T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition
Asahi Ushio, José Camacho-Collados · 2021
Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER).In this paper, we present T-NER 1 (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning.In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER.Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers.We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and crosslingual performance across the datasets.The results from our initial experiments show that in-domain performance is generally competitive across datasets.However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if finetuned on a combined dataset.To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub 2