Dialogue Management based on Multi-domain Corpus

Ge, Wendong; Xu, Bo

doi:10.18653/v1/w15-4648

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of two ontologies is proposed in [26]: one associated with a broad-coverage SLU module, and a second associated with a task-domain. The use of Recurrent Neural Networks has been very recently proposed in [27,28].…”

Section: State Of the Artmentioning

confidence: 99%

Building multi-domain conversational systems from single domain resources

Griol

Molina

2018

Neurocomputing

View full text Add to dashboard Cite

Current advances in the development of mobile and smart devices have generated a growing demand for natural human-machine interaction and favored the intelligent assistant metaphor, in which a single interface gives access to a wide range of functionalities and services. Conversational systems constitute and important enabling technology in this paradigm. However, they are usually defined to interact in semanticrestricted domains in which users are offered a limited number of options and functionalities. The design of multi-domain systems implies that a single conversational system is able to assist the user in a variety of tasks. In this paper we propose an architecture for the development of multi-domain conversational systems that allows: (1) integrating available multi and single domain speech recognition and understanding modules, (2) combining available system in the different domains implied so that it is not necessary to generate new expensive resources for the multidomain system, (3) achieving better domain recognition rates to select the appropriate interaction management strategies. We have evaluated our proposal combining three systems in different domains to show that the proposed architecture can satisfactory deal with multimodain dialogs.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Building multi-domain conversational systems from single domain resources

Griol

Molina

2018

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…Recent work on deep learning applied to task-oriented conversational agents include the following. [6] uses a Recurrent Neural Network (RNN) for dialogue act prediction in a POMDP-based dialogue system, which focuses on mapping system and user sentences to dialogue acts. [2] applies Deep Reinforcement Learning with a fully-connected neural network for trading negotiations in board games, which focuses on mapping game situations to dialogue actions.…”

Section: Literature Reviewmentioning

confidence: 99%

Scaling up deep reinforcement learning for multi-domain dialogue systems

Cuayáhuitl

Williamson

et al. 2017

2017 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems due to large search spaces. This paper proposes a three-stage method for multi-domain dialogue policy learning-termed NDQN, and applies it to an informationseeking spoken dialogue system in the domains of restaurants and hotels. In this method, the first stage does multi-policy learning via a network of DQN agents; the second makes use of compact state representations by compressing raw inputs; and the third stage applies a pre-training phase for bootstraping the behaviour of agents in the network. Experimental results comparing DQN (baseline) versus NDQN (proposed) using simulations report that the proposed method exhibits better scalability and is promising for optimising the behaviour of multi-domain dialogue systems. An additional evaluation reports that the NDQN agents outperformed a K-Nearest Neighbour baseline in task success and dialogue length, yielding more efficient and successful dialogues.

show abstract

“…The fields of Natural Language Processing (NLP) and Natural Language Understanding (NLU) have since developed many applications for the automatic identification, or classification, of DA's. Most prominently, within dialogue management systems, they have been used as high-level representations for user intents, system actions and dialogue state (Griol et al 2008;Ge and Xu 2015;CuayÁhuitl et al 2016;Wen et al 2016;Liu et al 2018;Firdaus et al 2020). DA's have also been applied to spoken language translation (Reithinger et al 1996;Kumar et al 2017), team communication in the domain of robot-assisted disaster response (Anikina and Kruijff-Korbayova 2019) and understanding the flow of conversation within therapy sessions (Lee et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Sentence encoding for Dialogue Act classification

2021

View full text Add to dashboard Cite

In this study, we investigate the process of generating single-sentence representations for the purpose of Dialogue Act (DA) classification, including several aspects of text pre-processing and input representation which are often overlooked or underreported within the literature, for example, the number of words to keep in the vocabulary or input sequences. We assess each of these with respect to two DA-labelled corpora, using a range of supervised models, which represent those most frequently applied to the task. Additionally, we compare context-free word embedding models with that of transfer learning via pre-trained language models, including several based on the transformer architecture, such as Bidirectional Encoder Representations from Transformers (BERT) and XLNET, which have thus far not been widely explored for the DA classification task. Our findings indicate that these text pre-processing considerations do have a statistically significant effect on classification accuracy. Notably, we found that viable input sequence lengths, and vocabulary sizes, can be much smaller than is typically used in DA classification experiments, yielding no significant improvements beyond certain thresholds. We also show that in some cases the contextual sentence representations generated by language models do not reliably outperform supervised methods. Though BERT, and its derivative models, do represent a significant improvement over supervised approaches, and much of the previous work on DA classification.

show abstract

Dialogue Management based on Multi-domain Corpus

Cited by 4 publications

References 21 publications

Building multi-domain conversational systems from single domain resources

Building multi-domain conversational systems from single domain resources

Scaling up deep reinforcement learning for multi-domain dialogue systems

Sentence encoding for Dialogue Act classification

Contact Info

Product

Resources

About