Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSelf-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
التدريب الذاتي يحسن ما قبل التدريب لتعلم القليل من اللقطة في أنظمة الحوار الموجهة نحو المهام
284
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نظرا لأن تكلفة وضع العلامات للوحدات المختلفة في أنظمة الحوار الموجهة نحو المهام (TOD) باهظ الثمن، فإن التحدي الرئيسي هو تدريب وحدات مختلفة بأقل قدر من البيانات المسمى. أظهرت نماذج اللغة المدربة مسبقا مؤخرا، نتائج واعدة واعدة لعدد قليل من التعلم في TOD. في هذه الورقة، نرتند نهجا للتدريب الذاتي للاستفادة من بيانات الحوار غير المسبق الوفيرة لزيادة تحسين النماذج المدربة للدولة المدربة مسبقا في سيناريوهات تعليمية قليلة لأنظمة TOD. على وجه التحديد، نقترح نهجا للتدريب الذاتي أن تستلم البيانات الأكثر ثقة أكثر ثقة لتدريب نموذج طالب أقوى. علاوة على ذلك، يقترح تقنية تكبير نص جديد (GradaG) تدريب الطالب بشكل أفضل عن طريق استبدال الرموز غير الحاسمة باستخدام نموذج لغة ملثم. نقوم بإجراء تجارب مكثفة وتحليلات موجودة على أربع مهام المصب في TOD، بما في ذلك تصنيف النوايا وتتبع ولاية الحوار وتنبؤ قانون الحوار واختيار الاستجابة. توضح النتائج التجريبية أن نهج التدريب الذاتي المقترح باستمرار يحسن باستمرار النماذج المدربة مسبقا من أحدث (بيرت، TOD-BERT-BERT) عند توفر عدد صغير فقط من البيانات المسمى.
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 promising 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.
References used
https://aclanthology.org/
rate research
Read More
Neural approaches to natural language generation in task-oriented dialogue have typically required large amounts of annotated training data to achieve satisfactory performance, especially when generating from compositional inputs. To address this iss
ue, we show that self-training enhanced with constrained decoding yields large gains in data efficiency on a conversational weather dataset that employs compositional meaning representations. In particular, our experiments indicate that self-training with constrained decoding can enable sequence-to-sequence models to achieve satisfactory quality using vanilla decoding with five to ten times less data than with ordinary supervised baseline; moreover, by leveraging pretrained models, data efficiency can be increased further to fifty times. We confirm the main automatic results with human evaluations and show that they extend to an enhanced, compositional version of the E2E dataset. The end result is an approach that makes it possible to achieve acceptable performance on compositional NLG tasks using hundreds rather than tens of thousands of training samples.
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks' performances. However, in task-oriente
d dialog modeling, we observe that further pre-training MLM does not always boost the performance on a downstream task. We find that DAPT is beneficial in the low-resource setting, but as the fine-tuning data size grows, DAPT becomes less beneficial or even useless, and scaling the size of DAPT data does not help. Through Representational Similarity Analysis, we conclude that more data for fine-tuning yields greater change of the model's representations and thus reduces the influence of initialization.
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tun
ing. Specifically, we first conduct self-supervised contrastive pre-training on collected intent datasets, which implicitly learns to discriminate semantically similar utterances without using any labels. We then perform few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther. Experimental results show that our proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.
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.
The lack of labeled training data for new features is a common problem in rapidly changing real-world dialog systems. As a solution, we propose a multilingual paraphrase generation model that can be used to generate novel utterances for a target feat
ure and target language. The generated utterances can be used to augment existing training data to improve intent classification and slot labeling models. We evaluate the quality of generated utterances using intrinsic evaluation metrics and by conducting downstream evaluation experiments with English as the source language and nine different target languages. Our method shows promise across languages, even in a zero-shot setting where no seed data 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
