Generating Informative Conclusions for Argumentative Texts

TL;DR

This paper introduces a new task of generating informative conclusions for argumentative texts, creating a large dataset, and exploring extractive and abstractive methods, including fine-tuned BART models, to improve conclusion generation.

Contribution

The paper presents Webis-ConcluGen-21, a large-scale corpus for conclusion generation, and investigates both extractive and abstractive approaches, including knowledge-augmented fine-tuning of BART.

Findings

Abstractive models with argumentative knowledge improve informativeness.

The corpus is suitable for training and evaluating conclusion generation models.

Trade-offs exist between informativeness and conciseness in generated conclusions.

Abstract

The purpose of an argumentative text is to support a certain conclusion. Yet, they are often omitted, expecting readers to infer them rather. While appropriate when reading an individual text, this rhetorical device limits accessibility when browsing many texts (e.g., on a search engine or on social media). In these scenarios, an explicit conclusion makes for a good candidate summary of an argumentative text. This is especially true if the conclusion is informative, emphasizing specific concepts from the text. With this paper we introduce the task of generating informative conclusions: First, Webis-ConcluGen-21 is compiled, a large-scale corpus of 136,996 samples of argumentative texts and their conclusions. Second, two paradigms for conclusion generation are investigated; one extractive, the other abstractive in nature. The latter exploits argumentative knowledge that augment the data via control codes and finetuning the BART model on several subsets of the corpus. Third, insights are provided into the suitability of our corpus for the task, the differences between the two generation paradigms, the trade-off between informativeness and conciseness, and the impact of encoding argumentative knowledge. The corpus, code, and the trained models are publicly available.