Conditional Variational AutoEncoder
Related Papers
Latent Variable Model for Multi-modal Translation
AbstractIn this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be …...
A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph
AbstractGenerating a vivid, novel, and diverse essay with only several given topic words is a promising task of natural language generation. Previous work in this task exists two challenging problems: …...
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling
AbstractGenerating questions based on answers and relevant contexts is a challenging task. Recent work mainly pays attention to the quality of a single generated question. However, question generation is actually …...
Guiding Variational Response Generator to Exploit Persona
AbstractLeveraging persona information of users in Neural Response Generators (NRG) to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over …...
Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders
AbstractConditional Variational AutoEncoder (CVAE) effectively increases the diversity and informativeness of responses in open-ended dialogue generation tasks through enriching the context vector with sampled latent variables. However, due to the …...
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data
AbstractPrevious works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this …...
A Variational Hierarchical Model for Neural Cross-Lingual Summarization
AbstractThe goal of the cross-lingual summarization (CLS) is to convert a document in one language (e.g., English) to a summary in another one (e.g., Chinese). The CLS task is essentially …...
Incorporating Causal Analysis into Diversified and Logical Response Generation
AbstractAlthough the Conditional Variational Auto-Encoder (CVAE) model can generate more diversified responses than the traditional Seq2Seq model, the responses often have low relevance with the input words or are illogical …...
Neural Machine Translation with Phrase-Level Universal Visual Representations
AbstractMultimodal machine translation (MMT) aims to improve neural machine translation (NMT) with additional visual information, but most existing MMT methods require paired input of source sentence and image, which makes …...
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
AbstractLifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems. To address the catastrophic forgetting issue of LL, generative replay methods are widely employed to consolidate past knowledge with …...