Abstract
The current natural language processing is strongly focused on raising accuracy. The progress comes at a cost of super-heavy models with hundreds of millions or even billions of parameters. However, simple syntactic tasks such as part-of-speech (POS) tagging, dependency parsing or named entity recognition (NER) do not require the largest models to achieve acceptable results. In line with this assumption we try to minimize the size of the model that jointly performs all three tasks. We introduce ComboNER: a lightweight tool, orders of magnitude smaller than state-of-the-art transformers. It is based on pre-trained subword embeddings and recurrent neural network architecture. ComboNER operates on Polish language data. The model has outputs for POS tagging, dependency parsing and NER. Our paper contains some insights from fine-tuning of the model and reports its overall results.- Anthology ID:
- 2021.ranlp-1.169
- Volume:
- Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
- Month:
- September
- Year:
- 2021
- Address:
- Held Online
- Venue:
- RANLP
- SIG:
- Publisher:
- INCOMA Ltd.
- Note:
- Pages:
- 1508–1514
- Language:
- URL:
- https://aclanthology.org/2021.ranlp-1.169
- DOI:
- Cite (ACL):
- Aleksander Wawer. 2021. ComboNER: A Lightweight All-In-One POS Tagger, Dependency Parser and NER. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1508–1514, Held Online. INCOMA Ltd..
- Cite (Informal):
- ComboNER: A Lightweight All-In-One POS Tagger, Dependency Parser and NER (Wawer, RANLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.ranlp-1.169.pdf