AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities
This addresses the challenge of extracting structured information from technical documents like LaTeX for researchers and practitioners in math and physics, though it is incremental as it builds on existing transformer-based methods.
The paper tackles the problem of linking mathematical symbols to descriptions in LaTeX documents by proposing an end-to-end joint entity and relation extraction approach that uses relation extraction to inform entity extraction, achieving high precision and third place in SemEval-2022 Task 12 with macro F1 scores of 95.43% for physics and 79.17% for math.
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