Text-to-Text Multi-view Learning for Passage Re-ranking
This work addresses passage re-ranking in NLP, but it is incremental as it builds on existing pretrained models by adding a view.
The paper tackles the problem of single-view learning being inadequate for passage re-ranking by proposing a text-to-text multi-view learning framework that incorporates a text generation view, resulting in improved ranking performance compared to the single-view counterpart.
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 proposed approach is of help to the ranking performance compared to its single-view counterpart. Ablation studies are also reported in the paper.