Publication Details

Employing argumentation knowledge graphs for neural argument generation

authored by
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.

External Organisation(s)
Leipzig University
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU Erlangen-Nürnberg)
Paderborn University
IBM Research Europe
Bauhaus-Universität Weimar
Type
Conference contribution
Pages
4744-4754
No. of pages
11
Publication date
2021
Publication status
Published
Peer reviewed
Yes
ASJC Scopus subject areas
Software, Computational Theory and Mathematics, Linguistics and Language, Language and Linguistics
Electronic version(s)
https://aclanthology.org/2021.acl-long.366.pdf (Access: Open)