Adversarial Learning on the Latent Space for Diverse Dialog Generation

Proceedings of the 28th International Conference on Computational Linguistics, pages 5026–5034 Barcelona, Spain (Online), December 8-13, 2020 5026 Adversarial Learning on the Latent Space for Diverse Dialog Generation Kashif Khan1∗, Gaurav Sahu1∗, Vikash Balasubramanian1∗, Lili Mou2, Olga Vechtomova1 1University of Waterloo 2Dept. Computing Science, University of Alberta Alberta Machine Intelligence Institute (Amii) {kashif.khan,gaurav.sahu,v9balasu,ovechtom}@uwaterloo.ca doublepower.mou@gmail.com Abstract Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation, but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework based on generative adversarial nets for gen- erating conditioned responses. Our model first learns a meaningful representation of sentences by autoencoding, and then learns to map an input query to the response representation, which is in turn decoded as a response sentence. Both quantitative and qualitative evaluations show that our model generates more fluent, relevant, and diverse responses than existing state-of-the-art methods.1 1 Introduction Dialog generation is a challenging problem because it not only requires us to model the context in a conversation but also to exploit it to generate a relevant and fluent response. A dialog generation system can be divided into two parts: 1) encoding the context of the conversation, and 2) generating a response conditioned on the given context. A generated response is considered to be “good” if it is meaningful, fluent, and most importantly, relevant to the given context. With the advancement of deep learning, sequence-to-sequence (Seq2Seq) models (Sutskever et al., 2014) are adopted for dialog systems to encode conversational context and generate a response. However, they suffer from the problem of generic utterance generation, e.g., always generating “I don’t know” (Serban et al., 2016; Li et al., 2016). One possible explanation (Wei et al., 2019) is the high uncertainty in dialog generation. A plausible response is analogous to a “mode” of a continuous distribution, and the response distribution is thus multimodal. However, the decoder of a Seq2Seq model is trained by cross- entropy loss, which is equivalent to minimizing the KL divergence between the target and predicted distributions. The asymmetric nature of KL divergence makes the learned distribution wide-spreading, analogous to the mode-averaging problem for continuous variables. Variational encoder-decoders (Serban et al., 2017; Bahuleyan et al., 2018; Zhao et al., 2017) and Wasserstein encoder-decoders (Bahuleyan et al., 2019) adopt probabilistic modeling to encourage di- versity in responses. However, their decoders are also trained by cross-entropy loss against the target sequence, still making the model generate generic utterances. In this paper, we propose an approach that uses adversarial learning in the latent space for dialog gen- eration. We first train a variational autoencoder (VAE) (Kingma and Welling, 2014) on sentences, and then apply a generative aderversarial network (GAN) on the latent space of the VAE. At inference time, we obtain the latent representation of the response from the generator of the GAN and decode it using the VAE’s decoder. In this way, we can benefit from the mode-capturing property of GANs (Mao et al., …

Content truncated to 500 words