Multi-domain Dialog System Research Articles

Mutually improved response generation and dialogue summarization for multi-domain task-oriented dialogue systems

With the development of pre-trained language models (PrLM), the research of PrLM-based multi-domain task-oriented dialogue systems (TOD) has attracted growing attention and has achieved great progress. However, most current studies suffer from two problems. First, they model dialogue state tracking as an independent subtask supervised by slot-value pairs, resulting in poor adaptability when transferring to new task domains. Second, these studies ignore the fact that not all dialogue histories are valuable for the ensuing turns as they increase in length. To tackle these two issues, we propose a simple and novel framework to explore multi-domain TOD by jointly training response generation and dialogue summarization with PrLM as the backbone. Specifically, first, we use fluent text generated by the dialogue summarization model to replace formatted dialogue states, treating the dialogue state identification task as a natural language generation task, which allows dialogue state tracking to be easily extended to new task domains. Second, dialogue summarization removes redundant and useless information from the current dialogue process and is fed into the response decoder enabling the system to focus on crucial details in long dialogues. Furthermore, we employ a dialogue chunk detector to assist the dialogue summarization model and design a fusion mechanism to dynamically integrate helpful dialogue summarization into the response generation process. Experimental results show that the proposed model achieves state-of-the-art performance in both automatic and human evaluations on two public datasets and demonstrate that the joint framework can benefit both tasks from each other.

External Slot Relationship Memory for Multi-Domain Dialogue State Tracking

Dialogue state tracking is an essential component in multi-domain dialogue systems that aims to accurately determine the current dialogue state based on the dialogue history. Existing research has addressed the issue of multiple mappings in dialogues by employing slot self-attention as a data-driven approach. However, learning the relationships between slots from a single sample often has limitations and may introduce noise and have high time complexity issues. In this paper, we propose an external slot relation memory-based dialogue state tracking model (ER-DST). By utilizing external memory storage, we learn the relationships between slots as a dictionary of multi-domain slot relations. Additionally, we employ a small filter to discard slot information irrelevant to the current dialogue state. Our method is evaluated on MultiWOZ 2.0 and MultiWOZ 2.1, achieving improvements of 0.23% and 0.39% over the baseline models, respectively, while reducing the complexity of the slot relationship learning component to O(n).

Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy

Achieving high performance in a multi-domain dialogue system with low computation is undoubtedly challenging. Previous works applying an end-to-end approach have been very successful. However, the computational cost remains a major issue since the large-sized language model using GPT-2 is required. Meanwhile, the optimization for individual components in the dialogue system has not shown promising result, especially for the component of dialogue management due to the complexity of multi-domain state and action representation. To cope with these issues, this article presents an efficient guidance learning where the imitation learning and the hierarchical reinforcement learning (HRL) with human-in-the-loop are performed to achieve high performance via an inexpensive dialogue agent. The behavior cloning with auxiliary tasks is exploited to identify the important features in latent representation. In particular, the proposed HRL is designed to treat each goal of a dialogue with the corresponding sub-policy so as to provide efficient dialogue policy learning by utilizing the guidance from human through action pruning and action evaluation, as well as the reward obtained from the interaction with the simulated user in the environment. Experimental results on ConvLab-2 framework show that the proposed method achieves state-of-the-art performance in dialogue policy optimization and outperforms the GPT-2 based solutions in end-to-end system evaluation.

Performance Improvement on Traditional Chinese Task-Oriented Dialogue Systems With Reinforcement Learning and Regularized Dropout Technique

The development of conversational voice assistant applications has been in full swing around the world. This paper aims to develop traditional Chinese multi-domain task-oriented dialogue (TOD) systems. It is typically implemented using pipeline approach, where submodules are optimized independently, resulting in inconsistencies with each other. Instead, this paper implements end-to-end multi-domain TOD models using pre-trained deep neural networks (DNNs). This allows us to integrate all the submodules into one single DNN model to solve the inconsistencies. Data shortages are common in conversational natural language processing (NLP) tasks using DNN models. In this regard, dropout regularization has been widely used to improve overfitting caused by insufficient training dataset. However, the randomness it introduces leads to non-negligible discrepancies between training and inference. On the other hand, pre-trained language models have successfully provided effective regularization for NLP tasks. An inherent disadvantage is that fine-tuning the pre-trained language model suffers from exposure bias and loss-evaluation mismatch. To this end, we propose a reinforcement learning (RL) approach to address both issues. Furthermore, we adopt a method called regularized dropout (R-Drop) to improve the inconsistency in dropout layers of DNNs. Experimental results show that both our proposed RL approach and the R-Drop technique can significantly improve the joint target accuracy (JGA) score and combined score of traditional Chinese TOD system in tasks of dialogue state tracking (DST) and end-to-end sentence prediction, respectively.

Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems

A task-oriented dialogue system (TOD) is an important application of artificial intelligence. In the past few years, works on multi-domain TODs have attracted increased research attention and have seen much progress. A main challenge of such dialogue systems is finding ways to deal with cross-domain slot sharing and dialogue act temporal planning. However, existing studies seldom consider the models’ reasoning ability over the dialogue history; moreover, existing methods overlook the structure information of the ontology schema, which makes them inadequate for handling multi-domain TODs. In this paper, we present a multi-task learning framework equipped with graph attention networks (GATs) to probe the above two challenges. In the method, we explore a dialogue state GAT consisting of a dialogue context subgraph and an ontology schema subgraph to alleviate the cross-domain slot sharing issue. We further construct a GAT-enhanced memory network using the updated nodes in the ontology subgraph to filter out the irrelevant nodes to acquire the needed dialogue states. For dialogue act temporal planning, a similar GAT and corresponding memory network are proposed to obtain fine-grained dialogue act representation. Moreover, we design an entity detection task to improve the capability of soft gate, which determines whether the generated tokens are from the vocabulary or knowledge base. In the training phase, four training tasks are combined and optimized simultaneously to facilitate the response generation process. The experimental results for automatic and human evaluations show that the proposed model achieves superior results compared to the state-of-the-art models on the MultiWOZ 2.0 and MultiWOZ 2.1 datasets.

Adversarial Training for Multi Domain Dialog System

Natural Language Understanding and Speech Understanding systems are now a global trend, and with the advancement of artificial intelligence and machine learning techniques, have drawn attention from both the academic and business communities. Domain prediction, intent detection and entity extraction or slot fillings are the most important parts for such intelligent systems. Various traditional machine learning algorithms such as Bayesian algorithm, Support Vector Machine, and Artificial Neural Network, along with recent Deep Neural Network techniques, are used to predict domain, intent, and entity. Most language understanding systems process user input in a sequential order: domain is first predicted, then intent and slots are filled according to the semantic frames of the predicted domain. This pipeline approach, however, has many disadvantages including downstream error; i.e., if the system fails to predict the domain, then the system also fails to predict intent and slot. The main purpose of this paper is to mitigate the risk of downstream error propagation in traditional pipelined models and improve the predictive performance of domain, intent, and slot- all of which are critical steps for speech understanding and dialog systems- with a deep learning-based single joint model trained with an adversarial approach and long short-term memory (LSTM) algorithm. The systematic experimental analysis shows significant improvements in predictive performance for domain, intent, and entity with the proposed adversarial joint model, compared to the base joint model.

Generating Predictable and Adaptive Dialog Policies in Single- and Multi-domain Goal-oriented Dialog Systems

Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.

DORA: Towards policy optimization for task-oriented dialogue system with efficient context

Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system, called Dialogue System with Optimizing a Recurrent Action Policy using Efficient Context (DORA), that uses SL, with subsequently applied RL to optimize dialogue systems using a recurrent dialogue policy. This dialogue policy recurrently generates explicit system actions as a both word-level and high-level policy. As a result, DORA is clearly optimized during both SL and RL steps by using an explicit system action policy that considers an efficient context instead of the entire dialogue history. The system actions are both interpretable and controllable, whereas the latent actions are not. DORA improved the success rate by 6.6 points on MultiWOZ 2.0 and by 10.9 points on MultiWOZ 2.1.

SUMBT+LaRL: Effective Multi-Domain End-to-End Neural Task-Oriented Dialog System

The recent advent of neural approaches for developing each dialog component in task-oriented dialog systems has remarkably improved, yet optimizing the overall system performance remains a challenge. Besides, previous research on modeling complicated multi-domain goal-oriented dialogs in end-to-end fashion has been limited. In this paper, we present an effective multi-domain end-to-end trainable neural dialog system <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SUMBT+LaRL</i> that incorporates two previous strong models and facilitates them to be fully differentiable. Specifically, the SUMBT+ estimates user-acts as well as dialog belief states, and the LaRL models latent system action spaces and generates responses given the estimated contexts. We emphasize that the training framework of three steps significantly and stably increase dialog success rates: separately pretraining the SUMBT+ and LaRL, fine-tuning the entire system, and then reinforcement learning of dialog policy. We also introduce new reward criteria of reinforcement learning for dialog policy training. Then, we discuss experimental results depending on the reward criteria and different dialog evaluation methods. Consequently, our model achieved the new state-of-the-art success rate of 85.4% on corpus-based evaluation, and a comparable success rate of 81.40% on simulator-based evaluation provided by the DSTC8 challenge. To our best knowledge, our work is the first comprehensive study of a modularized E2E multi-domain dialog system that learning from each component to the entire dialog policy for task success.

