arXiv Open Access 2021

Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning

Chiyu Zhang Muhammad Abdul-Mageed
Lihat Sumber

Abstrak

Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit social cues to drive pre-trained representations toward a broad set of concepts useful for a wide class of social meaning tasks. We test our models on $15$ different Twitter datasets for social meaning detection. Our methods achieve $2.34\%$ $F_1$ over a competitive baseline, while outperforming domain-specific language models pre-trained on large datasets. Our methods also excel in few-shot learning: with only $5\%$ of training data (severely few-shot), our methods enable an impressive $68.54\%$ average $F_1$. The methods are also language agnostic, as we show in a zero-shot setting involving six datasets from three different languages.

Topik & Kata Kunci

Penulis (2)

C

Chiyu Zhang

M

Muhammad Abdul-Mageed

Format Sitasi

Zhang, C., Abdul-Mageed, M. (2021). Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning. https://arxiv.org/abs/2108.00356

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