How Deep is your Learning: the DL-HARD Annotated Deep Learning Dataset

TL;DR

DL-HARD is a new annotated dataset that enhances the evaluation of neural ranking models on complex topics by providing detailed annotations and identifying challenging queries, thereby fostering research in this area.

Contribution

It introduces DL-HARD, a richly annotated dataset built on TREC DL topics, with a framework for identifying challenging queries to improve neural ranking research.

Findings

Substantial differences in system rankings on DL-HARD

DL-HARD reveals more challenging queries for neural models

Enhanced evaluation metrics for complex topics

Abstract

Deep Learning Hard (DL-HARD) is a new annotated dataset designed to more effectively evaluate neural ranking models on complex topics. It builds on TREC Deep Learning (DL) topics by extensively annotating them with question intent categories, answer types, wikified entities, topic categories, and result type metadata from a commercial web search engine. Based on this data, we introduce a framework for identifying challenging queries. DL-HARD contains fifty topics from the official DL 2019/2020 evaluation benchmark, half of which are newly and independently assessed. We perform experiments using the official submitted runs to DL on DL-HARD and find substantial differences in metrics and the ranking of participating systems. Overall, DL-HARD is a new resource that promotes research on neural ranking methods by focusing on challenging and complex topics.