TREC 2023 Tip-of-the-Tongue dataset

Description

The Tip-of-the-Tongue (ToT) Track focuses on the known-item identification task where the searcher has previously experienced or consumed the item (e.g., a movie) but cannot recall a reliable identifier (i.e., It's on the tip of my tongue...). Unlike traditional ad-hoc keyword-based search, these information requests tend to be natural-language, verbose, and complex containing a wide variety of search strategies such as multi-hop reasoning, and frequently express uncertainty and suffer from false memories.

Resources

Name Format Description Link
47 2023-qrels.txt https://trec.nist.gov/data/tot/2023-qrels.txt
57 2023-train.zip https://trec.nist.gov/data/tot/2023-train.zip
57 2023-dev.zip https://trec.nist.gov/data/tot/2023-dev.zip
57 2023-test.zip https://trec.nist.gov/data/tot/2023-test.zip
0 This corpus is distributed by the track coordinators via Zenodo https://zenodo.org/records/11185090/files/corpus.jsonl.zip?download=1

Tags

  • trec-text-retrieval-conference

Topics

Categories