Goto

Collaborating Authors

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

arXiv.org Artificial Intelligence

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.


Automated Assessment of Open-ended Student Answers in Tutorial Dialogues Using Gaussian Mixture Models

AAAI Conferences

Open-ended student answers often need to be assessed in context. However, there are not many previous works that consider context when automatically assessing student answers. Furthermore, student responses vary significantly in their explicit content and writing style which leads to a wide range of assessment scores for the same qualitative assessment category, e.g. correct answers vs. incorrect answers. In this paper, we propose an approach to assessing student answers that takes context into account and which handles variability using probabilistic Gaussian Mixture Models (GMMs). We developed the model using a recently released corpus called DT-Grade which was manually annotated, taking context into account, with four different levels of answer correctness. Our best GMM model outperforms the baseline model with a margin of 9% in terms of accuracy.


Instagram is reportedly testing a 'questions' feature for Stories

Mashable

Have a burning question for your most loyal Instagram followers? You might soon be able to ask them in your Stories. Instagram is reportedly testing a new feature that would let users ask their followers open-ended questions from within their Stories, according to a user who says they're part of the test. SEE ALSO: Instagram will tell you when you're'caught up' so you know when to stop scrolling The feature, first reported by Android Police, adds a new "question" sticker in the same menu where you can add GIFs, polls, music, and other add-ons to your Story. You can then ask an open-ended question for your followers who are prompted to "type something," in response to the question.


General Assembly Session Has Slim Agenda, Also Open-Ended

U.S. News

But parliamentary actions are expected to keep the work session running after Wednesday in case other issues surface. GOP legislators want to be ready in case they're asked by federal judges to redraw House and Senate districts. Lawmakers also could find agreement soon on judicial redistricting and judicial selection.


Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System

Journal of Artificial Intelligence Research

Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue policy, which addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We report on the design, construction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey. Our results show that by optimizing its performance via reinforcement learning, NJFun measurably improves system performance.