Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

TL;DR

This paper introduces a neural model that constructs dynamic, structured knowledge graphs from procedural text to improve machine comprehension and question answering, achieving state-of-the-art results on relevant datasets.

Contribution

The paper presents a novel neural approach that builds evolving knowledge graphs from text using machine reading comprehension, enhancing understanding and reasoning capabilities.

Findings

Achieves state-of-the-art results on PROPARA datasets.

Demonstrates effectiveness on RECIPES dataset.

Knowledge graphs aid in imposing commonsense constraints.

Abstract

We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text. It builds these graphs recurrently for each step of the described procedure, and uses them to track the evolving states of participant entities. We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans. The explicit, structured, and evolving knowledge graph representations that our model constructs can be used in downstream question answering tasks to improve machine comprehension of text, as we demonstrate empirically. On two comprehension tasks from the recently proposed PROPARA dataset (Dalvi et al., 2018), our model achieves state-of-the-art results. We further show that our model is competitive on the RECIPES dataset (Kiddon et al., 2015), suggesting it may be generally applicable. We present some evidence that the model's knowledge graphs help it to impose commonsense constraints on its predictions.