Towards Robust Neural Retrieval Models with Synthetic Pre-Training

Abstract

Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to standard supervised learning settings, where they have outperformed traditional term matching baselines. We conduct in-domain and out-of-domain evaluations of neural IR, and seek to improve its robustness across different scenarios, including zero-shot settings. We show that synthetic training examples generated using a sequence-to-sequence generator can be effective towards this goal: in our experiments, pre-training with synthetic examples improves retrieval performance in both in-domain and out-of-domain evaluation on five different test sets.

References in corpus (5)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• REALM: Retrieval-Augmented Language Model Pre-Training
• Pre-training Tasks for Embedding-based Large-scale Retrieval
• End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems
• Multi-Stage Pre-training for Low-Resource Domain Adaptation