Questions
- A trained transformer model can answer any question. (True/False)
- Question-answering requires no further research. It is perfect as it is. (True/False)
- Named Entity Recognition (NER) can provide useful information when looking for meaningful questions. (True/False)
- Semantic Role Labeling (SRL) is useless when preparing questions. (True/False)
- A question generator is an excellent way to produce questions. (True/False)
- Implementing question answering requires careful project management. (True/False)
- ELECTRA models have the same architecture as GPT-2. (True/False)
- ELECTRA models have the same architecture as BERT but are trained as discriminators. (True/False)
- NER can recognize a location and label it as
I-LOC
. (True/False) - NER can recognize a person and label that person as
I-PER
. (True/False)