CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NER
This is an incremental study for the NLP community, focusing on improving methods for complex named entity recognition tasks.
The paper compared span-prediction and sequence-labeling approaches for fine-grained named entity recognition, finding that span-prediction performed slightly better on test data and that using a larger XLM RoBERTa model significantly improved performance.
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 Sequence Labeling 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.