Learning Dense Representations of Phrases at Scale

TL;DR

This paper introduces DensePhrases, a method for learning dense phrase representations that significantly improves open-domain question answering accuracy and efficiency, enabling fast retrieval and downstream task application.

Contribution

The paper presents a novel approach to learn dense phrase representations from reading comprehension supervision, outperforming previous sparse models and enabling scalable, fast retrieval.

Findings

DensePhrases improves QA accuracy by 15-25% over previous models.

The model processes over 10 questions per second on CPUs.

Dense representations are effective for downstream slot filling tasks.

Abstract

Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019). However, current phrase retrieval models heavily depend on sparse representations and still underperform retriever-reader approaches. In this work, we show for the first time that we can learn dense representations of phrases alone that achieve much stronger performance in open-domain QA. We present an effective method to learn phrase representations from the supervision of reading comprehension tasks, coupled with novel negative sampling methods. We also propose a query-side fine-tuning strategy, which can support transfer learning and reduce the discrepancy between training and inference. On five popular open-domain QA datasets, our model DensePhrases improves over previous phrase retrieval models by 15%-25% absolute accuracy and matches the performance of state-of-the-art retriever-reader models. Our model is easy to parallelize due to pure dense representations and processes more than 10 questions per second on CPUs. Finally, we directly use our pre-indexed dense phrase representations for two slot filling tasks, showing the promise of utilizing DensePhrases as a dense knowledge base for downstream tasks.