The past 3 years of work in NLP have been characterized by the development and deployment of ever larger language models, especially for English. BERT, its variants, GPT-2/3, and others, most recently Switch-C, have pushed the boundaries of the possible both through architectural innovations and through sheer size. Using these pretrained models and the methodology of fine-tuning them for specific tasks, researchers have extended the state of the art on a wide array of tasks as measured by leaderboards on specific benchmarks for English. In this paper, we take a step back and ask: How big is too big? What are the possible risks associated with this technology and what paths are available for mitigating those risks? We provide recommendations including weighing the environmental and financial costs first, investing resources into curating and carefully documenting datasets rather than ingesting everything on the web, carrying out pre-development exercises evaluating how the planned approach fits into research and development goals and supports stakeholder values, and encouraging research directions beyond ever larger language models.

https://dl.acm.org/doi/pdf/10.1145/3442188.3445922

On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? &#x1f99c;

Recently, the emergence of pre-trained models (PTMs) has brought natural language processing (NLP) to a new era. In this survey, we provide a comprehensive review of PTMs for NLP. We first briefly introduce language representation learning and its research progress. Then we systematically categorize existing PTMs based on a taxonomy from four different perspectives. Next, we describe how to adapt the knowledge of PTMs to downstream tasks. Finally, we outline some potential directions of PTMs for future research. This survey is purposed to be a hands-on guide for understanding, using, and developing PTMs for various NLP tasks.

Pre-trained Models for Natural Language Processing: A Survey

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resource-restricted devices. To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models. By leveraging this new KD method, the plenty of knowledge encoded in a large “teacher” BERT can be effectively transferred to a small “student” TinyBERT. Then, we introduce a new two-stage learning framework for TinyBERT, which performs Transformer distillation at both the pre-training and task-specific learning stages. This framework ensures that TinyBERT can capture the general-domain as well as the task-specific knowledge in BERT. TinyBERT4 with 4 layers is empirically effective and achieves more than 96.8% the performance of its teacher BERT-Base on GLUE benchmark, while being 7.5x smaller and 9.4x faster on inference. TinyBERT4 is also significantly better than 4-layer state-of-the-art baselines on BERT distillation, with only ~28% parameters and ~31% inference time of them. Moreover, TinyBERT6 with 6 layers performs on-par with its teacher BERT-Base.

/pdf/tinybert-distilling-bert-for-natural-language-understanding-3v1e6ykntv.pdf

TinyBERT: Distilling BERT for Natural Language Understanding

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resource-restricted devices. To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models. By leveraging this new KD method, the plenty of knowledge encoded in a large teacher BERT can be effectively transferred to a small student Tiny-BERT. Then, we introduce a new two-stage learning framework for TinyBERT, which performs Transformer distillation at both the pretraining and task-specific learning stages. This framework ensures that TinyBERT can capture he general-domain as well as the task-specific knowledge in BERT. 
TinyBERT with 4 layers is empirically effective and achieves more than 96.8% the performance of its teacher BERTBASE on GLUE benchmark, while being 7.5x smaller and 9.4x faster on inference. TinyBERT with 4 layers is also significantly better than 4-layer state-of-the-art baselines on BERT distillation, with only about 28% parameters and about 31% inference time of them. Moreover, TinyBERT with 6 layers performs on-par with its teacher BERTBASE.

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.

/pdf/a-primer-in-bertology-what-we-know-about-how-bert-works-2v8af1zw7o.pdf

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

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 larger and more accurate models such as GPT2 and Megatron, suggest a trend of large pre-trained Transformer models. However, using these large models in production environments is a complex task requiring a large amount of compute, memory and power resources. In this work we show how to perform quantization-aware training during the fine-tuning phase of BERT in order to compress BERT by $4\times$ with minimal accuracy loss. Furthermore, the produced quantized model can accelerate inference speed if it is optimized for 8bit Integer supporting hardware.

Q8BERT: Quantized 8Bit BERT

Recently, pre-trained Transformer [1] based language models such as BERT [2] and GPT [3], have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even larger and more accurate models such as GPT2 [4] and Megatron11https://github.com/NVIDIA/Megatron-LM, suggest a trend of large pre-trained Transformer models. However, using these large models in production environments is a complex task requiring a large amount of compute, memory and power resources. In this work we show how to perform quantization-aware training during the fine-tuning phase of BERT in order to compress BERT by 4x with minimal accuracy loss. Furthermore, the produced quantized model can accelerate inference speed if it is optimized for 8bit Integer supporting hardware.

The disclosed method and apparatus combine interactions and transactions in order to detect fraud acts or fraud attempts. In one embodiment, one or more interactions is correlated with one or more transactions, the interactions is and transactions features are combined, and features are extracted from the combined structure. The features are compared against one or more profiles, and a combined risk score is determined for the interactions or transactions. If the risk score exceeds a predetermined threshold, a preventive/corrective action can be taken. In another embodiment, behavioral characteristics extracted from one or more interactions associated with a transaction, with a risk score obtained by analyzing the transaction. The behavioral characteristic are used to enhance suspicion level related to a transaction being fraudulent, and to enable the taking of measures related to the transaction or to the person handling the transaction. The combination thus enables better assessment whether a particular interaction or transaction is fraudulent, and therefore provides for better detection or prevention of such activities. In addition, making the fraud assessment more reliable enables more efficient resource allocation of personnel for monitoring the transactions and interactions, better usage of communication time by avoiding lengthy identification where not required, and generally higher efficiency.

Apparatus and method for fraud prevention

Methods and apparatus for the enhancement of speech to text engines, by providing indications to the correctness of the found words, based on additional sources besides the internal indication provided by the STT engine. The enhanced indications comprise sources of data such as acoustic features, CTI features, phonetic search and others. The apparatus and methods also enable the detection of important or significant keywords found in audio files, thus enabling more efficient usages, such as further processing or transfer of interactions to relevant agents, escalation of issues, or the like. The methods and apparatus employ a training phase in which word model and key phrase model are generated for determining an enhanced correctness indication for a word and an enhanced importance indication for a key phrase, based on the additional features.

Methods and apparatus for enhancing speech analytics

Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high variability from manually crafted prompts, and typically require billion-parameter language models to achieve high accuracy. To address these shortcomings, we propose SetFit (Sentence Transformer Fine-tuning), an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers (ST). SetFit works by first fine-tuning a pretrained ST on a small number of text pairs, in a contrastive Siamese manner. The resulting model is then used to generate rich text embeddings, which are used to train a classification head. This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques. Our experiments show that SetFit obtains comparable results with PEFT and PET techniques, while being an order of magnitude faster to train. We also show that SetFit can be applied in multilingual settings by simply switching the ST body. Our code is available at https://github.com/huggingface/setfit and our datasets at https://huggingface.co/setfit .

Moshe Wasserblat

Papers

Q8BERT: Quantized 8Bit BERT

Q8BERT: Quantized 8Bit BERT

Apparatus and method for fraud prevention

Methods and apparatus for enhancing speech analytics

Efficient Few-Shot Learning Without Prompts