Learning Discourse-level Diversity for Neural Dialog Models using
            Conditional Variational Autoencoders

Zhao, Tiancheng; Zhao, Ran; Eskénazi, Maxine

doi:10.18653/v1/p17-1061

Cited by 614 publications

(606 citation statements)

References 35 publications

Supporting

Mentioning

601

Contrasting

Order By: Relevance

“…build a VAE for text generation and design a cost function that encourages interpretability of the latent variables. Zhang et al (2016), Serban et al (2016) and Zhao et al (2017) apply VAE to sequence-to-sequence problems, improving over deterministic alternatives. Chen et al (2016) propose a hybrid model combining autoregressive convolutional layers with the VAE.…”

Section: Related Workmentioning

confidence: 99%

A Hybrid Convolutional Variational Autoencoder for Text Generation

Semeniuta¹,

Severyn²,

Barth³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

189

114

View full text Add to dashboard Cite

In this paper we explore the effect of architectural choices on learning a variational autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid the issue of the VAE collapsing to a deterministic model.

show abstract

Section: Related Workmentioning

confidence: 99%

A Hybrid Convolutional Variational Autoencoder for Text Generation

Semeniuta¹,

Severyn²,

Barth³

2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

189

114

View full text Add to dashboard Cite

show abstract

“…To better solve these problems, we propose a context-aware variational autoencoder (CWVAE) together with a two-stage training procedure. Vari-ational Autoencoder (VAE) based models have shown great potential in modeling the one-tomany problem and generate diversified inferences (Bowman et al, 2015;Zhao et al, 2017).…”

Section: Corresponding Authormentioning

confidence: 99%

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder

Du¹,

Ding²,

Liu³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP). Given an observed event, it is trivial for human to infer its intents and effects, while this type of If-Then reasoning still remains challenging for NLP systems. To facilitate this, a If-Then commonsense reasoning dataset Atomic is proposed, together with an RNN-based Seq2Seq model to conduct such reasoning. However, two fundamental problems still need to be addressed: first, the intents of an event may be multiple, while the generations of RNN-based Seq2Seq models are always semantically close; second, external knowledge of the event background may be necessary for understanding events and conducting the If-Then reasoning. To address these issues, we propose a novel context-aware variational autoencoder effectively learning event background information to guide the If-Then reasoning. Experimental results show that our approach improves the accuracy and diversity of inferences compared with state-of-the-art baseline methods.

show abstract

“…In addition to image generation, CVAE has been successfully applied to some NLP tasks. For example, Zhao et al (2017) apply CVAE to dialog generation, while Guu et al (2018) use CVAE for sentence generation.…”

Section: Conditional Variational Autoencodermentioning

confidence: 99%

Learning to Decipher Hate Symbols

Qian

ElSherief

Belding

et al. 2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Existing computational models to understand hate speech typically frame the problem as a simple classification task, bypassing the understanding of hate symbols (e.g., 14 words, kigy) and their secret connotations. In this paper, we propose a novel task of deciphering hate symbols. To do this, we leverage the Urban Dictionary and collected a new, symbolrich Twitter corpus of hate speech. We investigate neural network latent context models for deciphering hate symbols. More specifically, we study Sequence-to-Sequence models and show how they are able to crack the ciphers based on context. Furthermore, we propose a novel Variational Decipher and show how it can generalize better to unseen hate symbols in a more challenging testing setting.

show abstract

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

Cited by 614 publications

References 35 publications

A Hybrid Convolutional Variational Autoencoder for Text Generation

A Hybrid Convolutional Variational Autoencoder for Text Generation

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder

Learning to Decipher Hate Symbols

Contact Info

Product

Resources

About