Knowledge-Aware Procedural Text Understanding with Multi-Stage Training

TL;DR

This paper introduces KOALA, a knowledge-aware model with multi-stage training that enhances procedural text understanding by integrating external knowledge and fine-tuning strategies, achieving state-of-the-art results.

Contribution

The paper proposes a novel approach combining external knowledge retrieval and multi-stage training to improve procedural text understanding.

Findings

KOALA outperforms baselines on ProPara and Recipes datasets.

External knowledge integration improves reasoning accuracy.

Multi-stage training enhances model performance on procedural tasks.

Abstract

Procedural text describes dynamic state changes during a step-by-step natural process (e.g., photosynthesis). In this work, we focus on the task of procedural text understanding, which aims to comprehend such documents and track entities' states and locations during a process. Although recent approaches have achieved substantial progress, their results are far behind human performance. Two challenges, the difficulty of commonsense reasoning and data insufficiency, still remain unsolved, which require the incorporation of external knowledge bases. Previous works on external knowledge injection usually rely on noisy web mining tools and heuristic rules with limited applicable scenarios. In this paper, we propose a novel KnOwledge-Aware proceduraL text understAnding (KOALA) model, which effectively leverages multiple forms of external knowledge in this task. Specifically, we retrieve informative knowledge triples from ConceptNet and perform knowledge-aware reasoning while tracking the entities. Besides, we employ a multi-stage training schema which fine-tunes the BERT model over unlabeled data collected from Wikipedia before further fine-tuning it on the final model. Experimental results on two procedural text datasets, ProPara and Recipes, verify the effectiveness of the proposed methods, in which our model achieves state-of-the-art performance in comparison to various baselines.