RGCL at SemEval-2020 Task 6: Neural Approaches to Definition Extraction

TL;DR

This paper describes the RGCL team's neural network-based system for classifying definitions at sentence and token levels in SemEval 2020, using task-specific adaptations and an extended training set to achieve competitive results.

Contribution

It introduces a flexible neural approach with task-specific adaptations and an automatically extended training set for definition extraction.

Findings

Achieved acceptable evaluation scores on SemEval 2020 Task 6

Demonstrated flexibility in neural architecture selection

Utilized an automatically extended training set

Abstract

This paper presents the RGCL team submission to SemEval 2020 Task 6: DeftEval, subtasks 1 and 2. The system classifies definitions at the sentence and token levels. It utilises state-of-the-art neural network architectures, which have some task-specific adaptations, including an automatically extended training set. Overall, the approach achieves acceptable evaluation scores, while maintaining flexibility in architecture selection.