Guichard, JonathanJonathanGuichardRuane, ElayneElayneRuaneSmith, RossRossSmithBean, DanDanBeanVentresque, AnthonyAnthonyVentresque2019-04-242019-04-242019 IEEE2019-04-09http://hdl.handle.net/10197/10135The 2019 IEEE International Conference on Artificial Intelligence Testing (AITest), San Francisco, United States of America, 4-9 April 2019Assessing a conversational agent’s understanding capabilities is critical, as poor user interactions could seal the agent’s fate at the very beginning of its lifecycle with users abandoning the system. In this paper we explore the use of paraphrases as a testing tool for conversational agents. Paraphrases, which are different ways of expressing the same intent, are generated based on known working input by per- forming lexical substitutions. As the expected outcome for this newly generated data is known, we can use it to assess the agent’s robustness to language variation and detect potential understanding weaknesses. As demonstrated by a case study, we obtain encouraging results as it appears that this approach can help anticipate potential understanding shortcomings and that these shortcomings can be addressed by the generated paraphrases.en© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.TestingRobustnessToolsTask analysisGrannerEnginesSoftwareConference Publication10.1109/AITest.2019.000-72019-04-07SOW2017-054SOW2018-07713/RC/2094https://creativecommons.org/licenses/by-nc-nd/3.0/ie/