TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Part-Of-Speech Tagging	Social media	PretRand	Accuracy	91.46	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/joint-learning-of-pre-trained-and-random/part-of-speech-tagging-on-social-media)](https://paperswithcode.com/sota/part-of-speech-tagging-on-social-media?p=joint-learning-of-pre-trained-and-random)`

Joint Learning of Pre-Trained and Random Units for Domain Adaptation in Part-of-Speech Tagging

NAACL 2019 · Sara Meftah, Youssef Tamaazousti, Nasredine Semmar, Hassane Essafi, Fatiha Sadat ·

Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of adapting to new domains, pre-trained units struggle with learning uncommon target-specific patterns. In this paper, we propose to augment the target-network with normalised, weighted and randomly initialised units that beget a better adaptation while maintaining the valuable source knowledge. Our experiments on POS tagging of social media texts (Tweets domain) demonstrate that our method achieves state-of-the-art performances on 3 commonly used datasets.