Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model

End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate informative utterances, so it limits their usage from some real-world conversational applications. This paper attempts at generating diverse and informative responses with a variational generation model, which contains a joint attention mechanism conditioning on the information from both dialogue contexts and extra knowledge.

• Publication year

  2019

• Venue

  Computer Speech and Language

• Publication date

  2019-03-23

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1016/j.csl.2020.101069arXiv 1903.09813
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Overview of the seventh Dialog System Technology Challenge: DSTC7

  2020cited by this paper
• Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations

  2019cited by this paper
• OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs

  2019cited by this paper
• Overview of the sixth dialog system technology challenge: DSTC6

  2019cited by this paper
• Variational Memory Encoder-Decoder

  2018cited by this paper
• Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization

  2018cited by this paper
• Neural Approaches to Conversational AI

  2018cited by this paper
• Understanding Convolutional Neural Networks for Text Classification

  2018cited by this paper
• Variational Autoregressive Decoder for Neural Response Generation

  2018cited by this paper
• Improving Variational Encoder-Decoders in Dialogue Generation

  2018cited by this paper
• Variational Attention for Sequence-to-Sequence Models

  2017cited by this paper
• Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation

  2017cited by this paper
• Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning

  2017cited by this paper
• Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

  2017cited by this paper
• End-to-end Conversation Modeling Track in DSTC6

  2017cited by this paper
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

  2017cited by this paper
• A Knowledge-Grounded Neural Conversation Model

  2017cited by this paper
• End-to-End Task-Completion Neural Dialogue Systems

  2017cited by this paper
• Hierarchical Recurrent Attention Network for Response Generation

  2017cited by this paper
• Deep Reinforcement Learning for Dialogue Generation

  2016cited by this paper
• Coherent Dialogue with Attention-Based Language Models

  2016cited by this paper
• A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues

  2016cited by this paper
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

  2015cited by this paper
• Generating Sentences from a Continuous Space

  2015cited by this paper
• A Diversity-Promoting Objective Function for Neural Conversation Models

  2015cited by this paper
• A Neural Conversational Model

  2015cited by this paper
• Learning Structured Output Representation using Deep Conditional Generative Models

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014influential reference
• GloVe: Global Vectors for Word Representation

  2014cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Auto-Encoding Variational Bayes

  2013cited by this paper
• METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments

  2005cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

  2002cited by this paper

• Dynamic worker allocation in Seru production systems with actor-critic and pointer networks

  2025cites this paper
• Company-Specific Knowledge Matters: Retrieval-Augmented Generation for Earnings Call Answer Rehearsal

  2025cites this paper
• A Review of Knowledge-Grounded Dialogue Systems

  2023cites this paper
• Knowledge Interpolated Conditional Variational Auto-Encoder for Knowledge Grounded Dialogues

  2023cites this paper
• KINet: Incorporating Relevant Facts Into Knowledge-Grounded Dialog Generation

  2023cites this paper
• Neural response generation for task completion using conversational knowledge graph

  2023cites this paper
• Don’t Forget Your ABC’s: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems

  2022cites this paper
• SPK-CG: Siamese Network based Posterior Knowledge Selection Model for Knowledge Driven Conversation Generation

  2022cites this paper
• DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation

  2022cites this paper
• Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems

  2022cites this paper
• Unstructured Text Enhanced Open-Domain Dialogue System: A Systematic Survey

  2021influential citation
• Using Paralinguistic Information to Disambiguate User Intentions for Distinguishing Phrase Structure and Sarcasm in Spoken Dialog Systems

  2021cites this paper
• Knowledge-Grounded Dialogue Generation with Term-level De-noising

  2021cites this paper
• Unsupervised Knowledge Selection for Dialogue Generation

  2021cites this paper
• A Neural Conversation Generation Model via Equivalent Shared Memory Investigation

  2021cites this paper
• Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation

  2021cites this paper
• Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an Identity

  2021cites this paper
• A Pre-trained Document-Grounded Conversation Model with Learning Low-frequency Patterns

  2021cites this paper
• Multiple Knowledge Syncretic Transformer for Natural Dialogue Generation

  2020cites this paper
• On Dialogue Systems Based on Deep Learning

  2020cites this paper
• Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation

  2020cites this paper
• Cross Copy Network for Dialogue Generation

  2020cites this paper
• A Compare Aggregate Transformer for Understanding Document-grounded Dialogue

  2020cites this paper
• Exploiting Text Matching Techniques for Knowledge-Grounded Conversation

  2020cites this paper
• Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy

  2020cites this paper
• Knowledge-Grounded Chatbot Based on Dual Wasserstein Generative Adversarial Networks with Effective Attention Mechanisms

  2020cites this paper
• Incremental Transformer with Deliberation Decoder for Document Grounded Conversations

  2019cites this paper
• Utterance Embedding Knowledge Attention Self-Attention Context Attention Feed-Forward Target Embedding Self-Attention Context Attention Utterance Attention Feed-Forward Target Embedding Self-Attention Knowledge Attention First-Pass Attention Feed-Forward Document / Utterance Embedding Feed-Forward S

  2019cites this paper