@inproceedings{450c6730c47e40eca6b8d36e7881856b,
title = "DLS@CU-CORE: A Simple Machine Learning Model of Semantic Textual Similarity",
abstract = "We present a system submitted in the Semantic Textual Similarity (STS) task at the Second Joint Conference on Lexical and Computational Semantics (∗SEM 2013). Given two short text fragments, the goal of the system is to determine their semantic similarity. Our system makes use of three different measures of text similarity: word n-gram overlap, character n-gram overlap and semantic overlap. Using these measures as features, it trains a support vector regression model on SemEval STS 2012 data. This model is then applied on the STS 2013 data to compute textual similarities. Two different selections of training data result in very different performance levels: while a correlation of 0.4135 with gold standards was observed in the official evaluation (ranked 63rd among all systems) for one selection, the other resulted in a correlation of 0.5352 (that would rank 21st). ",
author = "Sultan, {Md Arafat} and Steven Bethard and Tamara Sumner",
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",
language = "English (US)",
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 = "176--180",
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",
}