BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT (original) (raw)

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

In the natural language processing literature, neural networks are becoming increasingly deeper and complex. The recent poster child of this trend is the deep language representation model, which includes BERT, ELMo, and GPT. These developments have led to the conviction that previous-generation, shallower neural networks for language understanding are obsolete. In this paper, however, we demonstrate that rudimentary, lightweight neural networks can still be made competitive without architecture changes, external training data, or additional input features. We propose to distill knowledge from BERT, a state-of-the-art language representation model, into a single-layer BiLSTM, as well as its siamese counterpart for sentence-pair tasks. Across multiple datasets in paraphrasing, natural language inference, and sentiment classification, we achieve comparable results with ELMo, while using roughly 100 times fewer parameters and 15 times less inference time.

A Primer in BERTology: What We Know About How BERT Works

Transactions of the Association for Computational Linguistics, 2020

Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue, and approaches to compression. We then outline directions for future research.

Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet

2020

One of the challenges in the NLP field is training large classification models, a task that is both difficult and tedious. It is even harder when GPU hardware is unavailable. The increased availability of pre-trained and off-the-shelf word embeddings, models, and modules aim at easing the process of training large models and achieving a competitive performance. We explore the use of off-the-shelf BERT models and share the results of our experiments and compare their results to those of LSTM networks and more simple baselines. We show that the complexity and computational cost of BERT is not a guarantee for enhanced predic-tive performance in the classification tasks at hand.

Augmenting BERT Carefully with Underrepresented Linguistic Features

arXiv (Cornell University), 2020

Fine-tuned Bidirectional Encoder Representations from Transformers (BERT)-based sequence classification models have proven to be effective for detecting Alzheimer's Disease (AD) from transcripts of human speech. However, previous research shows it is possible to improve BERT's performance on various tasks by augmenting the model with additional information. In this work, we use probing tasks as introspection techniques to identify linguistic information not wellrepresented in various layers of BERT, but important for the AD detection task. We supplement these linguistic features in which representations from BERT are found to be insufficient with hand-crafted features externally, and show that jointly fine-tuning BERT in combination with these features improves the performance of AD classification by upto 5% over fine-tuned BERT alone.

TiltedBERT: Resource Adjustable Version of BERT

2022

In this paper, we proposed a novel adjustable fine-tuning method that improves the training and inference time of the BERT model on downstream tasks. In the proposed method, we first detect more important word vectors in each layer by our proposed redundancy metric and then eliminate the less important word vectors with our proposed strategy. In our method, the word vector elimination rate in each layer is controlled by the Tilt-Rate hyper-parameter, and the model learns to work with a considerably lower number of Floating Point Operations (FLOPs) than the original BERT\textsubscript{base} model. Our proposed method does not need any extra training steps, and also it can be generalized to other transformer-based models. We perform extensive experiments that show the word vectors in higher layers have an impressive amount of redundancy that can be eliminated and decrease the training and inference time. Experimental results on extensive sentiment analysis, classification and regressi...

ConvBERT: Improving BERT with Span-based Dynamic Convolution

2020

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and thus suffers large memory footprint and computation cost. Although all its attention heads query on the whole input sequence for generating the attention map from a global perspective, we observe some heads only need to learn local dependencies, which means the existence of computation redundancy. We therefore propose a novel span-based dynamic convolution to replace these self-attention heads to directly model local dependencies. The novel convolution heads, together with the rest self-attention heads, form a new mixed attention block that is more efficient at both global and local context learning. We equip BERT with this mixed attention design and build a ConvBERT model. Experiments have shown that ConvBERT significantly outperforms BERT and its variants in various ...

The Universe of Utterances According to BERT

ICWS, 2023

It has been argued that BERT "rediscovers the traditional NLP pipeline", with lower layers extracting morphosyntactic features and higher layers creating holistic sentence-level representations. In this paper, we critically examine this assumption through a principle-componentguided analysis, extracing sets of inputs that correspond to specific activation patterns in BERT sentence representations. We find that even in higher layers, the model mostly picks up on a variegated bunch of low-level features, many related to sentence complexity, that presumably arise from its specific pre-training objectives.

SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions

ArXiv, 2021

Task-agnostic pre-training followed by taskspecific fine-tuning is a default approach to train NLU models. Such models need to be deployed on devices across the cloud and the edge with varying resource and accuracy constraints. For a given task, repeating pre-training and fine-tuning across tens of devices is prohibitively expensive. We propose SuperShaper, a task agnostic pretraining approach which simultaneously pretrains a large number of Transformer models by varying shapes, i.e., by varying the hidden dimensions across layers. This is enabled by a backbone network with linear bottleneck matrices around each Transformer layer which are sliced to generate differently shaped sub-networks. In spite of its simple design space and efficient implementation, SuperShaper discovers networks that effectively trade-off accuracy and model size: Discovered networks are more accurate than a range of hand-crafted and automatically searched networks on GLUE benchmarks. Further, we find two crit...

Exploring the Role of Transformers in NLP: From BERT to GPT-3

IRJET, 2023

The paper "Exploring the Role of Transformers in NLP: From BERT to GPT-3" provides an overview of the role of Transformers in NLP, with a focus on BERT and GPT-3. It covers topics such as the Role of Transformers in BERT, Transformer Encoder Architecture BERT, and Role of Transformers in GPT-3, Transformers in GPT-3 Architecture, Limitations of Transformers, Transformer Neural Network Design, and Pre-Training Process. The paper also discusses attention visualization and future directions for research, including developing more efficient models and integrating external knowledge sources. It is a valuable resource for researchers and practitioners in NLP, particularly the attention visualization section

ThisIsCompetition at SemEval-2019 Task 9: BERT is unstable for out-of-domain samples

Proceedings of the 13th International Workshop on Semantic Evaluation

This paper describes our system, Joint Encoders for Stable Suggestion Inference (JESSI), for the SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. JESSI is a combination of two sentence encoders: (a) one using multiple pre-trained word embeddings learned from log-bilinear regression (GloVe) and translation (CoVe) models, and (b) one on top of word encodings from a pre-trained deep bidirectional transformer (BERT). We include a domain adversarial training module when training for outof-domain samples. Our experiments show that while BERT performs exceptionally well for in-domain samples, several runs of the model show that it is unstable for out-ofdomain samples. The problem is mitigated tremendously by (1) combining BERT with a non-BERT encoder, and (2) using an RNNbased classifier on top of BERT. Our final models obtained second place with 77.78% F-Score on Subtask A (i.e. in-domain) and achieved an F-Score of 79.59% on Subtask B (i.e. out-of-domain), even without using any additional external data.