PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN

07/05/2022
by   Pan Du, et al.
0

Beyond topical relevance, passage ranking for open-domain factoid question answering also requires a passage to contain an answer (answerability). While a few recent studies have incorporated some reading capability into a ranker to account for answerability, the ranker is still hindered by the noisy nature of the training data typically available in this area, which considers any passage containing an answer entity as a positive sample. However, the answer entity in a passage is not necessarily mentioned in relation with the given question. To address the problem, we propose an approach called PReGAN for Passage Reranking based on Generative Adversarial Neural networks, which incorporates a discriminator on answerability, in addition to a discriminator on topical relevance. The goal is to force the generator to rank higher a passage that is topically relevant and contains an answer. Experiments on five public datasets show that PReGAN can better rank appropriate passages, which in turn, boosts the effectiveness of QA systems, and outperforms the existing approaches without using external data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset