Towards Flow Graph Prediction of Open-Domain Procedural Texts
This work addresses the challenge of automating procedural reasoning for broader applications, though it is incremental as it builds on existing recipe-based frameworks.
The paper tackles the problem of machine comprehension of procedural texts by predicting flow graphs from open-domain instructions, achieving higher performance through domain adaptation from cooking to wikiHow articles.
Machine comprehension of procedural texts is essential for reasoning about the steps and automating the procedures. However, this requires identifying entities within a text and resolving the relationships between the entities. Previous work focused on the cooking domain and proposed a framework to convert a recipe text into a flow graph (FG) representation. In this work, we propose a framework based on the recipe FG for flow graph prediction of open-domain procedural texts. To investigate flow graph prediction performance in non-cooking domains, we introduce the wikiHow-FG corpus from articles on wikiHow, a website of how-to instruction articles. In experiments, we consider using the existing recipe corpus and performing domain adaptation from the cooking to the target domain. Experimental results show that the domain adaptation models achieve higher performance than those trained only on the cooking or target domain data.