Training Neural Response Selection for Task-Oriented Dialogue Systems

Henderson, Matthew; Vulić, Ivan; Gerz, Daniela; Casanueva, Iñigo; Budzianowski, Paweł; Coope, Sam; Spithourakis, Georgios P.; Wen, Tao; Mrkšić, Nikola; Su, Pei-Hao

doi:10.18653/v1/p19-1536

Cited by 82 publications

(116 citation statements)

References 51 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Full details of the neural structure are given in Henderson et al (2019). To summarize, the context and response are both separately passed through sub-networks that:…”

Section: Encoder Modelmentioning

confidence: 99%

A Repository of Conversational Datasets

Henderson¹,

Budzianowski²,

Casanueva³

et al. 2019

Proceedings of the First Workshop on NLP for Conversational AI

Self Cite

View full text Add to dashboard Cite

Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds of millions of examples, and a standardised evaluation procedure for conversational response selection models using 1-of-100 accuracy. The repository contains scripts that allow researchers to reproduce the standard datasets, or to adapt the pre-processing and data filtering steps to their needs. We introduce and evaluate several competitive baselines for conversational response selection, whose implementations are shared in the repository, as well as a neural encoder model that is trained on the entire training set.

show abstract

“…Full details of the neural structure are given in Henderson et al (2019). To summarize, the context and response are both separately passed through sub-networks that:…”

Section: Encoder Modelmentioning

confidence: 99%

A Repository of Conversational Datasets

Henderson¹,

Budzianowski²,

Casanueva³

et al. 2019

Proceedings of the First Workshop on NLP for Conversational AI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Existing studies can be generally categorized into two groups. The first group is retrieval-based dialogue systems [9,32,38,40,52] which select the proper response from the response candidates under the given user input or dialogue context, and have been applied in many industrial products such as XiaoIce from Microsoft [29] and AliMe Assist from Alibaba [14]. The second group is generationbased dialogue systems [15,27,28,30] which generate the response word by word under an encoder-decoder framework [27,28].…”

Section: Introductionmentioning

confidence: 99%

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Hua

Zhao

Tao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrievalbased dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where all of the context and knowledge contents are used to match the response candidate with various representation methods. Actually, different parts of the context and knowledge are differentially important for recognizing the proper response candidate, as many utterances are useless due to the topic shift. Those excessive useless information in the context and knowledge can influence the matching process and leads to inferior performance. To address this problem, we propose a multi-turn Response Selection Model that can Detect the relevant parts of the Context and Knowledge collection (RSM-DCK). Our model first uses the recent context as a query to pre-select relevant parts of the context and knowledge collection at the word-level and utterance-level semantics. Further, the response candidate interacts with the selected context and knowledge collection respectively. In the end, the fused representation of the context and response candidate is utilized to post-select the relevant parts of the knowledge collection for matching with more confidence. We test our proposed model on two benchmark datasets. Evaluation results indicate that our model achieves better performance than the existing methods, and can effectively detect the relevant context and knowledge for response selection.

show abstract

“…Moreover, there are no clearly observed distinct patterns between successful dialogues for the two model types. This suggests that they might be effectively ensembled using a ranking model to evaluate the score of each response (Henderson et al, 2019b). We will investigate the complementarity of the two approaches along with ensemble methods in future work.…”

Section: Evaluation With Automatic Measuresmentioning

confidence: 99%

Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

Budzianowski¹,

Vulić²

2019

Proceedings of the 3rd Workshop on Neural Generation and Translation

Self Cite

223

133

View full text Add to dashboard Cite

Data scarcity is a long-standing and crucial challenge that hinders quick development of task-oriented dialogue systems across multiple domains: task-oriented dialogue models are expected to learn grammar, syntax, dialogue reasoning, decision making, and language generation from absurdly small amounts of taskspecific data. In this paper, we demonstrate that recent progress in language modeling pretraining and transfer learning shows promise to overcome this problem. We propose a taskoriented dialogue model that operates solely on text input: it effectively bypasses explicit policy and language generation modules. Building on top of the TransferTransfo framework and generative model pre-training (Radford et al., 2019), we validate the approach on complex multi-domain task-oriented dialogues from the MultiWOZ dataset. Our automatic and human evaluations show that the proposed model is on par with a strong task-specific neural baseline. In the long run, our approach holds promise to mitigate the data scarcity problem, and to support the construction of more engaging and more eloquent task-oriented conversational agents.

show abstract

Training Neural Response Selection for Task-Oriented Dialogue Systems

Cited by 82 publications

References 51 publications

A Repository of Conversational Datasets

A Repository of Conversational Datasets

Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems

Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

Contact Info

Product

Resources

About