Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDistilling Linguistic Context for Language Model Compression
تقطير السياق اللغوي لضغط نموذج اللغة
238
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تكمن الشبكة العصبية الباهظة الثمنية والذاكرة الكثيفة وراء النجاح الأخير لتعلم تمثيل اللغة. نقل المعرفة، وهي تقنية رئيسية لنشر مثل هذا النموذج اللغوي الواسع في البيئات النادرة من الموارد، ينقل المعرفة المتعلقة بتمثيلات الكلمات الفردية المستفادة دون قيود. في هذه الورقة، مستوحاة من الملاحظات الأخيرة أن تمثيلات اللغة في وضع معرفة نسبيا ولديها معرفة أكثر دلالة ككل، نقدم هدف تقطير معارف جديد لتعلم تمثيل اللغة الذي ينقل المعرفة السياقية عبر نوعين من العلاقات عبر الإنترنت: علاقة كلمة وطبقة تحول العلاقة. على عكس تقنيات التقطير الأخيرة الأخرى لنماذج اللغة، فإن تقطيرنا السياقي ليس لديه أي قيود على التغييرات المعمارية بين المعلم والطالب. نحن نقوم بالتحقق من فعالية طريقتنا حول المعايير الصعبة لمهام فهم اللغة، ليس فقط في بنية الأحجام المختلفة ولكن أيضا بالاشتراك مع Dynabert، طريقة تشذيب الحجم التكيفي المقترح مؤخرا.
A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, transfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the contextual knowledge via two types of relationships across representations: Word Relation and Layer Transforming Relation. Unlike other recent distillation techniques for the language models, our contextual distillation does not have any restrictions on architectural changes between teacher and student. We validate the effectiveness of our method on challenging benchmarks of language understanding tasks, not only in architectures of various sizes but also in combination with DynaBERT, the recently proposed adaptive size pruning method.
References used
https://aclanthology.org/
rate research
Read More
In this study, we propose a self-supervised learning method that distils representations of word meaning in context from a pre-trained masked language model. Word representations are the basis for context-aware lexical semantics and unsupervised sema
ntic textual similarity (STS) estimation. A previous study transforms contextualised representations employing static word embeddings to weaken excessive effects of contextual information. In contrast, the proposed method derives representations of word meaning in context while preserving useful context information intact. Specifically, our method learns to combine outputs of different hidden layers using self-attention through self-supervised learning with an automatically generated training corpus. To evaluate the performance of the proposed approach, we performed comparative experiments using a range of benchmark tasks. The results confirm that our representations exhibited a competitive performance compared to that of the state-of-the-art method transforming contextualised representations for the context-aware lexical semantic tasks and outperformed it for STS estimation.
Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like news recom
mendation and retrieval. However, most existing PLMs are in huge size with hundreds of millions of parameters. Many online news applications need to serve millions of users with low latency tolerance, which poses great challenges to incorporating PLMs in these scenarios. Knowledge distillation techniques can compress a large PLM into a much smaller one and meanwhile keeps good performance. However, existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence. In this paper, we propose NewsBERT, which can distill PLMs for efficient and effective news intelligence. In our approach, we design a teacher-student joint learning and distillation framework to collaboratively learn both teacher and student models, where the student model can learn from the learning experience of the teacher model. In addition, we propose a momentum distillation method by incorporating the gradients of teacher model into the update of student model to better transfer the knowledge learned by the teacher model. Thorough experiments on two real-world datasets with three tasks show that NewsBERT can empower various intelligent news applications with much smaller models.
In Arabic Language, diacritics are used to specify meanings as well as pronunciations. However, diacritics are often omitted from written texts, which increases the number of possible meanings and pronunciations. This leads to an ambiguous text and m
akes the computational process on undiacritized text more difficult. In this paper, we propose a Linguistic Attentional Model for Arabic text Diacritization (LAMAD). In LAMAD, a new linguistic feature representation is presented, which utilizes both word and character contextual features. Then, a linguistic attention mechanism is proposed to capture the important linguistic features. In addition, we explore the impact of the linguistic features extracted from the text on Arabic text diacritization (ATD) by introducing them to the linguistic attention mechanism. The extensive experimental results on three datasets with different sizes illustrate that LAMAD outperforms the existing state-of-the-art models.
With the increasing use of machine-learning driven algorithmic judgements, it is critical to develop models that are robust to evolving or manipulated inputs. We propose an extensive analysis of model robustness against linguistic variation in the se
tting of deceptive news detection, an important task in the context of misinformation spread online. We consider two prediction tasks and compare three state-of-the-art embeddings to highlight consistent trends in model performance, high confidence misclassifications, and high impact failures. By measuring the effectiveness of adversarial defense strategies and evaluating model susceptibility to adversarial attacks using character- and word-perturbed text, we find that character or mixed ensemble models are the most effective defenses and that character perturbation-based attack tactics are more successful.
Empathy is the link between self and others. Detecting and understanding empathy is a key element for improving human-machine interaction. However, annotating data for detecting empathy at a large scale is a challenging task. This paper employs multi
-task training with knowledge distillation to incorporate knowledge from available resources (emotion and sentiment) to detect empathy from the natural language in different domains. This approach yields better results on an existing news-related empathy dataset compared to strong baselines. In addition, we build a new dataset for empathy prediction with fine-grained empathy direction, seeking or providing empathy, from Twitter. We release our dataset for research purposes.
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
