Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning

Abstract

In this paper, we propose a Meta Cooperative Learning (MCL) framework for task-oriented dialog systems (TDSs). Our model consists of an auxiliary KB reasoning task for learning meta KB knowledge, an auxiliary dialogue reasoning task for learning dialogue patterns, and a TDS task (primary task) that aims at not only retrieving accurate entities from KB but also generating natural responses, which are coordinated to achieve collective success in both retrieving accurate KB entities and generating human-like responses via meta learning. Concretely, the dialog generation model amalgamates complementary meta KB and dialog knowledge from two novel auxiliary reasoning tasks that together provide integrated guidance to build a high-quality TDS by adding regularization terms to force primary network to produce similar results to auxiliary networks. While MCL automatically learns appropriate labels for the two auxiliary reasoning tasks from the primary task, without requiring access to any further data. The key idea behind MCL is to use the performance of the primary task, which is trained alongside the auxiliary tasks in one iteration, to improve the auxiliary labels for the next iteration with meta learning. Experimental results on three benchmark datasets show that MCL can generate higher quality responses compared to several strong baselines in terms of both automatic and human evaluations. Code to reproduce the results in this paper is available at: https://github.com/siat-nlp/MCL.

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions

“…Specifically, Eric and Manning (2017) employed a key-value retrieval mechanism to retrieve KB knowledge triplets. Other works treat KB and dialogue history equally as triplet memories (Madotto et al, 2018;Wu et al, 2019;Chen et al, 2019b;He et al, 2020a;Qin et al, 2021a). Memory networks (Sukhbaatar et al, 2015) have been applied to model the dependency between related entity triplets in KB (Bordes et al, 2017;Wang et al, 2020) and improves domain scalability (Qin et al, 2020b;Ma et al, 2021).…”

Leveraging hierarchical semantic‐emotional memory in emotional conversation generation

“…[9] presented a large number of prior methods and datasets for implementing the dialogue systems. Motivated by the significant achievements of the sequence-to-sequence models in conditional text generation, numerous works have been introduced to produce responses with the seq2seq framework [4][5][6]. These models could be learnt and optimised in the end-to-end way and have good flexibility in generating innovative responses.…”

“…With the availability of large-scale conversation data online, much attention has been given to full data-driven neural conversational systems. The sequence-to-sequence model is a typical dialogue generation approach [4][5][6], which employs a recurrent neural network (RNN) encoder to encode the conversation history as a representation, and then feeds this conversation representation into another RNN decoder to generate emotional responses word by word. The conversation systems implemented with the sequence-to-sequence techniques have overwhelmingly established state-of-the-art performances in response generation, since they are learnt in an end-to-end way and can be scale to large-scale corpora, which could generate responses with good quality and flexibility.…”

From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue

“…Task-oriented Dialogue systems (ToDs) aim to assist users in accomplishing various tasks, such as hotel and restaurant reservations (Luong, Pham, and Manning 2015;). Since the system response is guided not only by the dialogue history but also by the query knowledge base results, the ability to query the external knowledge base is essential in the EToDs (He et al 2020a;Qin et al 2021;He, Wang, and Chen 2020). Figure 1 illustrates such an example where the user asks for information about the chinese restaurant.…”