Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts

TL;DR

This paper introduces Textual Analogy Parsing (TAP), a task to model higher-order relations in sentences by explicitly representing shared and compared facts, enabling advanced discourse understanding.

Contribution

It proposes the TAP task, creates a new dataset, and develops a model using ILP to enforce structural constraints for better meaning representation.

Findings

The model effectively captures shared and compared facts in text.

The dataset enables training and evaluation of TAP systems.

Structural constraints improve parsing accuracy.

Abstract

To understand a sentence like "whereas only 10% of White Americans live at or below the poverty line, 28% of African Americans do" it is important not only to identify individual facts, e.g., poverty rates of distinct demographic groups, but also the higher-order relations between them, e.g., the disparity between them. In this paper, we propose the task of Textual Analogy Parsing (TAP) to model this higher-order meaning. The output of TAP is a frame-style meaning representation which explicitly specifies what is shared (e.g., poverty rates) and what is compared (e.g., White Americans vs. African Americans, 10% vs. 28%) between its component facts. Such a meaning representation can enable new applications that rely on discourse understanding such as automated chart generation from quantitative text. We present a new dataset for TAP, baselines, and a model that successfully uses an ILP to enforce the structural constraints of the problem.