AaltoNLP at SemEval-2022 Task 11: Ensembling Task-adaptive Pretrained Transformers for Multilingual Complex NER

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2022

Major/Subject

Mcode

Degree programme

Language

en

Pages

6
1477-1482

Series

SemEval 2022 - 16th International Workshop on Semantic Evaluation, Proceedings of the Workshop

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.

Description

Publisher Copyright: © 2022 Association for Computational Linguistics.

Keywords

Other note

Citation

Pietiläinen, A & Ji, S 2022, AaltoNLP at SemEval-2022 Task 11: Ensembling Task-adaptive Pretrained Transformers for Multilingual Complex NER . in G Emerson, N Schluter, G Stanovsky, R Kumar, A Palmer, N Schneider, S Singh & S Ratan (eds), SemEval 2022 - 16th International Workshop on Semantic Evaluation, Proceedings of the Workshop . Association for Computational Linguistics, pp. 1477-1482, International Workshop on Semantic Evaluation, Seattle, Washington, United States, 14/07/2022 . https://doi.org/10.18653/v1/2022.semeval-1.202