Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTR-BERT: Dynamic Token Reduction for Accelerating BERT Inference
TR-BERT: تخفيض الرمز المميز الديناميكي لتسريع بيرت بيرت
208
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما تكون نماذج اللغة المدربة مسبقا مسبقا (PLMS) باهظة الثمن بشكل أساسي في الاستدلال، مما يجعلها غير عملية في مختلف تطبيقات العالم الحقيقي المحدودة. لمعالجة هذه المشكلة، نقترح مقاربة تخفيض رمزية ديناميكية لتسريع استنتاج PLMS، والتي تسمى Tr-Bert، والتي يمكن أن تتكيف مرونة عدد الطبقة من كل رمزي في الاستدلال لتجنب الحساب الزائد. خصيصا، تقوم Tr-Bert بتصوير عملية تخفيض الرمز المميز كأداة اختيار رمز تخطيط متعدد الخطوات وتعلم تلقائيا استراتيجية الاختيار عبر التعلم التعزيز. تظهر النتائج التجريبية على العديد من مهام NLP المصب أن Tr-Bert قادرة على تسريع بيرتف بمقدار 2-5 مرات لإرضاء متطلبات الأداء المختلفة. علاوة على ذلك، يمكن ل TR-Bert تحقيق أداء أفضل مع حساب أقل في مجموعة من المهام النصية الطويلة لأن تكييف رقم الطبقة على مستوى الرمز المميز يسرع بشكل كبير عملية انتباه الذات في plms. يمكن الحصول على شفرة المصدر وتفاصيل التجربة لهذه الورقة من https://github.com/thunlp/tr-bert.
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 accelerate 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.
References used
https://aclanthology.org/
rate research
Read More
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause excessive matchin
g noise and problems of frequent updates. In this paper, we propose DyLex, a plug-in lexicon incorporation approach for BERT based sequence labeling tasks. Instead of leveraging embeddings of words in the lexicon as in conventional methods, we adopt word-agnostic tag embeddings to avoid re-training the representation while updating the lexicon. Moreover, we employ an effective supervised lexical knowledge denoising method to smooth out matching noise. Finally, we introduce a col-wise attention based knowledge fusion mechanism to guarantee the pluggability of the proposed framework. Experiments on ten datasets of three tasks show that the proposed framework achieves new SOTA, even with very large scale lexicons.
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 d
istillation 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.
In previous work, it has been shown that BERT can adequately align cross-lingual sentences on the word level. Here we investigate whether BERT can also operate as a char-level aligner. The languages examined are English, Fake English, German and Gree
k. We show that the closer two languages are, the better BERT can align them on the character level. BERT indeed works well in English to Fake English alignment, but this does not generalize to natural languages to the same extent. Nevertheless, the proximity of two languages does seem to be a factor. English is more related to German than to Greek and this is reflected in how well BERT aligns them; English to German is better than English to Greek. We examine multiple setups and show that the similarity matrices for natural languages show weaker relations the further apart two languages are.
Bidirectional Encoder Representations from Transformers (BERT) has achieved state-of-the-art performances on several text classification tasks, such as GLUE and sentiment analysis. Recent work in the legal domain started to use BERT on tasks, such as
legal judgement prediction and violation prediction. A common practise in using BERT is to fine-tune a pre-trained model on a target task and truncate the input texts to the size of the BERT input (e.g. at most 512 tokens). However, due to the unique characteristics of legal documents, it is not clear how to effectively adapt BERT in the legal domain. In this work, we investigate how to deal with long documents, and how is the importance of pre-training on documents from the same domain as the target task. We conduct experiments on the two recent datasets: ECHR Violation Dataset and the Overruling Task Dataset, which are multi-label and binary classification tasks, respectively. Importantly, on average the number of tokens in a document from the ECHR Violation Dataset is more than 1,600. While the documents in the Overruling Task Dataset are shorter (the maximum number of tokens is 204). We thoroughly compare several techniques for adapting BERT on long documents and compare different models pre-trained on the legal and other domains. Our experimental results show that we need to explicitly adapt BERT to handle long documents, as the truncation leads to less effective performance. We also found that pre-training on the documents that are similar to the target task would result in more effective performance on several scenario.
Choosing the most suitable classifier in a linguistic context is a well-known problem in the production of Mandarin and many other languages. The present paper proposes a solution based on BERT, compares this solution to previous neural and rule-base
d models, and argues that the BERT model performs particularly well on those difficult cases where the classifier adds information to the text.
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
