Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHow to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
كيفية اختيار واحد بين الكل؟دراسة تجريبية نحو تقلير تقارير المعرفة في فهم اللغة الطبيعية
184
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تقطير المعرفة (KD) هي خوارزمية ضغط نموذجية تساعد في نقل المعرفة في شبكة عصبية كبيرة في واحدة أصغر.على الرغم من أن KD قد أظهرت وعد على مجموعة واسعة من تطبيقات معالجة اللغة الطبيعية (NLP)، يفهم القليل حول كيفية مقارنة خوارزمية KD واحدة مع آخر وما إذا كانت هذه الأساليب يمكن أن تكون مجانية لبعضها البعض.في هذا العمل، نقوم بتقييم خوارزميات KD المختلفة على اختبار داخل المجال والخروج والمصدري.نقترح إطارا لتقييم متانة الخصومة لخوارزميات متعددة الدكتوراط.علاوة على ذلك، نقدم خوارزمية KD جديدة، مجتمعة د.ك، والتي تستفيد من نهجين واعدين (مخطط تدريب أفضل وزعم البيانات أكثر كفاءة).تظهر النتائج التجريبية الواسعة لدينا أن مجتمعة - KD تحقق نتائج أحدث النتائج على مرجع الغراء، وتعميم خارج المجال، ومتانة الخصومة مقارنة بالأساليب التنافسية.
Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge in a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications, little is understood about how one KD algorithm compares to another and whether these approaches can be complimentary to each other. In this work, we evaluate various KD algorithms on in-domain, out-of-domain and adversarial testing. We propose a framework to assess adversarial robustness of multiple KD algorithms. Moreover, we introduce a new KD algorithm, Combined-KD, which takes advantage of two promising approaches (better training scheme and more efficient data augmentation). Our extensive experimental results show that Combined-KD achieves state-of-the-art results on the GLUE benchmark, out-of-domain generalization, and adversarial robustness compared to competitive methods.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we propose a definition and taxonomy of various types of non-standard textual content -- generally referred to as noise'' -- in Natural Language Processing (NLP). While data pre-processing is undoubtedly important in NLP, especially wh
en dealing with user-generated content, a broader understanding of different sources of noise and how to deal with them is an aspect that has been largely neglected. We provide a comprehensive list of potential sources of noise, categorise and describe them, and show the impact of a subset of standard pre-processing strategies on different tasks. Our main goal is to raise awareness of non-standard content -- which should not always be considered as noise'' -- and of the need for careful, task-dependent pre-processing. This is an alternative to blanket, all-encompassing solutions generally applied by researchers through standard'' pre-processing pipelines. The intention is for this categorisation to serve as a point of reference to support NLP researchers in devising strategies to clean, normalise or embrace non-standard content.
Knowledge Distillation (KD) is extensively used to compress and deploy large pre-trained language models on edge devices for real-world applications. However, one neglected area of research is the impact of noisy (corrupted) labels on KD. We present,
to the best of our knowledge, the first study on KD with noisy labels in Natural Language Understanding (NLU). We document the scope of the problem and present two methods to mitigate the impact of label noise. Experiments on the GLUE benchmark show that our methods are effective even under high noise levels. Nevertheless, our results indicate that more research is necessary to cope with label noise under the KD.
Evaluation for many natural language understanding (NLU) tasks is broken: Unreliable and biased systems score so highly on standard benchmarks that there is little room for researchers who develop better systems to demonstrate their improvements. The
recent trend to abandon IID benchmarks in favor of adversarially-constructed, out-of-distribution test sets ensures that current models will perform poorly, but ultimately only obscures the abilities that we want our benchmarks to measure. In this position paper, we lay out four criteria that we argue NLU benchmarks should meet. We argue most current benchmarks fail at these criteria, and that adversarial data collection does not meaningfully address the causes of these failures. Instead, restoring a healthy evaluation ecosystem will require significant progress in the design of benchmark datasets, the reliability with which they are annotated, their size, and the ways they handle social bias.
Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchica
l/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge. In this tutorial we will present a roadmap to line up the state-of-the-art methods to tackle these challenges on this cutting-edge problem. We will dive deep into various technical components: how to represent knowledge, how to feed knowledge into a generation model, how to evaluate generation results, and what are the remaining challenges?
Existing pre-trained language models (PLMs) have demonstrated the effectiveness of self-supervised learning for a broad range of natural language processing (NLP) tasks. However, most of them are not explicitly aware of domain-specific knowledge, whi
ch is essential for downstream tasks in many domains, such as tasks in e-commerce scenarios. In this paper, we propose K-PLUG, a knowledge-injected pre-trained language model based on the encoder-decoder transformer that can be transferred to both natural language understanding and generation tasks. Specifically, we propose five knowledge-aware self-supervised pre-training objectives to formulate the learning of domain-specific knowledge, including e-commerce domain-specific knowledge-bases, aspects of product entities, categories of product entities, and unique selling propositions of product entities. We verify our method in a diverse range of e-commerce scenarios that require domain-specific knowledge, including product knowledge base completion, abstractive product summarization, and multi-turn dialogue. K-PLUG significantly outperforms baselines across the board, which demonstrates that the proposed method effectively learns a diverse set of domain-specific knowledge for both language understanding and generation tasks. Our code is available.
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
