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

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1438 - 1443 July 14-15, 2022 ©2022 Association for Computational Linguistics LMN at SemEval-2022 Task 11: A Transformer-based System for English Named Entity Recognition Ngoc Minh Lai Van Ho Middle School nl834771@gmail.com Abstract Processing complex and ambiguous named en- tities 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: Mul- tilingual Complex Named Entity Recognition. Inspired by the recent advances in pretrained Transformer language models, we propose a simple yet effective Transformer-based base- line 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 us- ing entity linking. While the approach does not improve the final performance, we also discuss it in this paper. 1 Introduction Recognizing complex named entities (NEs) is a challenging research problem, but it has not re- ceived sufficient attention from the natural lan- guage processing community (Meng et al., 2021a; Fetahu et al., 2021). Complex NEs can be com- plex noun phrases (e.g., National Baseball Hall of Fame and Museum), gerunds (e.g., Saving Private Ryan), infinitives (e.g., To Build a Fire), or even full clauses (e.g., I Capture The Castle). This am- biguity makes it difficult to recognize them based on their context (Aguilar et al., 2017; Luken et al., 2018; Hanselowski et al., 2018). In this paper, we describe our participation in the English track of SemEval-2022 Task 11: Multilin- gual Complex Named Entity Recognition (Malmasi et al., 2022a,b). Inspired by the recent success of Transformer-based pre-trained language models in many NLP tasks (Devlin et al., 2019; Joshi et al., 2019; Lai et al., 2019; Joshi et al., 2020; Tran et al., 2020; Yu et al., 2020; Wen et al., 2021; Lai et al., 2021; Monaikul et al., 2021), we propose a simple but effective Transformer-based baseline for the task. Despite its simplicity, our proposed approach shows promising results: the official ranking indi- cated that our system achieved a macro F1 score of 72.50% on the test set and ranked 12th out of 30 teams. 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. In the following sections, we first describe the related work in Section 2 and the proposed method in Section 3. We then describe the experiments and their results in Section 4. Finally, Section 5 concludes this work and discusses potential future research directions. 2 Related Work Many previous named entity recognition (NER) methods are based on the sequence labeling ap- proach (Collobert et al., 2011; Ma and Hovy, 2016; Lample et al., 2016; Chiu and Nichols, 2016; Lee et al., 2019; Yang …

Content truncated to 500 words