Argument Invention from First Principles

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1013–1026 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 1013 Argument Invention from First Principles Yonatan Bilu , Ariel Gera, Daniel Hershcovich, Benjamin Sznajder, Dan Lahav, Guy Moshkowich, Anael Malet, Assaf Gavron, Noam Slonim IBM Research {yonatanb,arielge,benjams,dan.lahav,guy.moshkowitch,assaf.gavron,noams}@il.ibm.com, daniel.hershcovich@gmail.com, anael.malet@sciencespo.fr Abstract Competitive debaters often find themselves facing a challenging task – how to debate a topic they know very little about, with only minutes to prepare, and without access to books or the Internet? What they often do is rely on ”first principles”, commonplace argu- ments which are relevant to many topics, and which they have refined in past debates. In this work we aim to explicitly define a taxonomy of such principled recurring arguments, and, given a controversial topic, to automatically identify which of these arguments are relevant to the topic. As far as we know, this is the first time that this approach to argument invention is formalized and made explicit in the context of NLP. The main goal of this work is to show that it is possible to define such a taxonomy. While the taxonomy suggested here should be thought of as a ”first attempt” it is nonetheless coherent, covers well the relevant topics and coincides with what professional debaters ac- tually argue in their speeches, and facilitates automatic argument invention for new topics. 1 Introduction In his treatise De Inventione Cicero defines the five canons of classical rhetoric as: inventio (inven- tion), dispositio (arrangement), elocutio (style), memoria (memory), and pronuntiatio (delivery). The first of these, Inventio, is defined as a sys- tematic search for arguments (Glenn et al., 2008), with applicability to a wide variety of situations often seen as a desired property (Lauer, 2004). This problem has been referred to in the context of NLP as the task of Argument Invention (Wal- ton and Gordon, 2012, 2017), but did not receive abundant attention. One natural way people go through the pro- cess of inventio is to look for arguments in rele- vant texts, or, if they are familiar with the topic, rely on their knowledge and memoria for doing so. This is reminiscent of the way Argument Min- ing algorithms operate (see e.g. Lippi and Torroni, 2015, 2016). However, we often find ourselves in situations where that is not possible. For exam- ple, when arguing politics over lunch, we might find ourselves backed into a corner, facing a topic with which we are not very familiar, but somehow nonetheless need to justify or oppose. This often happens because we were initially arguing some principle, and now we need to apply it to an unfa- miliar example. Professional debaters often face this problem. Presented with an unfamiliar topic they need to quickly come up with relevant arguments. The main technique for doing so is called arguing from ”first principles” – relying on a ”bank” of princi- pled arguments, which are relevant to a wide vari- ety of topics1. …

Content truncated to 500 words