DeepAI AI Chat
Log In Sign Up

Dialog-based Language Learning

by   Jason Weston, et al.

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.


page 1

page 2

page 3

page 4


Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems

A long-term goal of machine learning is to build intelligent conversatio...

Analyzing Language Learned by an Active Question Answering Agent

We analyze the language learned by an agent trained with reinforcement l...

Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering

Human conversation is a complex mechanism with subtle nuances. It is hen...

Emotion Twenty Questions Dialog System for Lexical Emotional Intelligence

This paper presents a web-based demonstration of Emotion Twenty Question...

DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents

Large language models (LLMs) have emerged as valuable tools for many nat...

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

One long-term goal of machine learning research is to produce methods th...

Probing Emergent Semantics in Predictive Agents via Question Answering

Recent work has shown how predictive modeling can endow agents with rich...