Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
إطار تعليمي ثلاث مراحل لتوليد الحوار المعرفي المنخفض
243
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أظهرت نماذج المحادثة العصبية إمكانات كبيرة تجاه توليد ردود بطلاقة وإمعلومات عن طريق إدخال معرفة خلفية خارجية. ومع ذلك، فمن الشائع بناء هذه الحوارات المدرجة في المعرفة، وعادة ما تؤدي النماذج الحالية بشكل سيء عند النقل إلى مجالات جديدة مع عينات تدريب محدودة. لذلك، فإن بناء نظام حوار مدرج في المعرفة بموجب إعداد الموارد المنخفضة هو قضية حاسمة لا تزال. في هذه الورقة، نقترح إطارا لتعليم تعليمي رواية ثلاث مراحل يستند إلى التعلم الإشرافه ضعيف يفيد من الحوارات على نطاق واسع وقاعدة المعرفة غير المنظمة. للتعاون بشكل أفضل مع هذا الإطار، نضع متغير من المحولات مع فك فك التشفير التي تسهل التعلم المنطلق لتوليد الاستجابة وإدماج المعرفة. تشير نتائج التقييم إلى معيارين إلى أن نهجنا يمكن أن يتفوق على أساليب حديثة أخرى مع بيانات تدريب أقل، وحتى في سيناريو الموارد الصفرية، فإن نهجنا لا يزال ينفذ جيدا.
Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.
References used
https://aclanthology.org/
rate research
Read More
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.
Knowledge-grounded dialogue generation has achieved promising performance with the engagement of external knowledge sources. Typical approaches towards this task usually perform relatively independent two sub-tasks, i.e., knowledge selection and know
ledge-aware response generation. In this paper, in order to improve the diversity of both knowledge selection and knowledge-aware response generation, we propose a collaborative latent variable (CoLV) model to integrate these two aspects simultaneously in separate yet collaborative latent spaces, so as to capture the inherent correlation between knowledge selection and response generation. During generation, our proposed model firstly draws knowledge candidate from the latent space conditioned on the dialogue context, and then samples a response from another collaborative latent space conditioned on both the context and the selected knowledge. Experimental results on two widely-used knowledge-grounded dialogue datasets show that our model outperforms previous methods on both knowledge selection and response generation.
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning algorithms,
may not generalize well to testing tasks when they are not well-supported by training tasks. This paper studies a low-resource text classification problem and bridges the gap between meta-training and meta-testing tasks by leveraging the external knowledge bases. Specifically, we propose KGML to introduce additional representation for each sentence learned from the extracted sentence-specific knowledge graph. The extensive experiments on three datasets demonstrate the effectiveness of KGML under both supervised adaptation and unsupervised adaptation settings.
In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which
makes the performance significantly degraded. Moreover, many existing secure FL designs work only under the restrictive assumption that none of the clients can be dropped out from the training protocol. To tackle these problems, we propose SEFL, a secure and efficient federated learning framework that (1) eliminates the need for the trusted entities; (2) achieves similar and even better model accuracy compared with existing FL designs; (3) is resilient to client dropouts.
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage
both labeled dialogue and text data. The 3 tasks jointly optimize the same pre-trained Transformer -- conditioned dialogue generation task on the labeled dialogue data, conditioned language encoding task and conditioned language generation task on the labeled text data. Experimental results show that our approach outperforms the state-of-the-art models by leveraging the labeled texts, and it also obtains larger improvement in performance comparing to the previous methods to leverage text data.
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
