Abstract
This paper summarizes the CLaC submission for the MultiCoNER 2 task which concerns the recognition of complex, fine-grained named entities. We compare two popular approaches for NER, namely SequenceLabeling and Span Prediction. We find that our best Span Prediction system performs slightly better than our best Sequence Labeling system on test data. Moreover, we find that using the larger version of XLM RoBERTa significantly improves performance. Post-competition experiments show that Span Prediction and Sequence Labeling approaches improve when they use special input tokens ([s] and [/s]) of XLM-RoBERTa. The code for training all models, preprocessing, and post-processing is available at https://github.com/harshshredding/semeval2023-multiconer-paper.- Anthology ID:
- 2023.semeval-1.215
- Volume:
- Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1558–1561
- Language:
- URL:
- https://aclanthology.org/2023.semeval-1.215
- DOI:
- 10.18653/v1/2023.semeval-1.215
- Cite (ACL):
- Harsh Verma and Sabine Bergler. 2023. CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling Approaches for NER. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1558–1561, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling Approaches for NER (Verma & Bergler, SemEval 2023)
- PDF:
- https://preview.aclanthology.org/landing_page/2023.semeval-1.215.pdf