yevhenkost/cutiesRun28-05-2020-roberta-base-evidenceAlignment

Pretrained model for evidence alignment on cutietestrun28May2020 dataset. The task was binary prediction whether the claim and evidence are relevant to each other. The model was built as a part of CEASystem.

Usage

model = transformers.AutoModelForSequenceClassification.from_pretrained("yevhenkost/cutiesRun28-05-2020-roberta-base-evidenceAlignment")
tokenizer = transformers.AutoTokenizer.from_pretrained("yevhenkost/cutiesRun28-05-2020-roberta-base-evidenceAlignment")

claim_evidence_pairs = [
  ["The water is wet", "The sky is blue"],
["The car crashed", "Driver could not see the road"]
]

tokenized_inputs = tokenizer.batch_encode_plus(
            predict_pairs,
            return_tensors="pt",
            padding=True,
            truncation=True
        )
preds = model(**tokenized_batch_input)

# logits: preds.logits