Conversations From Make-Believe: An Attentive Encoder–Decoder Chatbot Trained on Scripted Dialogue

This paper builds a fully neural, open-domain chat-bot that learns to respond like a conversational partner rather than a search engine, using an encoder-decoder with bidirectional recurrent memory and a token-level attention mechanism to track context across turns. A large corpus of fictional, face-to-face exchanges is cleaned into paired utterances, tokenized with subword units, and used to train the model end-to-end, yielding fluent, on-topic replies without hand-crafted rules or retrieval templates. Training and validation use sequence likelihood objectives, while quality is assessed with both automatic indicators (e.g., perplexity and n-gram overlap) and qualitative probes that test specificity, coherence, and avoidance of generic "safe" answers. A lightweight desktop interface demonstrates interactive behavior by surfacing multiple candidate responses from beam search and selecting among them for variety and fit. The study discusses common failure modes in open-domain chat (repetition, blandness, drift) and outlines practical remedies—data curation, decoding constraints, and post-training reward signals—to further align responses with human conversational expectations.

• Publication year

  2025

• Venue

  International Conference on Advances in Computing and Artificial Intelligence

• Publication date

  2025-12-26

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ACAI68217.2025.11406303
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Attention is All you Need

  2017cited by this paper
• Adversarial Learning for Neural Dialogue Generation

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

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

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

  2016cited by this paper
• A Persona-Based Neural Conversation Model

  2016cited by this paper
• A Diversity-Promoting Objective Function for Neural Conversation Models

  2015cited by this paper
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• Effective Approaches to Attention-based Neural Machine Translation

  2015cited by this paper
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems

  2015cited by this paper
• A Neural Conversational Model

  2015cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014influential reference
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014influential reference
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• A computational approach to politeness with application to social factors

  2013cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• Movie-DiC: a Movie Dialogue Corpus for Research and Development

  2012cited by this paper
• The Anatomy of A.L.I.C.E.

  2009cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• ELIZA—a computer program for the study of natural language communication between man and machine

  1966cited by this paper

• No citing papers are available for this paper.