CLDec 14, 2022
VTCC-NLP at NL4Opt competition subtask 1: An Ensemble Pre-trained language models for Named Entity Recognition
arXiv:2212.07219v18 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis
This work addresses named entity recognition for optimization problem datasets, but it is incremental as it combines existing models without introducing a new paradigm.
The paper tackled named entity recognition in the NL4Opt competition by combining three pre-trained language models (XLM-R, BART, and DeBERTa-V3) for contextualized embeddings, achieving a 92.9% F1 score on the test set and ranking 5th on the leaderboard.
We propose a combined three pre-trained language models (XLM-R, BART, and DeBERTa-V3) as an empower of contextualized embedding for named entity recognition. Our model achieves a 92.9% F1 score on the test set and ranks 5th on the leaderboard at NL4Opt competition subtask 1.