A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents

12/02/2018
by   Heriberto Cuayáhuitl, et al.
0

The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given that the amount of dialogue history and corresponding representations can play an important role in the overall performance of a conversational system. This paper studies the amount of history required by conversational agents for reliably predicting dialogue rewards. The task of dialogue reward prediction is chosen for investigating the effects of varying amounts of dialogue history and their impact on system performance. Experimental results using a dataset of 18K human-human dialogues report that lengthy dialogue histories of at least 10 sentences are preferred (25 sentences being the best in our experiments) over short ones, and that lengthy histories are useful for training dialogue reward predictors with strong positive correlations between target dialogue rewards and predicted ones.

READ FULL TEXT
research
04/11/2021

Conversational Semantic Role Labeling

Semantic role labeling (SRL) aims to extract the arguments for each pred...
research
05/24/2022

A Dataset for Sentence Retrieval for Open-Ended Dialogues

We address the task of sentence retrieval for open-ended dialogues. The ...
research
09/26/2019

Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement

We present "AutoJudge", an automated evaluation method for conversationa...
research
04/22/2020

Where is the context? – A critique of recent dialogue datasets

Recent dialogue datasets like MultiWOZ 2.1 and Taskmaster-1 constitute s...
research
03/20/2021

Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training

Despite important progress, conversational systems often generate dialog...
research
07/05/2023

Different Games in Dialogue: Combining character and conversational types in strategic choice

In this paper, we show that investigating the interaction of conversatio...
research
12/06/2022

Sources of Noise in Dialogue and How to Deal with Them

Training dialogue systems often entails dealing with noisy training exam...

Please sign up or login with your details

Forgot password? Click here to reset