You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Our models are intended for academic use only. If you are not affiliated with an academic institution, please provide a rationale for using our models. Please allow us a few business days to manually review subscriptions.

Model Card

Model Description

This is an xlm-roberta-large model finetuned on English training data labelled with the 10 major level codes from the LiSST thesaurus:

Demographics: DEMOGRAPHY, LIFE EVENTS, IDENTITY
Environment: ENVIRONMENT (including HOME)
Health: HEALTH & CARE
Work: WORK & EMPLOYMENT (including TRAINING)
Education: EDUCATION & QUALIFICATION
Network: FAMILY & SOCIAL NETWORK
Values: ATTITUDES, VALUES
Policy: PUBLIC POLICY
Time use: TIME USE, LEISURE
Income: INCOME AND CONSUMPTION

How to Use the Model

from transformers import AutoTokenizer, pipeline

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-large")
pipe = pipeline(
    model="poltextlab/ontolisst_major_v1_xlm-roberta-large_8_5e-06_128",
    task="text-classification",
    tokenizer=tokenizer,
    use_fast=False,
    token="<your_hf_read_only_token>"
)

text = "Apart from yourself (and your husband/wife/partner), does anyone else living in your household make a contribution towards the cost of the accommodation?
pipe(text)

Gated Access

This model requires gated access. You must pass the token parameter when loading the model. In earlier versions of the Transformers package, you may need to use the use_auth_token parameter instead.

Model Performance

The model was evaluated on a test set of 1,627 English examples.

Accuracy: 0.82
Precision: 0.82
Recall: 0.82
Weighted Average F1-score: 0.82

Classification Report

Label	Precision	Recall	F1-score	Support
1 (Demographics)	0.70	0.52	0.60	117
2 (Environment)	0.79	0.72	0.75	109
3 (Health)	0.89	0.94	0.92	679
4 (Work)	0.83	0.84	0.84	127
5 (Education)	0.81	0.83	0.82	111
6 (Network)	0.77	0.87	0.82	241
7 (Values)	0.72	0.70	0.71	138
8 (Policy)	0.89	0.31	0.46	26
9 (Time use)	0.75	0.26	0.39	23
10 (Income)	0.68	0.71	0.70	56

Downloads last month: 1,334

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support