Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models
طريقة خروج مبكرة في المستقبل العالمية في المستقبل لتسريع استنتاج النماذج المدربة مسبقا مسبقا
308
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف آلية الخروج المبكر إلى تسريع سرعة الاستدلال من نماذج اللغة المدربة مسبقا على نطاق واسع. الفكرة الأساسية هي الخروج مبكرا دون المرور من خلال كل طبقات الاستدلال في مرحلة الاستدلال. لإجراء تنبؤات دقيقة لمهام المصب، ينبغي النظر في المعلومات اللغوية الهرمية المدمجة في جميع الطبقات بشكل مشترك. ومع ذلك، فقد تقتصر الكثير من الأبحاث الآن على استخدام التمثيلات المحلية لطبقة الخروج. هذا العلاج يفقد حتما معلومات عن الطبقات السابقة غير المستخدمة وكذلك الميزات الرفيعة المستوى المضمنة في الطبقات المستقبلية، مما يؤدي إلى الأداء دون الأمثل. لمعالجة هذه المشكلة، نقترح طريقة مستقبلية جديدة جديدة لإجراء تنبؤات شاملة من منظور عالمي. نأخذ أولا في الاعتبار جميع المعلومات اللغوية المضمنة في الطبقات السابقة، ثم اتخذ خطوة أخرى لإشراك المعلومات المستقبلية التي لا يمكن الوصول إليها في الأصل للتنبؤات. توضح تجارب واسعة أن أسلوبنا تتفوق على أساليب الخروج المبكر السابقة من هامش كبير، مما يؤدي إلى أداء أفضل وقوي.
Early exit mechanism aims to accelerate the inference speed of large-scale pre-trained language models. The essential idea is to exit early without passing through all the inference layers at the inference stage. To make accurate predictions for downstream tasks, the hierarchical linguistic information embedded in all layers should be jointly considered. However, much of the research up to now has been limited to use local representations of the exit layer. Such treatment inevitably loses information of the unused past layers as well as the high-level features embedded in future layers, leading to sub-optimal performance. To address this issue, we propose a novel Past-Future method to make comprehensive predictions from a global perspective. We first take into consideration all the linguistic information embedded in the past layers and then take a further step to engage the future information which is originally inaccessible for predictions. Extensive experiments demonstrate that our method outperforms previous early exit methods by a large margin, yielding better and robust performance.
References used
https://aclanthology.org/
rate research
Read More
Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words i
n pre-training could further improve the performance of PrLMs. However, given that span-level clues are introduced and fixed in pre-training, previous methods are time-consuming and lack of flexibility. To alleviate the inconvenience, this paper presents a novel span fine-tuning method for PrLMs, which facilitates the span setting to be adaptively determined by specific downstream tasks during the fine-tuning phase. In detail, any sentences processed by the PrLM will be segmented into multiple spans according to a pre-sampled dictionary. Then the segmentation information will be sent through a hierarchical CNN module together with the representation outputs of the PrLM and ultimately generate a span-enhanced representation. Experiments on GLUE benchmark show that the proposed span fine-tuning method significantly enhances the PrLM, and at the same time, offer more flexibility in an efficient way.
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However, directly c
onnecting BERT as an encoder and GPT as a decoder can be challenging in machine translation, for GPT-like models lack a cross-attention component that is needed in seq2seq decoders. In this paper, we propose Graformer to graft separately pre-trained (masked) language models for machine translation. With monolingual data for pre-training and parallel data for grafting training, we maximally take advantage of the usage of both types of data. Experiments on 60 directions show that our method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLEU in en2x directions comparing with the multilingual Transformer of the same size.
Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training. Recent works o
nly propose lightweight model updates as models may already possess useful knowledge from past experience, but a challenge remains in understanding what parts and to what extent models should be refined for a given task. In this paper, we investigate what models learn from commonsense reasoning datasets. We measure the impact of three different adaptation methods on the generalization and accuracy of models. Our experiments with two models show that fine-tuning performs best, by learning both the content and the structure of the task, but suffers from overfitting and limited generalization to novel answers. We observe that alternative adaptation methods like prefix-tuning have comparable accuracy, but generalize better to unseen answers and are more robust to adversarial splits.
We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform
style transfer. We use a well-performing paraphraser guided by style-trained language models to keep the text content and remove toxicity. Our second method uses BERT to replace toxic words with their non-offensive synonyms. We make the method more flexible by enabling BERT to replace mask tokens with a variable number of words. Finally, we present the first large-scale comparative study of style transfer models on the task of toxicity removal. We compare our models with a number of methods for style transfer. The models are evaluated in a reference-free way using a combination of unsupervised style transfer metrics. Both methods we suggest yield new SOTA results.
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cro
ss-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-trained model in a sentence retrieval task. Our methods also achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
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
