Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6247–6252 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 6247 Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models Tuhin Chakrabarty 1, Aadit Trivedi2, and Smaranda Muresan1,3 1Department of Computer Science, Columbia University 2College of Computing, Georgia Tech 3Data Science Institute, Columbia University atrivedi@gatech.edu, {tuhin.chakr,smara}@cs.columbia.edu Abstract Enthymemes are defined as arguments where a premise or conclusion is left implicit. We tackle the task of generating the implicit premise in an enthymeme, which requires not only an understanding of the stated conclusion and premise, but also additional inferences that could depend on commonsense knowledge. The largest available dataset for enthymemes (Habernal et al., 2018) consists of 1.7k sam- ples, which is not large enough to train a neu- ral text generation model. To address this is- sue, we take advantage of a similar task and dataset: Abductive reasoning in narrative text (Bhagavatula et al., 2020). However, we show that simply using a state-of-the-art seq2seq model fine-tuned on this data might not gen- erate meaningful implicit premises associated with the given enthymemes. We demonstrate that encoding discourse-aware commonsense during fine-tuning improves the quality of the generated implicit premises and outperforms all other baselines both in automatic and hu- man evaluations on three different datasets. 1 Introduction In argumentation theory, an enthymeme is defined as an incomplete argument found in discourse, where some components are explicit, but other propositions are left implicit and need to be filled in as premises or conclusions to fully understand what the argument is (Walton and Reed, 2005). In many instances the missing proposition is a premise. The well-cited example of the Silver Blade case from one of Sherlock Holmes’ stories (Walton and Reed, 2005) presents such as an incomplete argument A dog was kept in the stable, and yet, though someone had been in and fetched out a horse, he had not barked enough to rouse the two lads in the loft. Obviously, the midnight visitor was someone whom the dog knew well. Reason Vaccinations save lives Claim Vaccination should be mandatory for all children ZeroShot Vaccines save lives, they save money Fine-tuned on ART Vaccinations are the best way to protect children. Fine-tuned on ART +PARA-C Vaccinations are the best way to prevent childhood diseases. Table 1: Implicit Premise Generation by BART (Lewis et al., 2020) in three different setting for an input en- thymeme from dataset by Habernal et al. (2018) The missing premise in this case is the general- ization “Dogs generally bark when a person enters an area unless the dog knows the person well." While there has been work on identification (i.e., classification) and reconstruction of implicit premises in enthymemes (Rajendran et al., 2016; Habernal et al., 2018; Reisert et al., 2015; Boltuži´c and Šnajder, 2016; Razuvayevskaya and Teufel, 2017), to our knowledge, automatically generat- ing an implicit premise from a given enthymeme is a new task. There are two main challenges that need to be addressed: 1) lack of …

Content truncated to 500 words