DeepAI AI Chat
Log In Sign Up

Using Ternary Rewards to Reason over Knowledge Graphs with Deep Reinforcement Learning

by   Fréderic Godin, et al.

In this paper, we investigate the practical challenges of using reinforcement learning agents for question-answering over knowledge graphs. We examine the performance metrics used by state-of-the-art systems and determine that they are inadequate. More specifically, they do not evaluate the systems correctly for situations when there is no answer available and thus agents optimized for these metrics are poor at modeling confidence. We introduce a simple new performance metric for evaluating question-answering agents that is more representative of practical usage conditions, and optimize for this metric by extending the binary reward structure used in prior work to a ternary reward structure which also rewards an agent for not answering a question rather than giving an incorrect answer. We show that this can drastically improve the precision of answered questions while only not answering a limited number of questions that were previously answered correctly.


page 1

page 2

page 3

page 4


Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs

The rise of personal assistants has made conversational question answeri...

An Answer Verbalization Dataset for Conversational Question Answerings over Knowledge Graphs

We introduce a new dataset for conversational question answering over Kn...

Answering Questions Over Knowledge Graphs Using Logic Programming Along with Language Models

Question Answering over Knowledge Graphs (KGQA) is the task of answering...

Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks

We examine the problem of question answering over knowledge graphs, focu...

Sybil-proof Answer Querying Mechanism

We study a question answering problem on a social network, where a reque...

FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering

The widely used Fact-based Visual Question Answering (FVQA) dataset cont...

ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models

This work provides a thorough study on how reward scaling can affect per...