PA Ph&Tech at SemEval-2022 Task 11: NER Task with Ensemble Embedding from Reinforcement Learning
Qizhi Lin, Changyu Hou, Xiaopeng Wang, Jun Wang, Yixuan Qiao, Peng Jiang, Xiandi Jiang, Benqi Wang, Qifeng Xiao
Abstract
From pretrained contextual embedding to document-level embedding, the selection and construction of embedding have drawn more and more attention in the NER domain in recent research. This paper aims to discuss the performance of ensemble embeddings on complex NER tasks. Enlightened by Wang’s methodology, we try to replicate the dominating power of ensemble models with reinforcement learning optimizor on plain NER tasks to complex ones. Based on the composition of semeval dataset, the performance of the applied model is tested on lower-context, QA, and search query scenarios together with its zero-shot learning ability. Results show that with abundant training data, the model can achieve similar performance on lower-context cases compared to plain NER cases, but can barely transfer the performance to other scenarios in the test phase.- Anthology ID:
- 2022.semeval-1.198
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1444–1447
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.198
- DOI:
- 10.18653/v1/2022.semeval-1.198
- Cite (ACL):
- Qizhi Lin, Changyu Hou, Xiaopeng Wang, Jun Wang, Yixuan Qiao, Peng Jiang, Xiandi Jiang, Benqi Wang, and Qifeng Xiao. 2022. PA Ph&Tech at SemEval-2022 Task 11: NER Task with Ensemble Embedding from Reinforcement Learning. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1444–1447, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- PA Ph&Tech at SemEval-2022 Task 11: NER Task with Ensemble Embedding from Reinforcement Learning (Lin et al., SemEval 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.198.pdf
- Data
- MS MARCO, ORCAS