{
 "id": "amazon/AmazonQAC",
 "owner": "amazon",
 "name": "AmazonQAC",
 "downloads": 767,
 "likes": 19,
 "last_modified": "2024-11-19T18:37:25.000Z",
 "stated_licence": "cdla-permissive-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation",
  "text2text-generation",
  "text-retrieval"
 ],
 "citation": "@inproceedings{everaert-etal-2024-amazonqac,\n    title = \"{A}mazon{QAC}: A Large-Scale, Naturalistic Query Autocomplete Dataset\",\n    author = \"Everaert, Dante  and\n      Patki, Rohit  and\n      Zheng, Tianqi  and\n      Potts, Christopher\",\n    editor = \"Dernoncourt, Franck  and\n      Preo{\\c{t}}iuc-Pietro, Daniel  and\n      Shimorina, Anastasia\",\n    booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, US\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.emnlp-industry.78\",\n    pages = \"1046--1055\",\n    abstract = \"Query Autocomplete (QAC) is a critical feature in modern search engines, facilitating user interaction by predicting search queries based on input prefixes. Despite its widespread adoption, the absence of large-scale, realistic datasets has hindered advancements in QAC system development. This paper addresses this gap by introducing AmazonQAC, a new QAC dataset sourced from Amazon Search logs, comprising 395M samples. The dataset includes actual sequences of user-typed prefixes leading to final search terms, as well as session IDs and timestamps that support modeling the context-dependent aspects of QAC. We assess Prefix Trees, semantic retrieval, and Large Language Models (LLMs) with and without finetuning. We find that finetuned LLMs perform best, particularly when incorporating ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "975cbfac4623ffb054c59631e06e39d0831e47fb",
 "stated_evidence": "https://huggingface.co/datasets/amazon/AmazonQAC/blob/975cbfac4623ffb054c59631e06e39d0831e47fb/README.md",
 "file_evidence": "https://huggingface.co/datasets/amazon/AmazonQAC/tree/975cbfac4623ffb054c59631e06e39d0831e47fb",
 "card_nc": false
}