A Network-based End-to-End Trainable Task-oriented Dialogue System

Wen, Tao; Vandyke, David; Mrkšić, Nikola; Gašić, Milica; Rojas-Barahona, Lina Maria; Su, Pei-Hao; Ultes, Stefan; Young, Steve

doi:10.18653/v1/e17-1042

Cited by 455 publications

(319 citation statements)

References 27 publications

Supporting

Mentioning

279

Contrasting

Unclassified

Order By: Relevance

“…More recently, [3] used domain description based unstructured knowledge using an additional recurrent neural network (GRU) architecture added to the word embeddings for domain keywords to further improve the performance of such models. There are also many recent works that incorporated end-to-end models with structured knowledge sources, such as knowledge graphs [24], [5], [25]. [6] used a key-value retrieval network to augment the vocabulary distribution of the keys of the KG with the attentions of their associated values.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

2019

View full text Add to dashboard Cite

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their end-to-end text generation functionality. Since such models can greatly benefit from user intent and knowledge graph integration, in this paper we propose an RNN-based end-to-end encoder-decoder architecture which is trained with joint embeddings of the knowledge graph and the corpus as input. The model provides an additional integration of user intent along with text generation, trained with multi-task learning paradigm along with an additional regularization technique to penalize generating the wrong entity as output. The model further incorporates a Knowledge Graph entity lookup during inference to guarantee the generated output is state-full based on the local knowledge graph provided. We finally evaluated the model using the BLEU score, empirical evaluation depicts that our proposed architecture can aid in the betterment of task-oriented dialogue system's performance.

show abstract

Section: Related Workmentioning

confidence: 99%

“…[6] introduced such a multi-turn, multi-domain task-oriented dialogue dataset. They performed a Wizard-of-Oz based data collection scheme inspired by [24]. They used the Amazon Mechanical Turk (AMT) platform for data collection.…”

Section: Datasetmentioning

confidence: 99%

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

2019

View full text Add to dashboard Cite

show abstract

“…Wen et al [62] constructed a task-oriented dialogue system by using a modular neural generation model. Neural network is used to realize the process of all modules, and specific tasks of restaurant reservation was achieved.…”

Section: A Task-oriented Dialogue Systemsmentioning

confidence: 99%

AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions

Zhang

Guo

Wang

et al. 2019

2019 IEEE SmartWorld, Ubiquitous Intelligence &Amp; Computing, Advanced &Amp; Trusted Computing, Scalable Computing &Amp; Commu

View full text Add to dashboard Cite

In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural network-based methods emerged. Meanwhile, the research objectives have also changed from generating smooth and coherent sentences to infusing personalized traits to enrich the diversification of newly generated content. With the rapid development of text generation solutions, one comprehensive survey is urgent to summarize the achievements and track the state of the arts. In this survey paper, we present the general systematical framework, illustrate the widely utilized models and summarize the classic applications of text generation.

show abstract

“…3). These models have shown state-of-the-art performance in machine translation tasks , and have been applied to text-based dialogue management with promising results (Lowe et al, 2015;Wen et al, 2016). For the task of generating dense representations of phone sequences, the seq2seq model is trained in a similar way to auto-encoders (Vincent et al, 2008), where in- put and target sequences are the same, forcing the model to learn to reconstruct the input sequence.…”

Section: Seq2seq Phone Encodermentioning

confidence: 99%

Using phone features to improve dialogue state tracking generalisation to unseen states

Casanueva

Hain

Nicolao

et al. 2016

Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

View full text Add to dashboard Cite

The generalisation of dialogue state tracking to unseen dialogue states can be very challenging. In a slot-based dialogue system, dialogue states lie in discrete space where distances between states cannot be computed. Therefore, the model parameters to track states unseen in the training data can only be estimated from more general statistics, under the assumption that every dialogue state will have the same underlying state tracking behaviour. However, this assumption is not valid. For example, two values, whose associated concepts have different ASR accuracy, may have different state tracking performance. Therefore, if the ASR performance of the concepts related to each value can be estimated, such estimates can be used as general features. The features will help to relate unseen dialogue states to states seen in the training data with similar ASR performance. Furthermore, if two phonetically similar concepts have similar ASR performance, the features extracted from the phonetic structure of the concepts can be used to improve generalisation. In this paper, ASR and phonetic structurerelated features are used to improve the dialogue state tracking generalisation to unseen states of an environmental control system developed for dysarthric speakers.

show abstract

A Network-based End-to-End Trainable Task-oriented Dialogue System

Cited by 455 publications

References 27 publications

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-task Learning

AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions

Using phone features to improve dialogue state tracking generalisation to unseen states

Contact Info

Product

Resources

About