@inproceedings{8474f21460564a13b3d41e1a60d99ccc,
title = "A Dataset of Syntactic-Ngrams over Time from a Very Large Corpus of English Books",
abstract = "We created a dataset of syntactic-ngrams (counted dependency-tree fragments) based on a corpus of 3.5 million English books. The dataset includes over 10 billion distinct items covering a wide range of syntactic configurations. It also includes temporal information, facilitating new kinds of research into lexical semantics over time. This paper describes the dataset, the syntactic representation, and the kinds of information provided.",
author = "Yoav Goldberg and Jon Orwant",
note = "Publisher Copyright: {\textcopyright}2013 Association for Computational Linguistics.; 2nd Joint Conference on Lexical and Computational Semantics, SEM 2013 ; Conference date: 13-06-2013 Through 14-06-2013",
year = "2013",
month = jan,
day = "1",
language = "الإنجليزيّة",
series = "SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, Proceedings of the Main Conference and the Shared Task: Semantic Textual SimilaritySEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity",
publisher = "Association for Computational Linguistics (ACL)",
pages = "241--247",
editor = "Mona Diab and Tim Baldwin and Marco Baroni",
booktitle = "SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics, Proceedings of the Main Conference and the Shared Task",
address = "الولايات المتّحدة",
}