Dialog-based Language Learning

Abstract

A long-term goal of machine learning research is to build an intelligent dialog agent. Most research in natural language understanding has focused on learning from fixed training sets of labeled data, with supervision either at the word level (tagging, parsing tasks) or sentence level (question answering, machine translation). This kind of supervision is not realistic of how humans learn, where language is both learned by, and used for, communication. In this work, we study dialog-based language learning, where supervision is given naturally and implicitly in the response of the dialog partner during the conversation. We study this setup in two domains: the bAbI dataset of (Weston et al., 2015) and large-scale question answering from (Dodge et al., 2015). We evaluate a set of baseline learning strategies on these tasks, and show that a novel model incorporating predictive lookahead is a promising approach for learning from a teacher's response. In particular, a surprising result is that it can learn to answer questions correctly without any reward-based supervision at all.

References in corpus (5)

• Sequence Level Training with Recurrent Neural Networks
• Large-scale Simple Question Answering with Memory Networks
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
• MazeBase: A Sandbox for Learning from Games

Cited by in corpus (17)

• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• A Neural Knowledge Language Model
• Generative Deep Neural Networks for Dialogue: A Short Review
• Teaching Machines to Describe Images via Natural Language Feedback
• REFINER: Reasoning Feedback on Intermediate Representations
• Towards a Continuous Knowledge Learning Engine for Chatbots
• A Paradigm for Situated and Goal-Driven Language Learning
• Towards Multi-Agent Communication-Based Language Learning
• Deep Active Learning for Dialogue Generation
• Why Build an Assistant in Minecraft?
• Language Expansion In Text-Based Games
• Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
• Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning
• Grounding Human-to-Vehicle Advice for Self-driving Vehicles
• e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations
• Scaffolding Networks: Incremental Learning and Teaching Through Questioning
• Pseudo Labeling and Negative Feedback Learning for Large-scale Multi-label Domain Classification