@inproceedings{15e05d0c76d841d29e098d71d3ff9141,
title = "CompanyName2Vec: Company Entity Matching based on Job Ads",
abstract = "Entity Matching is an essential part of all real-world systems that take in structured and unstructured data coming from different sources. Typically no common key is available for connecting records. Massive data cleaning and integration processes require completion before any data analytics, or further processing can be performed. Although record linkage is frequently regarded as a somewhat tedious but necessary step, it reveals valuable insights, supports data visualization, and guides further analytic approaches to the data. Here, we focus on organization entity matching. We introduce CompanyName2Vec, a novel algorithm to solve company entity matching (CEM) using a neural network model to learn company name semantics from a job ad corpus, without relying on any information on the matched company besides its name. Based on a real-world data, we show that CompanyName2Vec outperforms other evaluated methods and solves the CEM challenge with an average success rate of 89.3%.",
keywords = "CompanyName2Vec, Entity Matching, LSTM, Organization Name Matching",
author = "Ran Ziv and Ilan Gronau and Michael Fire",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022 ; Conference date: 13-10-2022 Through 16-10-2022",
year = "2022",
month = jan,
day = "1",
doi = "10.1109/DSAA54385.2022.10032350",
language = "English",
series = "Proceedings - 2022 IEEE 9th International Conference on Data Science and Advanced Analytics, DSAA 2022",
publisher = "Institute of Electrical and Electronics Engineers",
editor = "Huang, {Joshua Zhexue} and Yi Pan and Barbara Hammer and Khan, {Muhammad Khurram} and Xing Xie and Laizhong Cui and Yulin He",
booktitle = "Proceedings - 2022 IEEE 9th International Conference on Data Science and Advanced Analytics, DSAA 2022",
address = "United States",
}