Finding the Needle in the Haystack: How to Train a Dense Passage Retriever

Author(s): Thilina Rajapakse

Originally published on Towards AI.

Let’s see how we can train a model to perform dense-passage retrieval with Transformer models using Simple Transformers.

Photo by matthew Feeney on Unsplash

Passage retrieval is a conceptually simple task where a system has to retrieve the most relevant passage(s) given an input query. Open-domain question answering is a common use case of passage retrieval. Here, the system has access to a large corpus of candidate contexts (passages that may contain the answer to the question) and is tasked with retrieving the passage or passages that are most relevant to the question — the most relevant passage or passages being the passages most likely to contain the information necessary to answer the question.

For example, consider a retrieval system… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI