destonedbob/nusiss-election-project-aspect-seq2seq-model-facebook-bart-large

Finetuned model for a university project to identify aspect relating to a specific entity within sentence (Possible entities Trump, Kamala, Others).

Input test format: entity of interest: <entity> [SEP] <sentence> For Others, entity should be "neither trump nor kamala"

model_name = 'destonedbob/nusiss-election-project-aspect-seq2seq-model-facebook-bart-large'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
pipeline = pipeline('text2text-generation', model=model, tokenizer=tokenizer)

df = pd.DataFrame([
    'entity of interest: trump [SEP] I think Trump is a criminal',
    'entity of interest: trump [SEP] I think Trump has lousy ideas when it comes to the economy',
    'entity of interest: kamala [SEP] Kamala cannot run a country, all she does is laugh', 
    'entity of interest: neither trump nor kamala [SEP] Biden did not make any sense during his debate'
    ], columns=['sentence'])

pipeline(df.sentence.tolist(), batch_size=2)