AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities

TL;DR

This paper introduces a transformer-based joint entity and relation extraction model for linking mathematical symbols to descriptions in LaTeX documents, achieving high precision and competitive leaderboard placement.

Contribution

The novel end-to-end approach incorporates relation information into entity extraction, enabling training on partially annotated datasets and improving extraction accuracy.

Findings

Achieved 95.43% macro F1 in physics domain

Reached 79.17% macro F1 in math domain

Placed 3rd in SemEval-2022 Task 12 leaderboard

Abstract

In this paper, we present an end-to-end joint entity and relation extraction approach based on transformer-based language models. We apply the model to the task of linking mathematical symbols to their descriptions in LaTeX documents. In contrast to existing approaches, which perform entity and relation extraction in sequence, our system incorporates information from relation extraction into entity extraction. This means that the system can be trained even on data sets where only a subset of all valid entity spans is annotated. We provide an extensive evaluation of the proposed system and its strengths and weaknesses. Our approach, which can be scaled dynamically in computational complexity at inference time, produces predictions with high precision and reaches 3rd place in the leaderboard of SemEval-2022 Task 12. For inputs in the domain of physics and math, it achieves high relation extraction macro F1 scores of 95.43% and 79.17%, respectively. The code used for training and evaluating our models is available at: https://github.com/nicpopovic/RE1st