AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents

TL;DR

AgAsk is an intelligent agent designed to answer farmers' questions by mining scientific agricultural documents, utilizing neural ranking models to improve retrieval accuracy, and providing a deployment architecture for real-world use.

Contribution

This paper introduces a new agricultural question-answering system, a comprehensive test collection, and demonstrates the effectiveness of neural ranking models in this domain.

Findings

Neural rankers outperform traditional models in matching questions to relevant passages.

The provided test collection facilitates further research in scientific document retrieval.

The deployment architecture enables practical use of AgAsk via messaging platforms.

Abstract

Decisions in agriculture are increasingly data-driven; however, valuable agricultural knowledge is often locked away in free-text reports, manuals and journal articles. Specialised search systems are needed that can mine agricultural information to provide relevant answers to users' questions. This paper presents AgAsk -- an agent able to answer natural language agriculture questions by mining scientific documents. We carefully survey and analyse farmers' information needs. On the basis of these needs we release an information retrieval test collection comprising real questions, a large collection of scientific documents split in passages, and ground truth relevance assessments indicating which passages are relevant to each question. We implement and evaluate a number of information retrieval models to answer farmers questions, including two state-of-the-art neural ranking models. We show that neural rankers are highly effective at matching passages to questions in this context. Finally, we propose a deployment architecture for AgAsk that includes a client based on the Telegram messaging platform and retrieval model deployed on commodity hardware. The test collection we provide is intended to stimulate more research in methods to match natural language to answers in scientific documents. While the retrieval models were evaluated in the agriculture domain, they are generalisable and of interest to others working on similar problems. The test collection is available at: \url{https://github.com/ielab/agvaluate}.