LMN at SemEval-2022 Task 11: A Transformer-based System for English Named Entity Recognition

Abstract

Processing complex and ambiguous named entities is a challenging research problem, but it has not received sufficient attention from the natural language processing community. In this short paper, we present our participation in the English track of SemEval-2022 Task 11: Multilingual Complex Named Entity Recognition. Inspired by the recent advances in pretrained Transformer language models, we propose a simple yet effective Transformer-based baseline for the task. Despite its simplicity, our proposed approach shows competitive results in the leaderboard as we ranked 12 over 30 teams. Our system achieved a macro F1 score of 72.50% on the held-out test set. We have also explored a data augmentation approach using entity linking. While the approach does not improve the final performance, we also discuss it in this paper.

Improving Named Entity Recognition in Bahasa Indonesia with Transformer-Word2Vec-CNN-Attention Model

“…The TWCAM method outperforms the other models, 4. Proposed TWCAM method is compared with others Method F1-Score BiLSTM [18] 75.18 Transformer+W2V [19] 72.50 Transformer+CNN [20] 75.31 Transformer+W2V+CNN [21] 76.45 Transformer+W2V+Attn [22] 78.…”

“…Combining existing resources that fulfill the aim of contribution-centric extraction targets and further annotating additional data to create a large corpus which is made publicly available. Lai [19] proposed Transformer-based approach achieved competitive results in the leaderboard and ranked 12th out of 30 teams. The system achieved a macro F1 score of 72.50% on the held-out test set.…”