The tale of two MS MARCO -- and their unfair comparisons

April 25, 2023 Β· Declared Dead Β· πŸ› Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Carlos Lassance, StΓ©phane Clinchant arXiv ID 2304.12904 Category cs.IR: Information Retrieval Citations 14 Venue Annual International ACM SIGIR Conference on Research and Development in Information Retrieval Last Checked 3 months ago
Abstract
The MS MARCO-passage dataset has been the main large-scale dataset open to the IR community and it has fostered successfully the development of novel neural retrieval models over the years. But, it turns out that two different corpora of MS MARCO are used in the literature, the official one and a second one where passages were augmented with titles, mostly due to the introduction of the Tevatron code base. However, the addition of titles actually leaks relevance information, while breaking the original guidelines of the MS MARCO-passage dataset. In this work, we investigate the differences between the two corpora and demonstrate empirically that they make a significant difference when evaluating a new method. In other words, we show that if a paper does not properly report which version is used, reproducing fairly its results is basically impossible. Furthermore, given the current status of reviewing, where monitoring state-of-the-art results is of great importance, having two different versions of a dataset is a large problem. This is why this paper aims to report the importance of this issue so that researchers can be made aware of this problem and appropriately report their results.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted