A Neural Conversational Model
2015/06/19 by Oriol Vinyals, Quoc V. Le, Quoc Le +2 · 4 voices · 1,509 citations
Computer Science · #Artificial intelligence #Computer science #Natural Language Processing Techniques #Natural language processing #Speech and dialogue systems #Speech recognition #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1506.05869
published in arXiv (Cornell University) (Cornell University) · ICML Deep Learning Workshop 2015
openalex publication_date 2015/06/19 · arxiv created 2015/07/22 · arxiv updated 2015/07/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Abstract
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules. We find that this straightforward model can generate simple conversations given a large conversational training dataset. Our preliminary results suggest that, despite optimizing the wrong objective function, the model is able to converse well. It is able extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles. On a domain-specific IT helpdesk dataset, the model can find a solution to a technical problem via conversations. On a noisy open-domain movie transcript dataset, the model can perform simple forms of common sense reasoning. As expected, we also find that the lack of consistency is a common failure mode of our model.
Citations
Cited by
- It’s Not What You Say, It’s How You Say It: Evaluating LLM Responses to Expressions of Belief
- Knowing Ourselves Through Others: Reflecting with AI in Digital Human Debates
- Deep Neural Network for Semantic-based Text Recognition in Images
- Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
- RecSim: A Configurable Simulation Platform for Recommender Systems
- AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses
- Memory and attention in deep learning
- Learning to generate one-sentence biographies from Wikidata
- Dialogue Systems Engineering: A Survey and Future Directions
- Memory-Augmented Recurrent Networks for Dialogue Coherence
- IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems
- End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs
- Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning
- Lifelong Knowledge Learning in Rule-based Dialogue Systems
- Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
- Sequential Copying Networks
- Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
- Knowledge Injection into Dialogue Generation via Language Models
- Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
- Regularizing Dialogue Generation by Imitating Implicit Scenarios
- Exploiting Cross-Sentence Context for Neural Machine Translation
- Social and Emotional Etiquette of Chatbots: A Qualitative Approach to Understanding User Needs and Expectations
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
- An Ensemble Model with Ranking for Social Dialogue
- Theoretical Foundations and Mitigation of Hallucination in Large Language Models
- A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
- EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
- Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
- Deep Reinforcement Learning for Multi-Domain Dialogue Systems
- Exploring Neural Models for Parsing Natural Language into First-Order Logic
- Context-Aware Sequence-to-Sequence Models for Conversational Systems
- Multi-Fact Correction in Abstractive Text Summarization
- Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
- A Multi-Turn Emotionally Engaging Dialog Model
- Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
- RubyStar: A Non-Task-Oriented Mixture Model Dialog System
- Enhancing Self-Disclosure In Neural Dialog Models By Candidate\n Re-ranking
- Teaching Machines to Describe Images via Natural Language Feedback
- GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
- Sequence to Sequence Learning for Optical Character Recognition
- Creativity in Machine Learning
- Seq2Seq AI Chatbot with Attention Mechanism
- Knowledge-Grounded Response Generation with Deep Attentional Latent-Variable Model
- Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses
- EmpDG: Multiresolution Interactive Empathetic Dialogue Generation
- Continuously Learning Neural Dialogue Management
- How Robust are Deep Neural Networks?
- Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
- A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
- Alleviate Exposure Bias in Sequence Prediction with Recurrent Neural Networks
- Evaluating Personal Assistants on Mobile devices
- Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System
- When is it permissible for artificial intelligence to lie? A trust-based approach
- The RLLChatbot: a solution to the ConvAI challenge
- Neural Sequence Model Training via α-divergence Minimization
- Keyword-Guided Neural Conversational Model
- Knowledge-based end-to-end memory networks
- ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
- The Eighth Dialog System Technology Challenge
- Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues
- Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
- Why Do Neural Response Generation Models Prefer Universal Replies?
