Text-to-Text Multi-view Learning for Passage Re-ranking
arXiv:2104.14133
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.
arXiv commentAccepted as short paper in SIGIR 2021
References in corpus (7)
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling
- Passage Re-ranking with BERT
- Document Expansion by Query Prediction
- Multi-Stage Document Ranking with BERT
- Pretrained Transformers for Text Ranking: BERT and Beyond
- Improving Sentence Representations with Consensus Maximisation