Text-to-Text Multi-view Learning for Passage Re-ranking

TL;DR

This paper introduces a multi-view learning framework for passage re-ranking that incorporates both ranking and text generation views, improving performance over traditional single-view models.

Contribution

It proposes a novel text-to-text multi-view learning approach that integrates text generation into passage ranking models, enhancing their effectiveness.

Findings

Improved ranking performance with multi-view learning

Effective integration of text generation view

Ablation studies confirm the contribution of each view

Abstract

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.