The problem of understanding the reasons behindwhy different machine learning classifiers make specific predictions is a difficult one, mainly because the inner workings of thealgorithms underlying such tools are not amenable to the directextraction of succinct explanations. In this paper, we address theproblem of automatically extracting balanced explanations frompredictions generated by any classifier, which include not onlywhy the prediction might be correct but also why it could bewrong. Our framework, called Balanced English Explanations ofForecasts, can generate such explanations in natural language.After showing that the problem of generating explanations is NPcomplete, we focus on the development of a heuristic algorithm,empirically showing that it produces high-quality results bothin terms of objective measures—with statistically significanteffects shown for several parameter variations—and subjectiveevaluations based on a survey completed by 100 anonymousparticipants recruited via Amazon Mechanical Turk.
To View the Base Paper Abstract Contents
Now it is Your Time to Shine.
Great careers Start Here.
We Guide you to Every Step
Success! You're Awesome
Thank you for filling out your information!
We’ve sent you an email with your Final Year Project PPT file download link at the email address you provided. Please enjoy, and let us know if there’s anything else we can help you with.
To know more details Call 900 31 31 555
The WISEN Team