Automatic Detection of Machine Generated Text: A Critical Survey

Proceedings of the 28th International Conference on Computational Linguistics, pages 2296–2309 Barcelona, Spain (Online), December 8-13, 2020 2296 Automatic Detection of Machine Generated Text: A Critical Survey Ganesh Jawahar, Muhammad Abdul-Mageed, Laks V.S. Lakshmanan University of British Columbia, Vancouver, Canada ganeshjwhr@gmail.com, muhammad.mageed@ubc.ca, laks@cs.ubc.ca Abstract Text generative models (TGMs) excel in producing text that matches the style of human language reasonably well. Such TGMs can be misused by adversaries, e.g., by automatically generating fake news and fake product reviews that can look authentic and fool humans. Detectors that can distinguish text generated by TGM from human written text play a vital role in mitigating such misuse of TGMs. Recently, there has been a flurry of works from both natural language pro- cessing (NLP) and machine learning (ML) communities to build accurate detectors for English. Despite the importance of this problem, there is currently no work that surveys this fast-growing literature and introduces newcomers to important research challenges. In this work, we fill this void by providing a critical survey and review of this literature to facilitate a comprehensive un- derstanding of this problem. We conduct an in-depth error analysis of the state-of-the-art detector and discuss research directions to guide future work in this exciting area. 1 Introduction Current state-of-the-art text generative models (TGMs) excel in producing text that approaches the style of human language, especially in terms of grammaticality, fluency, coherency, and usage of real world knowledge (Radford et al., 2019; Zellers et al., 2019; Keskar et al., 2019; Bakhtin et al., 2020; Brown et al., 2020). TGMs are useful in a wide variety of applications, including story generation (Fan et al., 2018), conversational response generation (Zhang et al., 2020), code auto-completion (Solaiman et al., 2019), and radiology report generation (Liu et al., 2019a). However, TGMs can also be misused for fake news generation (Zellers et al., 2019; Brown et al., 2020; Uchendu et al., 2020), fake product reviews generation (Adelani et al., 2020), and spamming/phishing. (Weiss, 2019). Thus, it is important to build tools that can minimize the threats posed by the misuse of TGMs. The commonly used approach to combat the threats posed by the misuse of TGMs is to formulate the problem of distinguishing text generated by TGMs and human written text as a classification task. The classifier, henceforth called detector, can be used to automatically remove machine generated text from online platforms such as social media, e-commerce, email clients, and government forums, when the intention of the TGM generated text is abuse. An ideal detector should be: (i) accurate, that is, good accuracy with a good trade-off for false positives and false negatives depending on the online platform (email client, social media) on which TGM is applied (Solaiman et al., 2019); (ii) data-efficient, that is, needs as few examples as possible from the TGM used by the attacker (Zellers et al., 2019); (iii) generalizable, that is, detects text generated by different modeling choices of the TGM used by the attacker such as model architecture, TGM training data, …

Content truncated to 500 words