Exploring Answer Information Methods for Question Generation with Transformers
This work addresses question generation for NLP applications, but it is incremental as it adapts existing methods from RNN models to Transformers.
The paper tackled the problem of incorporating target answer information into question generation with Transformers, finding that answer prompting achieved the best performance on metrics like ROUGE and METEOR, with a custom metric showing how many generated questions retained the original answer.
There has been a lot of work in question generation where different methods to provide target answers as input, have been employed. This experimentation has been mostly carried out for RNN based models. We use three different methods and their combinations for incorporating answer information and explore their effect on several automatic evaluation metrics. The methods that are used are answer prompting, using a custom product method using answer embeddings and encoder outputs, choosing sentences from the input paragraph that have answer related information, and using a separate cross-attention attention block in the decoder which attends to the answer. We observe that answer prompting without any additional modes obtains the best scores across rouge, meteor scores. Additionally, we use a custom metric to calculate how many of the generated questions have the same answer, as the answer which is used to generate them.