MTSS: Learn from Multiple Domain Teachers and Become a Multi-Domain Dialogue Expert

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response. In this paper, we propose a novel method to acquire a satisfying policy and subtly circumvent the knotty dialogue state representation problem in the multi-domain setting. Inspired by real school teaching scenarios, our method is composed of multiple domain-specific teachers and a universal student. Each individual teacher only focuses on one specific domain and learns its corresponding domain knowledge and dialogue policy based on a precisely extracted single domain dialogue state representation. Then, these domain-specific teachers impart their domain knowledge and policies to a universal student model and collectively make this student model a multi-domain dialogue expert. Experiment results show that our method reaches competitive results with SOTAs in both multi-domain and single domain setting.

Ontology-based framework for a multi-domain spoken dialogue system

Multi-domain spoken dialogue is a challenging field where the objective of the most proposed ideas is to mimic the human–human dialogue. This paper proposes to tackle the domain selection problem in the context of multi-domain spoken dialogue as a set theory problem to resolve. First, we built each dialogue domain as an ontology following an architecture with some rules to respect. Second, each ontology is considered as a set and its concepts are the elements. Third, an ontology-based classifier is used to map the user sentence into a set of ontologies concepts and to generate an intersection between these concepts. Finally, a new turn analysis and domain selection algorithm is proposed to infer the intended domain from the user sentence using the intersection set and three techniques, namely Domain Rewards, Dominant Concept, and Current Domain. To evaluate the proposed approach, a corpus of 120 simulated dialogues was built to cover four application domains. In our experiment, the assessment of the system is performed by considering all possibilities of a natural verbal interaction where a changing of semantic context occurs during the dialogue. The obtained results show that the system accuracy reaches a satisfactory performance of 83.13% while the average number of turns by dialogue is 6.79.

Unsupervised Spoken Language Understanding for a Multi-Domain Dialog System

This paper proposes an unsupervised spoken language understanding (SLU) framework for a multi-domain dialog system. Our unsupervised SLU framework applies a non-parametric Bayesian approach to dialog acts, intents and slot entities, which are the components of a semantic frame. The proposed approach reduces the human effort necessary to obtain a semantically annotated corpus for dialog system development. In this study, we analyze clustering results using various evaluation metrics for four dialog corpora. We also introduce a multi-domain dialog system that uses the unsupervised SLU framework. We argue that our unsupervised approach can help overcome the annotation acquisition bottleneck in developing dialog systems. To verify this claim, we report a dialog system evaluation, in which our method achieves competitive results in comparison with a system that uses a manually annotated corpus. In addition, we conducted several experiments to explore the effect of our approach on reducing development costs. The results show that our approach be helpful for the rapid development of a prototype system and reducing the overall development costs.

Example-based dialog modeling for practical multi-domain dialog system

This paper proposes a generic dialog modeling framework for a multi-domain dialog system to simultaneously manage goal-oriented and chat dialogs for both information access and entertainment. We developed a dialog modeling technique using an example-based approach to implement multiple applications such as car navigation, weather information, TV program guidance, and chatbot. Example-based dialog modeling (EBDM) is a simple and effective method for prototyping and deploying of various dialog systems. This paper also introduces the system architecture of multi-domain dialog systems using the EBDM framework and the domain spotting technique. In our experiments, we evaluate our system using both simulated and real users. We expect that our approach can support flexible management of multi-domain dialogs on the same framework.

Managing out-of-grammar utterances by topic estimation with domain extensibility in multi-domain spoken dialogue systems

Spoken dialogue systems must inevitably deal with out-of-grammar utterances. We address this problem in multi-domain spoken dialogue systems, which deal with more tasks than a single-domain system. We defined a topic by augmenting a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, domain extensibility, that is, the ability to add new domains to the system, should be inherently retained in multi-domain systems. To estimate domains without sacrificing extensibility, we collected documents from the Web as training data. Since the data contained a certain amount of noise, we used latent semantic mapping (LSM), which enables robust topic estimation by removing the effects of noise from the data. Experimental results showed that our method improved topic estimation accuracy by 23.2 points for data including out-of-grammar utterances.

Linking Semantic and Knowledge Representations in a Multi-Domain Dialogue System

We describe a two-layer architecture for supporting semantic interpretation and domain reasoning in dialogue systems. Building system that supports both semantic interpretation and domain reasoning in a transparent and well-integrated manner is an unresolved problem because of the diverging requirements of the semantic representations used in contextual interpretation versus the knowledge representations used in domain reasoning. We propose an architecture that provides both portability and efficiency in natural language interpretation by maintaining separate semantic and domain knowledge representations, and integrating them via an ontology mapping procedure. The ontology mapping is used to obtain representations of utterances in a form most suitable for domain reasoners and to automatically specialize the lexicon. The use of a linguistically motivated parser for producing semantic representations for complex natural language sentences facilitates building portable semantic interpretation components as well as connections with domain reasoners. Two evaluations demonstrate the effectiveness of our approach: we show that a small number of mapping rules are sufficient for customizing the generic semantic representation to a new domain, and that our automatic lexicon specialization technique improves parser speed and accuracy.