Information Extraction Tool Text2ALM: From Narratives to Action Language System Descriptions

TL;DR

Text2ALM is a narrative understanding tool that uses an action language to perform reasoning on complex event descriptions, achieving competitive results on benchmark tasks by combining NLP and knowledge reasoning.

Contribution

The paper introduces Text2ALM, a novel system that integrates natural language processing with action language reasoning to interpret narratives and answer questions effectively.

Findings

Outperforms or matches state-of-the-art on 6 of 7 bAbI tasks

Generalizes to a broader range of narratives

Combines NLP and knowledge reasoning techniques

Abstract

In this work we design a narrative understanding tool Text2ALM. This tool uses an action language ALM to perform inferences on complex interactions of events described in narratives. The methodology used to implement the Text2ALM system was originally outlined by Lierler, Inclezan, and Gelfond (2017) via a manual process of converting a narrative to an ALM model. It relies on a conglomeration of resources and techniques from two distinct fields of artificial intelligence, namely, natural language processing and knowledge representation and reasoning. The effectiveness of system Text2ALM is measured by its ability to correctly answer questions from the bAbI tasks published by Facebook Research in 2015. This tool matched or exceeded the performance of state-of-the-art machine learning methods in six of the seven tested tasks. We also illustrate that the Text2ALM approach generalizes to a broader spectrum of narratives.