Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

by   Rajarshi Das, et al.
University of Massachusetts Amherst

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.


page 1

page 2

page 3

page 4


Relation/Entity-Centric Reading Comprehension

Constructing a machine that understands human language is one of the mos...

Procedural Reasoning Networks for Understanding Multimodal Procedures

This paper addresses the problem of comprehending procedural commonsense...

Procedural Reading Comprehension with Attribute-Aware Context Flow

Procedural texts often describe processes (e.g., photosynthesis and cook...

Interactive Machine Comprehension with Dynamic Knowledge Graphs

Interactive machine reading comprehension (iMRC) is machine comprehensio...

A Study of the Tasks and Models in Machine Reading Comprehension

To provide a survey on the existing tasks and models in Machine Reading ...

Reading Comprehension using Entity-based Memory Network

This paper introduces a novel neural network model for question answerin...

Please sign up or login with your details

Forgot password? Click here to reset