- Towards Extracting Software Requirements from App Reviews using Seq2seq Framework
- ARAML: A Stable Adversarial Training Framework for Text Generation
- Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations
- Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
- Towards a Human-like Open-Domain Chatbot
- Improving Text Generation with Student-Forcing Optimal Transport
- Data-Efficient Methods for Dialogue Systems
- Retrieval-Enhanced Adversarial Training for Neural Response Generation
- Learning to Select Knowledge for Response Generation in Dialog Systems
- Predicting User Engagement Status for Online Evaluation of Intelligent Assistants
- Emily: Developing An Emotion-affective Open-Domain Chatbot with Knowledge Graph-based Persona
- Unsupervised Text Style Transfer using Language Models as Discriminators
- ScriptWriter: Narrative-Guided Script Generation
- Training Neural Response Selection for Task-Oriented Dialogue Systems
- Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
- End-to-end optimization of goal-driven and visually grounded dialogue systems
- Seq2Seq Mimic Games: A Signaling Perspective
- Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
- Neural Programmer: Inducing Latent Programs with Gradient Descent
- Learning to Start for Sequence to Sequence Architecture
- Personalized Chatbot Trustworthiness Ratings
- PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
- Improving Multi-turn Dialogue Modelling with Utterance ReWriter
- AffectON: Incorporating Affect Into Dialog Generation
- Exploiting Persona Information for Diverse Generation of Conversational Responses
- Attention over Parameters for Dialogue Systems
- DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
- A practical approach to dialogue response generation in closed domains
- Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
- Towards Knowledge-Based Recommender Dialog System
- A Survey of Available Corpora for Building Data-Driven Dialogue Systems
- A Taxonomy of Empathetic Response Intents in Human Social Conversations
- Alquist: The Alexa Prize Socialbot
- How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
- Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans
- Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
- A Hierarchical Latent Structure for Variational Conversation Modeling
- An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
- Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
- Recent Trends in Deep Learning Based Natural Language Processing
- Self-Supervised Dialogue Learning
- Recent advances in conversational NLP : Towards the standardization of Chatbot building
- Auditing Data Provenance in Text-Generation Models
- Natural Language Generation with Neural Variational Models
- Hybrid Code Networks using a convolutional neural network as an input layer achieves higher turn accuracy
- Open-Domain Dialogue Generation Based on Pre-trained Language Models
- A Realistic Face-to-Face Conversation System based on Deep Neural Networks
- Teaching Machines to Converse
- Retrieval-based Goal-Oriented Dialogue Generation
- Adversarial Learning for Neural Dialogue Generation
- ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
- Generating Dialogue Responses from a Semantic Latent Space
- Personalization in Goal-Oriented Dialog
- Falls Prediction Based on Body Keypoints and Seq2Seq Architecture
- Neural Net Models for Open-Domain Discourse Coherence
- Deep Retrieval-Based Dialogue Systems: A Short Review
- Recurrent Models for Auditory Attention in Multi-Microphone Distance Speech Recognition
- Deep Reinforcement Learning for Dialogue Generation
- Steering Output Style and Topic in Neural Response Generation
- GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue
- Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models
- Paraphrase Generation with Deep Reinforcement Learning
- Zero-Resource Knowledge-Grounded Dialogue Generation
- Learning to Reformulate the Queries on the WEB
- Automating App Review Response Generation
- Improved Deep Learning Baselines for Ubuntu Corpus Dialogs
- Evaluating Syntactic Properties of Seq2seq Output with a Broad Coverage HPSG: A Case Study on Machine Translation
- Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection
- Log-Linear RNNs: Towards Recurrent Neural Networks with Flexible Prior Knowledge
- The Technological Gap Between Virtual Assistants and Recommendation Systems
- Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
- An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
- Latent Intention Dialogue Models
- Towards Persona-Based Empathetic Conversational Models
- Multi-Turn Beam Search for Neural Dialogue Modeling
- Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges
- Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
- Deep Reader: Information extraction from Document images via relation extraction and Natural Language
- Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
- Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
- Latent Topic Conversational Models
- End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis
- Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data
- Efficient Natural Language Response Suggestion for Smart Reply
- Amanuensis: The Programmer's Apprentice
- Neural Language Generation: Formulation, Methods, and Evaluation
- SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
- Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards
- Shaping the Narrative Arc: An Information-Theoretic Approach to\n Collaborative Dialogue
- OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts
- Focus-Constrained Attention Mechanism for CVAE-based Response Generation
- Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network
- Enhancing Dialogue Generation via Multi-Level Contrastive Learning
- Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
- Adversarial Bootstrapping for Dialogue Model Training
- Towards a continuous modeling of natural language domains
- Modeling Dyadic Conversations for Personality Inference
- NE-Table: A Neural key-value table for Named Entities
- Learning to Caption Images through a Lifetime by Asking Questions
- Learning End-to-End Goal-Oriented Dialog with Multiple Answers
- The LAMBADA dataset: Word prediction requiring a broad discourse context
- Content Word-based Sentence Decoding and Evaluating for Open-domain Neural Response Generation
- Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
- End-to-End Trainable Non-Collaborative Dialog System
- Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
- Maria: A Visual Experience Powered Conversational Agent
- Table-to-Text Natural Language Generation with Unseen Schemas
- Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
- MOSS: End-to-End Dialog System Framework with Modular Supervision
- Syntax-Infused Variational Autoencoder for Text Generation
- Chainer: A Deep Learning Framework for Accelerating the Research Cycle
- Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
- Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
- Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
- Generative Deep Neural Networks for Dialogue: A Short Review
- Prediction, Selection, and Generation: Exploration of Knowledge-Driven Conversation System
- A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect
- Improving Multi-Turn Response Selection Models with Complementary Last-Utterance Selection by Instance Weighting
- Matching Questions and Answers in Dialogues from Online Forums
- Low-Resource Knowledge-Grounded Dialogue Generation
- A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems
- Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
- Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
- Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability
- An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation
- A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
- Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
- SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
- 2015 in science [wikipedia]
Discussions
Related