Dialog-based Language Learning

04/20/2016
by   Jason Weston, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/21/2015

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

A long-term goal of machine learning is to build intelligent conversatio...
research
01/23/2018

Analyzing Language Learned by an Active Question Answering Agent

We analyze the language learned by an agent trained with reinforcement l...
research
03/29/2018

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...
research
10/05/2022

Emotion Twenty Questions Dialog System for Lexical Emotional Intelligence

This paper presents a web-based demonstration of Emotion Twenty Question...
research
03/30/2023

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

Large language models (LLMs) have emerged as valuable tools for many nat...
research
02/19/2015

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

One long-term goal of machine learning research is to produce methods th...
research
06/01/2020

Probing Emergent Semantics in Predictive Agents via Question Answering

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

Please sign up or login with your details

Forgot password? Click here to reset