Linguistic representations for fewer-shot relation extraction across domains

TL;DR

This paper investigates how linguistic representations like syntactic and semantic graphs can improve cross-domain, few-shot relation extraction, showing that both types enhance performance similarly across domains.

Contribution

It extends prior work by evaluating the impact of linguistic graphs on cross-domain, few-shot relation extraction, demonstrating their comparable utility in improving generalization.

Findings

Linguistic graphs significantly boost few-shot transfer performance.

Semantic and syntactic graphs have roughly equal utility.

Linguistic representations aid cross-domain generalization.

Abstract

Recent work has demonstrated the positive impact of incorporating linguistic representations as additional context and scaffolding on the in-domain performance of several NLP tasks. We extend this work by exploring the impact of linguistic representations on cross-domain performance in a few-shot transfer setting. An important question is whether linguistic representations enhance generalizability by providing features that function as cross-domain pivots. We focus on the task of relation extraction on three datasets of procedural text in two domains, cooking and materials science. Our approach augments a popular transformer-based architecture by alternately incorporating syntactic and semantic graphs constructed by freely available off-the-shelf tools. We examine their utility for enhancing generalization, and investigate whether earlier findings, e.g. that semantic representations can be more helpful than syntactic ones, extend to relation extraction in multiple domains. We find that while the inclusion of these graphs results in significantly higher performance in few-shot transfer, both types of graph exhibit roughly equivalent utility.