Neural Response Generation with Dynamic Vocabularies

Wu, Yu; Wu, Wei; Yang, Dejian; Xu, Can; Li, Zhoujun

doi:10.48550/arxiv.1711.11191

Cited by 27 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…or knowledge as conditions to generate more specific responses [7,8] and by improving the model structure, the training algorithms and the decoding strategies [9,10,11]. Additionally, conditional variational autoencoders (CVAEs), which were originally proposed for image generation [12,13], have recently been applied to dialog response generation [14,15].…”

Section: Introductionmentioning

confidence: 99%

Condition-transforming Variational Autoencoder for Conversation Response Generation

Ruan

Ling

Liu³

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the prior distribution of latent variable z follows a multivariate Gaussian distribution with mean and variance modulated by the input conditions. Previous work found that this distribution tends to become conditionindependent in practical application. In our proposed CTVAE model, the latent variable z is sampled by performing a non-linear transformation on the combination of the input conditions and the samples from a condition-independent prior distribution N (0, I). In our objective evaluations, the CTVAE model outperforms the CVAE model on fluency metrics and surpasses a sequence-to-sequence (Seq2Seq) model on diversity metrics. In subjective preference tests, our proposed CTVAE model performs significantly better than CVAE and Seq2Seq models on generating fluency, informative and topic relevant responses.

show abstract

Section: Introductionmentioning

confidence: 99%

Condition-transforming Variational Autoencoder for Conversation Response Generation

Ruan

Ling

Liu³

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…The Dist-1 and Dist-2 scores, for unigrams and bigrams, are the ratios of types to tokens. This kind of diversity measurement is initially proposed by Li et al (2016) to examine the "generic response problem", which is then widely adopted in recent work (Xing et al 2016;Wu et al 2017);…”

mentioning

confidence: 99%

Incorporating Relevant Knowledge in Context Modeling and Response Generation

Li,

Cao

et al. 2018

Preprint

View full text Add to dashboard Cite

To sustain engaging conversation, it is critical for chatbots to make good use of relevant knowledge. Equipped with a knowledge base, chatbots are able to extract conversation-related attributes and entities to facilitate context modeling and response generation. In this work, we distinguish the uses of attribute and entity and incorporate them into the encoder-decoder architecture in different manners. Based on the augmented architecture, our chatbot is able to generate responses by referring to proper entities from the collected knowledge. To validate the proposed approach, we build a movie conversation corpus on which the proposed approach significantly outperforms other four knowledge-grounded models.

show abstract