Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSelf-Training using Rules of Grammar for Few-Shot NLU
التدريب الذاتي باستخدام قواعد قواعد القواعد لعدد قليل من طلقة NLU
295
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نتعامل مع مشكلة شبكات التدريب الذاتي ل NLU في بيئة الموارد المنخفضة --- عدد قليل من البيانات المسمى والكثير من البيانات غير المسماة. إن فعالية التدريب الذاتي هي نتيجة لزيادة مقدار البيانات التدريبية أثناء التدريب. ومع ذلك، يصبح أقل فعالية في إعدادات الموارد المنخفضة بسبب الملصقات غير الموثوقة المتوقعة بواسطة نموذج المعلم على البيانات غير المسبقة. تم استخدام قواعد القواعد، التي تصف الهيكل النحوي للبيانات، في NLU للحصول على شرح أفضل. نقترح استخدام قواعد القواعد في التدريب الذاتي كآلية وضع العلامات الزائفة أكثر موثوقية، خاصة عندما يكون هناك عدد قليل من البيانات المسمى. نقوم بتصميم خوارزمية فعالة تقوم ببناء وتوسيع قواعد قواعد اللغة دون تورط بشري. ثم ندمج القواعد المبنية كآلية وضع العلامات الزائفة في التدريب الذاتي. هناك سيناريوهات محتملة فيما يتعلق بتوزيع البيانات: غير معروف أو معروف في التدريب قبل التدريب. إننا نوضح تجريبيا أن نهجنا يتفوق بشكل كبير على الأساليب الحديثة في ثلاث مجموعات بيانات معيار لكل من السيناريوهات.
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.
References used
https://aclanthology.org/
rate research
Read More
Meta-learning has recently been proposed to learn models and algorithms that can generalize from a handful of examples. However, applications to structured prediction and textual tasks pose challenges for meta-learning algorithms. In this paper, we a
pply two meta-learning algorithms, Prototypical Networks and Reptile, to few-shot Named Entity Recognition (NER), including a method for incorporating language model pre-training and Conditional Random Fields (CRF). We propose a task generation scheme for converting classical NER datasets into the few-shot setting, for both training and evaluation. Using three public datasets, we show these meta-learning algorithms outperform a reasonable fine-tuned BERT baseline. In addition, we propose a novel combination of Prototypical Networks and Reptile.
This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and effic
ient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model -- IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT.
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.
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, wh
ich 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.
We introduce a method for generating error-correction rules for grammar pattern errors in a given annotated learner corpus. In our approach, annotated edits in the learner corpus are converted into edit rules for correcting common writing errors. The
method involves automatic extraction of grammar patterns, and automatic alignment of the erroneous patterns and correct patterns. At run-time, grammar patterns are extracted from the grammatically correct sentences, and correction rules are retrieved by aligning the extracted grammar patterns with the erroneous patterns. Using the proposed method, we generate 1,499 high-quality correction rules related to 232 headwords. The method can be used to assist ESL students in avoiding grammatical errors, and aid teachers in correcting students' essays. Additionally, the method can be used in the compilation of collocation error dictionaries and the construction of grammar error correction systems.
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
