Knowledge-Enhanced Evidence Retrieval for Counterargument Generation

TL;DR

This paper introduces a knowledge-enhanced NLI system that improves the retrieval of complex counterevidence for counterargument generation by incorporating knowledge graphs, outperforming existing models especially on inference-intensive cases.

Contribution

The paper presents a novel knowledge-enhanced NLI model that effectively handles causality and example-based reasoning, advancing counterevidence retrieval capabilities.

Findings

Outperforms baseline NLI models on inference-heavy datasets

Enhances counterevidence retrieval accuracy, especially for complex cases

Demonstrates the effectiveness of knowledge graphs in reasoning tasks

Abstract

Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a natural language inference (NLI) model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.