Downloads · 30 days
14
1% of all-time downloads
lucy3/roberta_social_roles
roberta_social_roles is a token classification model from lucy3. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
This model is a token classifier that extracts social roles from explicit expressions of self-identification in sentences, e.g. I am a designer, entrepreneur, and mother.
Downloads · 30 days
14
1% of all-time downloads
All-time downloads
2.2K
Public
Repo size
2 GB
Likes
0
Public
Click a slice to open those files.
.pt993 MB · 67%
From the Hugging Face model README
This model is a token classifier that extracts social roles from explicit expressions of self-identification in sentences, e.g. I am a designer, entrepreneur, and mother.
We continue pretraining RoBERTa-base for 10 epochs on individuals' about pages, which is a subset of Common Crawl and can be accessed here.
Then, we finetuned on hand-annotated token-level labels as described in this paper. We use a train-dev-test split of 600/200/200 labeled sentences.
Our definition of "roles" or "occupations" on about pages is any singular noun referring to the subject of the bio. The roles and occupations can be ones that the subject actively participated in the past, e.g. Throughout my life I have been a teacher, a startup founder, and a seashell collector.
Subject of the about page
Positive examples of self-identification
Negative examples
Language(s) (NLP): English
License: Apache 2.0
We use tagged social roles in web pages to assess the social impact of LLM pretraining data curation decisions. Text linked to descriptions of their creators can also facilitate other areas of research, including self-presentation and language variation.
On our test set, we achieve a precision score of 0.856, recall score of 0.945, and F1 score of 0.898.
@misc{lucy2024aboutme,
title={AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters},
author={Li Lucy and Suchin Gururangan and Luca Soldaini and Emma Strubell and David Bamman and Lauren Klein and Jesse Dodge},
year={2024},
eprint={2401.06408},
archivePrefix={arXiv},
primaryClass={cs.CL}
}