Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContinual Learning for Grounded Instruction Generation by Observing Human Following Behavior
التعلم المستمر لتوليد التعليم الأساسي من خلال مراقبة سلوك الإنسان بعد
250
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
مجردة نحن ندرس التعلم المستمر لتوليد تعليم اللغة الطبيعي، من خلال مراقبة تنفيذ تعليمات المستخدمين البشري.نحن نركز على سيناريو تعاوني، حيث يقوم النظام على كلا من كل من المهام التي يقوم بها المستخدمون البشريون الذين يستخدمون اللغة الطبيعية.نقارن تنفيذ المستخدم للحصول على التعليمات التي تم إنشاؤها إلى النظام الأصلي نية كإشارة إلى نجاح النظام في توصيل نيتها.نوضح كيفية استخدام هذه الإشارة لتحسين قدرة النظام على إنشاء تعليمات عبر تعلم الشرط السياقي.في التفاعل مع المستخدمين الحقيقيين، يوضح نظامنا تحسينات دراماتيكية في قدرتها على توليد اللغة بمرور الوقت.
Abstract We study continual learning for natural language instruction generation, by observing human users' instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural language. We compare user execution of generated instructions to the original system intent as an indication to the system's success communicating its intent. We show how to use this signal to improve the system's ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.
References used
https://aclanthology.org/
rate research
Read More
Neural machine translation (NMT) models are data-driven and require large-scale training corpus. In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
However, this bears the risk of catastrophic forgetting that the performance on the general domain is decreased drastically. In this work, we propose a new continual learning framework for NMT models. We consider a scenario where the training is comprised of multiple stages and propose a dynamic knowledge distillation technique to alleviate the problem of catastrophic forgetting systematically. We also find that the bias exists in the output linear projection when fine-tuning on the in-domain corpus, and propose a bias-correction module to eliminate the bias. We conduct experiments on three representative settings of NMT application. Experimental results show that the proposed method achieves superior performance compared to baseline models in all settings.
Continual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. In this paper, we propose a first-ever
continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in both modularized and end-to-end learning settings. In addition, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. We also suggest that the upper bound performance of continual learning should be equivalent to multitask learning when data from all domain is available at once. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform better, by a large margin, compared to other continuous learning techniques, and only slightly worse than the multitask learning upper bound while being 20X faster in learning new domains. We also report several trade-offs in terms of parameter usage, memory size and training time, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released to promote more research in this direction.
We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translation. Our approach is suitable f
or large-scale datasets, applies to distant languages with unseen scripts, incurs only minor degradation on the translation performance for the original language pairs and provides competitive performance even in the case where we only possess monolingual data for the new languages.
Curriculum learning, a machine training strategy that feeds training instances to the model from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile, knowledge distillation, a knowledge transformation methodology among
teachers and students networks can yield significant performance boost for student models. Hence, in this paper, we introduce a combination of curriculum learning and knowledge distillation for efficient dialogue generation models, where curriculum learning can help knowledge distillation from data and model aspects. To start with, from the data aspect, we cluster the training cases according to their complexity, which is calculated by various types of features such as sentence length and coherence between dialog pairs. Furthermore, we employ an adversarial training strategy to identify the complexity of cases from model level. The intuition is that, if a discriminator can tell the generated response is from the teacher or the student, then the case is difficult that the student model has not adapted to yet. Finally, we use self-paced learning, which is an extension to curriculum learning to assign weights for distillation. In conclusion, we arrange a hierarchical curriculum based on the above two aspects for the student model under the guidance from the teacher model. Experimental results demonstrate that our methods achieve improvements compared with competitive baselines.
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product. The DIL setting is particula
rly suited to ASC because in testing the system needs not know the task/domain to which the test data belongs. To our knowledge, this setting has not been studied before for ASC. This paper proposes a novel model called CLASSIC. The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing. Experimental results show the high effectiveness of CLASSIC.
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
