Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning
Gaml-Bert: تحسين بيرت المبكر الخروج من التدرج التعلم المتبادل
342
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نقترح إطارا جديدا، برت التعلم المتبادل المتماثل التدرج (Gaml-Bert)، لتحسين الخروج المبكر من Bert.مساهمات Gaml-Bert هي طي ثنائي.نقوم بإجراء مجموعة من التجارب الطيارية، والتي توضح أن تقطير المعرفة المتبادلة بين الخروج الضحل والخروج العميق يؤدي إلى أداء أفضل لكليهما.من هذه الملاحظة، نستخدم التعلم المتبادل لتحسين عروض بيرت المبكرة المبكرة، أي نطلب من كل خروج من بيرت متعددة الخروج لتقطير المعرفة من بعضها البعض.ثانيا، نقترح GA، طريقة تدريب جديدة تقوم بمحاذاة التدرجات من تقطير المعرفة إلى خسائر الانتروبية.يتم إجراء تجارب واسعة النطاق على معيار الغراء، والذي يدل على أن لدينا Gaml-Bert يمكن أن تتفوق بشكل كبير على أحدث الطرق التي تخرج من أحدث الطرق (SOTA) في وقت مبكر.
In this work, we propose a novel framework, Gradient Aligned Mutual Learning BERT (GAML-BERT), for improving the early exiting of BERT. GAML-BERT's contributions are two-fold. We conduct a set of pilot experiments, which shows that mutual knowledge distillation between a shallow exit and a deep exit leads to better performances for both. From this observation, we use mutual learning to improve BERT's early exiting performances, that is, we ask each exit of a multi-exit BERT to distill knowledge from each other. Second, we propose GA, a novel training method that aligns the gradients from knowledge distillation to cross-entropy losses. Extensive experiments are conducted on the GLUE benchmark, which shows that our GAML-BERT can significantly outperform the state-of-the-art (SOTA) BERT early exiting methods.
References used
https://aclanthology.org/
rate research
Read More
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 to acceler
ate PLMs' inference, named TR-BERT, which could flexibly adapt the layer number of each token in inference to avoid redundant calculation. Specially, TR-BERT formulates the token reduction process as a multi-step token selection problem and automatically learns the selection strategy via reinforcement learning. The experimental results on several downstream NLP tasks show that TR-BERT is able to speed up BERT by 2-5 times to satisfy various performance demands. Moreover, TR-BERT can also achieve better performance with less computation in a suite of long-text tasks since its token-level layer number adaption greatly accelerates the self-attention operation in PLMs. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/TR-BERT.
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-tra
ined acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text. Specifically, we unify a pre-trained acoustic model (wav2vec 2.0) and a language model (BERT) into an end-to-end trainable framework. A Representation Aggregation Module is designed to aggregate acoustic and linguistic representation, and an Embedding Attention Module is introduced to incorporate acoustic information into BERT, which can effectively facilitate the cooperation of two pre-trained models and thus boost the representation learning. Extensive experiments show that our Wav-BERT significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.
A currently popular research area in end-to-end speech translation is the use of knowledge distillation from a machine translation (MT) task to improve the speech translation (ST) task. However, such scenario obviously only allows one way transfer, w
hich is limited by the performance of the teacher model. Therefore, We hypothesis that the knowledge distillation-based approaches are sub-optimal. In this paper, we propose an alternative--a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student. This allows us to improve the performance of end-to-end ST more effectively than with a teacher-student paradigm. As a side benefit, performance of the MT model also improves. Experimental results show that in our mutual-learning scenario, models can effectively utilise the auxiliary information from peer models and achieve compelling results on Must-C dataset.
Fine-tuning pre-trained language models suchas BERT has become a common practice dom-inating leaderboards across various NLP tasks.Despite its recent success and wide adoption,this process is unstable when there are onlya small number of training sam
ples available.The brittleness of this process is often reflectedby the sensitivity to random seeds. In this pa-per, we propose to tackle this problem basedon the noise stability property of deep nets,which is investigated in recent literature (Aroraet al., 2018; Sanyal et al., 2020). Specifically,we introduce a novel and effective regulariza-tion method to improve fine-tuning on NLPtasks, referred to asLayer-wiseNoiseStabilityRegularization (LNSR). We extend the theo-ries about adding noise to the input and provethat our method gives a stabler regularizationeffect. We provide supportive evidence by ex-perimentally confirming that well-performingmodels show a low sensitivity to noise andfine-tuning with LNSR exhibits clearly bet-ter generalizability and stability. Furthermore,our method also demonstrates advantages overother state-of-the-art algorithms including L2-SP (Li et al., 2018), Mixout (Lee et al., 2020)and SMART (Jiang et al., 20)
Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem
, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
