Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSTraTA: Self-Training with Task Augmentation for Better Few-shot Learning
طبقات: التدريب الذاتي مع تكبير المهمة لتحسين التعلم قليلا
281
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من نجاحاتها الأخيرة في معالجة العديد من مهام NLP، لا تؤدي نماذج اللغة المدربة مسبقا على نطاق واسع وكذلك في إعدادات قليلة، حيث تتوفر حفنة من الأمثلة التدريبية فقط. لمعالجة هذا القصور، نقترح الطبقات، والتي تعني التدريب الذاتي مع تكبير المهمة، وهو نهج يبني على أفكارين رئيسيين للرافعة الفعالة من البيانات غير المسبقة. أولا، تستخدم Strata تكبير المهمة، وهي تقنية جديدة توليف كمية كبيرة من البيانات الخاصة بضبط المهمة المساعدة من النصوص المستهدفة من النصوص المستهدفة. ثانيا، تقوم الطبقات بإجراء تدريبات ذاتية من خلال زيادة ضبط النموذج القوي القوي الذي تم إنشاؤه بواسطة تكبير المهمة على توزيع واسع للبيانات المسمى الزائفة. توضح تجاربنا أن الطبقات يمكن أن تحسن بشكل كبير كفاءة عينة في 12 معيارا قليلة بالرصاص. بشكل ملحوظ، على DataSet SST-2 المعنويات، Strata، مع 8 أمثلة تدريبية فقط لكل فصل، تحقق نتائج قابلة للمقارنة للضبط بشكل جيد مع أمثلة تدريبية 67K. تكشف تحليلاتنا أن تكبير المهمة والتدريب الذاتي متكاملين وفعالا بشكل مستقل.
Despite their recent successes in tackling many NLP tasks, large-scale pre-trained language models do not perform as well in few-shot settings where only a handful of training examples are available. To address this shortcoming, we propose STraTA, which stands for Self-Training with Task Augmentation, an approach that builds on two key ideas for effective leverage of unlabeled data. First, STraTA uses task augmentation, a novel technique that synthesizes a large amount of data for auxiliary-task fine-tuning from target-task unlabeled texts. Second, STraTA performs self-training by further fine-tuning the strong base model created by task augmentation on a broad distribution of pseudo-labeled data. Our experiments demonstrate that STraTA can substantially improve sample efficiency across 12 few-shot benchmarks. Remarkably, on the SST-2 sentiment dataset, STraTA, with only 8 training examples per class, achieves comparable results to standard fine-tuning with 67K training examples. Our analyses reveal that task augmentation and self-training are both complementary and independently effective.
References used
https://aclanthology.org/
rate research
Read More
As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promis
ing results for few-shot learning in ToD. In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems. Specifically, we propose a self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model. Moreover, a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model. We conduct extensive experiments and present analyses on four downstream tasks in ToD, including intent classification, dialog state tracking, dialog act prediction, and response selection. Empirical results demonstrate that the proposed self-training approach consistently improves state-of-the-art pre-trained models (BERT, ToD-BERT) when only a small number of labeled data are available.
Natural Language Processing (NLP) is increasingly relying on general end-to-end systems that need to handle many different linguistic phenomena and nuances. For example, a Natural Language Inference (NLI) system has to recognize sentiment, handle num
bers, perform coreference, etc. Our solutions to complex problems are still far from perfect, so it is important to create systems that can learn to correct mistakes quickly, incrementally, and with little training data. In this work, we propose a continual few-shot learning (CFL) task, in which a system is challenged with a difficult phenomenon and asked to learn to correct mistakes with only a few (10 to 15) training examples. To this end, we first create benchmarks based on previously annotated data: two NLI (ANLI and SNLI) and one sentiment analysis (IMDB) datasets. Next, we present various baselines from diverse paradigms (e.g., memory-aware synapses and Prototypical networks) and compare them on few-shot learning and continual few-shot learning setups. Our contributions are in creating a benchmark suite and evaluation protocol for continual few-shot learning on the text classification tasks, and making several interesting observations on the behavior of similarity-based methods. We hope that our work serves as a useful starting point for future work on this important topic.
We tackle the problem of self-training networks for NLU in low-resource environment---few labeled data and lots of unlabeled data. The effectiveness of self-training is a result of increasing the amount of training data while training. Yet it becomes
less effective in low-resource settings due to unreliable labels predicted by the teacher model on unlabeled data. Rules of grammar, which describe the grammatical structure of data, have been used in NLU for better explainability. We propose to use rules of grammar in self-training as a more reliable pseudo-labeling mechanism, especially when there are few labeled data. We design an effective algorithm that constructs and expands rules of grammar without human involvement. Then we integrate the constructed rules as a pseudo-labeling mechanism into self-training. There are two possible scenarios regarding data distribution: it is unknown or known in prior to training. We empirically demonstrate that our approach substantially outperforms the state-of-the-art methods in three benchmark datasets for both scenarios.
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to a
utomatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource-rich conditions. However, evaluations using real-world lowresource languages still result in unsatisfactory performance. This work prop
oses a novel zeroshot NMT modeling approach that learns without the now-standard assumption of a pivot language sharing parallel data with the zero-shot source and target languages. Our approach is based on three stages: initialization from any pre-trained NMT model observing at least the target language, augmentation of source sides leveraging target monolingual data, and learning to optimize the initial model to the zero-shot pair, where the latter two constitute a selflearning cycle. Empirical findings involving four diverse (in terms of a language family, script and relatedness) zero-shot pairs show the effectiveness of our approach with up to +5.93 BLEU improvement against a supervised bilingual baseline. Compared to unsupervised NMT, consistent improvements are observed even in a domain-mismatch setting, attesting to the usability of our method.
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
