Nikhita

@thenewcomer Hi, I am facing a similar problem. The performance is dropping when I using BERT encoders. Please let me know if you managed to fix this problems and get...

Hi, yes I have done all of that and am able to get the ELMo embeddings to work. My question is regarding how exactly they are being used in the...

@j6mes Okay. Considering this example from the file `heuristic_gold_dev_genre_50_2.jsonl` : `{"mutated": "Exercise is bad for heart health.", "original": "Exercise is good for heart health.", "mutation": "substitute_similar", "claim_id": 3518, "original_id": 3517,...

@j6mes Do you mean `pipeline_text` and not `pipeline_evidence`? In the above example, it is already in the form of a list of lists with 2 elements each: page name and...

Thank you!

@j6mes Hi, I have a couple of questions about the data format of your model. In the following example, ``` {"prediction": "correction: Penguin Books revolutionized publishing in the 1940s.", "actual":...

@j6mes I see. So does this mean that both the "actual: correction" field and 'target' field from the above example contain the incorrect, mutated version of the input statement? If...

@j6mes Thank you for replying. I will look into the supervised version. Regarding the `mask_based_correction_reader.py` file, I have the following question regarding the below code snippet: ``` claim_tokens = instance["original_claim"].split()...