Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation
Preprint
Abstract
A major obstacle to the wide-spread adoption of neural retrieval models is that they require large supervised training sets to surpass traditional term-based techniques, which are constructed from raw corpora. In this paper, we propose an approach to zero-shot learning for passage retrieval that uses synthetic question generation to close this gap. The question generation system is trained on general domain data, but is applied to documents in the targeted domain. This allows us to create arbitrarily large, yet noisy, question-passage relevance pairs that are domain specific. Furthermore, when this is coupled with a simple hybrid term-neural model, first-stage retrieval performance can be improved further. Empirically, we show that this is an effective strategy for building neural passage retrieval models in the absence of large training corpora. Depending on the domain, this technique can even approach the accuracy of supervised models.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- ColBERT2020
- Context-Aware Term Weighting For First Stage Passage Retrieval2020
- BioBERT: a pre-trained biomedical language representation model for biomedical text miningBioinformatics, 2019
- Billion-Scale Similarity Search with GPUsIEEE Transactions on Big Data, 2019
- Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the UglyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Cross Domain Regularization for Neural Ranking Models using Adversarial Learning2018
- Neural Vector Spaces for Unsupervised Information RetrievalACM Transactions on Information Systems, 2018
- A Neural Click Model for Web Search2016
- Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information RetrievalIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Learning to rank2007