states of all the tokens in a layer-wise manner. In this paper, however, we observe that although distilling the teachers hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled. To understand this effect, we conduct a series of analysis. Specifically, we divide the HSK of BERT into three dimensions, namely depth, length and width. We first investigate a variety of strategies to extract crucial knowledge for each single dimension and then jointly compress the three dimensions. In this way, we show that 1) the students performance can be improved by extracting and distilling the crucial HSK, and 2) using a tiny fraction of HSK can achieve the same performance as extensive HSK distillation. Based on the second finding, we further propose an efficient KD paradigm to compress BERT, which does not require loading the teacher during the training of student. For two kinds of student models and computing devices, the proposed KD paradigm gives rise to training speedup of 2.7x ~ 3.4x.
قيم البحث
اقرأ أيضاً
Despite pre-trained language models such as BERT have achieved appealing performance in a wide range of natural language processing tasks, they are computationally expensive to be deployed in real-time applications. A typical method is to adopt knowl
edge distillation to compress these large pre-trained models (teacher models) to small student models. However, for a target domain with scarce training data, the teacher can hardly pass useful knowledge to the student, which yields performance degradation for the student models. To tackle this problem, we propose a method to learn to augment for data-scarce domain BERT knowledge distillation, by learning a cross-domain manipulation scheme that automatically augments the target with the help of resource-rich source domains. Specifically, the proposed method generates samples acquired from a stationary distribution near the target data and adopts a reinforced selector to automatically refine the augmentation strategy according to the performance of the student. Extensive experiments demonstrate that the proposed method significantly outperforms state-of-the-art baselines on four different tasks, and for the data-scarce domains, the compressed student models even perform better than the original large teacher model, with much fewer parameters (only ${sim}13.3%$) when only a few labeled examples available.
End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent from speech
without using an intermediate ASR module. However, such end-to-end framework suffers from the unavailability of large speech resources with higher acoustic variation in spoken language understanding. In this work, we exploit the scope of the transformer distillation method that is specifically designed for knowledge distillation from a transformer based language model to a transformer based speech model. In this regard, we leverage the reliable and widely used bidirectional encoder representations from transformers (BERT) model as a language model and transfer the knowledge to build an acoustic model for intent classification using the speech. In particular, a multilevel transformer based teacher-student model is designed, and knowledge distillation is performed across attention and hidden sub-layers of different transformer layers of the student and teacher models. We achieve an intent classification accuracy of 99.10% and 88.79% for Fluent speech corpus and ATIS database, respectively. Further, the proposed method demonstrates better performance and robustness in acoustically degraded condition compared to the baseline method.
Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive during infe
rence. As a result, it is difficult to deploy them on resource-restricted devices. To improve the inference performance, as well as reduce the model size while maintaining the model accuracy, we propose a novel quantization method named KDLSQ-BERT that combines knowledge distillation (KD) with learned step size quantization (LSQ) for language model quantization. The main idea of our method is that the KD technique is leveraged to transfer the knowledge from a teacher model to a student model when exploiting LSQ to quantize that student model during the quantization training process. Extensive experiment results on GLUE benchmark and SQuAD demonstrate that our proposed KDLSQ-BERT not only performs effectively when doing different bit (e.g. 2-bit $sim$ 8-bit) quantization, but also outperforms the existing BERT quantization methods, and even achieves comparable performance as the full-precision base-line model while obtaining 14.9x compression ratio. Our code will be public available.
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness. In this work, we propose to use pre-trained language models for knowledge graph completion. We treat triples in knowledge graphs as
textual sequences and propose a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples. Our method takes entity and relation descriptions of a triple as input and computes scoring function of the triple with the KG-BERT language model. Experimental results on multiple benchmark knowledge graphs show that our method can achieve state-of-the-art performance in triple classification, link prediction and relation prediction tasks.
Significant memory and computational requirements of large deep neural networks restrict their application on edge devices. Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the knowledge of a tr
ained large teacher model is transferred to a smaller student model. The success of knowledge distillation is mainly attributed to its training objective function, which exploits the soft-target information (also known as dark knowledge) besides the given regular hard labels in a training set. However, it is shown in the literature that the larger the gap between the teacher and the student networks, the more difficult is their training using knowledge distillation. To address this shortcoming, we propose an improved knowledge distillation method (called Annealing-KD) by feeding the rich information provided by the teachers soft-targets incrementally and more efficiently. Our Annealing-KD technique is based on a gradual transition over annealed soft-targets generated by the teacher at different temperatures in an iterative process, and therefore, the student is trained to follow the annealed teacher output in a step-by-step manner. This paper includes theoretical and empirical evidence as well as practical experiments to support the effectiveness of our Annealing-KD method. We did a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and 100) and NLP language inference with BERT-based models on the GLUE benchmark and consistently got superior results.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
