Text-to-Text Multi-view Learning for Passage Re-ranking. (arXiv:2104.14133v2 [cs.IR] UPDATED)

Recently, much progress in natural language processing has been driven by
deep contextualized representations pretrained on large corpora. Typically, the
fine-tuning on these pretrained models for a specific downstream task is based
on single-view learning, which is however inadequate as a sentence can be
interpreted differently from different perspectives. Therefore, in this work,
we propose a text-to-text multi-view learning framework by incorporating an
additional view -- the text generation view -- into a typical single-view
passage ranking model. Empirically, the …

arxiv learning ranking text