Employing argumentation knowledge graphs for neural argument generation

verfasst von

Khalid Al-Khatib, Lukas Trautner, Henning Wachsmuth, Yufang Hou, Benno Stein

Abstract

Generating high-quality arguments, while being challenging, may benefit a wide range of downstream applications, such as writing assistants and argument search engines. Motivated by the effectiveness of utilizing knowledge graphs for supporting general text generation tasks, this paper investigates the usage of argumentation-related knowledge graphs to control the generation of arguments. In particular, we construct and populate three knowledge graphs, employing several compositions of them to encode various knowledge into texts of debate portals and relevant paragraphs from Wikipedia. Then, the texts with the encoded knowledge are used to fine-tune a pre-trained text generation model, GPT-2. We evaluate the newly created arguments manually and automatically, based on several dimensions important in argumentative contexts, including argumentativeness and plausibility. The results demonstrate the positive impact of encoding the graphs' knowledge into debate portal texts for generating arguments with superior quality than those generated without knowledge.

Externe Organisation(en)

Universität Leipzig
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU Erlangen-Nürnberg)
Universität Paderborn
IBM Research Europe
Bauhaus-Universität Weimar

Typ

Aufsatz in Konferenzband

Seiten

4744-4754

Anzahl der Seiten

11

Publikationsdatum

2021

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Software, Theoretische Informatik und Mathematik, Linguistik und Sprache, Sprache und Linguistik

Elektronische Version(en)

https://aclanthology.org/2021.acl-long.366.pdf (Zugang: Offen)