Abstract
This paper presents the system description of team AaltoNLP for SemEval-2022 shared task 11: MultiCoNER. Transformer-based models have produced high scores on standard Named Entity Recognition (NER) tasks. However, accuracy on complex named entities is still low. Complex and ambiguous named entities have been identified as a major error source in NER tasks. The shared task is about multilingual complex named entity recognition. In this paper, we describe an ensemble approach, which increases accuracy across all tested languages. The system ensembles output from multiple same architecture task-adaptive pretrained transformers trained with different random seeds. We notice a large discrepancy between performance on development and test data. Model selection based on limited development data may not yield optimal results on large test data sets.- Anthology ID:
- 2022.semeval-1.202
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Guy Emerson, Natalie Schluter, Gabriel Stanovsky, Ritesh Kumar, Alexis Palmer, Nathan Schneider, Siddharth Singh, Shyam Ratan
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1477–1482
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.202
- DOI:
- 10.18653/v1/2022.semeval-1.202
- Cite (ACL):
- Aapo Pietiläinen and Shaoxiong Ji. 2022. AaltoNLP at SemEval-2022 Task 11: Ensembling Task-adaptive Pretrained Transformers for Multilingual Complex NER. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1477–1482, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- AaltoNLP at SemEval-2022 Task 11: Ensembling Task-adaptive Pretrained Transformers for Multilingual Complex NER (Pietiläinen & Ji, SemEval 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2022.semeval-1.202.pdf
- Data
- MultiCoNER