paper-with-me

홈 › Papers

Adversarial Learning on the Latent Space for Diverse Dialog Generation

2019-11-10 · COLING 2020 8 · Kashif Khan, Gaurav Sahu, Vikash Balasubramanian, Lili Mou, Olga Vechtomova

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 generating 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.

📄 PDF Abstract BibTeX arXiv:1911.03817

Code (1)

vikigenius/conditional_text_generation 공식 구현 pytorch

Tasks

Sentence

Similar Papers 제목 키워드 기반

DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space

2024-04-10 · Jianxiang Xiang, Zhenhua Liu, Haodong Liu, Yin Bai 외

In real-life conversations, the content is diverse, and there exists the one-to-many problem that requires diverse generation. Previous studies attempted to introduce discrete or Gaussian-based continuous latent variable…

DenoisingDialogue GenerationDiversity

Multi-turn Dialogue Response Generation in an Adversarial Learning Framework

2018-05-30 · WS 2019 8 · Oluwatobi Olabiyi, Alan Salimov, Anish Khazane, Erik T. Mueller

We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified…

DecoderResponse GenerationWord Embeddings

APo-VAE: Text Generation in Hyperbolic Space

2020-04-30 · NAACL 2021 4 · Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao 외

Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without …

Language ModelingLanguage ModellingResponse GenerationText Generation

OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation

2021-04-06 · NAACL 2021 4 · Petr Marek, Vishal Ishwar Naik, Vincent Auvray, Anuj Goyal

Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialog system. Most dialog systems are trained on a pool of annotated OOD data to achieve this goal. However, collecting the annotated OOD data for a giv…

Generative Adversarial NetworkOut of Distribution (OOD) Detection

DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder

2018-05-31 · ICLR 2019 5 · Xiaodong Gu, Kyunghyun Cho, Jung-Woo Ha, Sunghun Kim

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior su…

Response Generation