Targeted Sentiment Analysis in News Headlines

BERT classifier fine-tuned in a news headlines dataset annotated for target polarity.

(details to be published)

Examples

Input is as follows

Headline [SEP] Target

where headline is the news title and target is an entity present in the headline.

Try

Alberto Fernández: "El gobierno de Macri fue un desastre" [SEP] Macri (should be NEG)

and

Alberto Fernández: "El gobierno de Macri fue un desastre" [SEP] Alberto Fernández (POS or NEU)

Downloads last month: 14

Safetensors

Model size

110M params

Tensor type

I64

F32

Inference Examples

Text Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.