A Generative Approach to Question Answering
This addresses the problem of generating accurate and readable answers in question answering for NLP applications, representing an incremental advancement.
The paper tackles generative question answering by framing it as a generative task with an encoder-decoder model, using copying mechanisms and coverage vectors to reduce errors like fact retention and repetitions, achieving superior results on MS-MARCO with improvements in correctness and readability.
Question Answering has come a long way from answer sentence selection, relational QA to reading and comprehension. We shift our attention to generative question answering (gQA) by which we facilitate machine to read passages and answer questions by learning to generate the answers. We frame the problem as a generative task where the encoder being a network that models the relationship between question and passage and encoding them to a vector thus facilitating the decoder to directly form an abstraction of the answer. Not being able to retain facts and making repetitions are common mistakes that affect the overall legibility of answers. To counter these issues, we employ copying mechanism and maintenance of coverage vector in our model respectively. Our results on MS-MARCO demonstrate it's superiority over baselines and we also show qualitative examples where we improved in terms of correctness and readability