@inproceedings{81f82a758ae34b91a42260923f6ee68c,
title = "Revisiting correlations between intrinsic and extrinsic evaluations of word embeddings",
abstract = "The evaluation of word embeddings has received a considerable amount of attention in recent years, but there have been some debates about whether intrinsic measures can predict the performance of downstream tasks. To investigate this question, this paper presents the first study on the correlation between results of intrinsic evaluation and extrinsic evaluation with Chinese word embeddings. We use word similarity and word analogy as the intrinsic tasks, Named Entity Recognition and Sentiment Classification as the extrinsic tasks. A variety of Chinese word embeddings trained with different corpora and context features are used in the experiments. From the data analysis, we reach some interesting conclusions: there are strong correlations between intrinsic and extrinsic evaluations, and the performance of different tasks can be affected by training corpora and context features to varying degrees.",
keywords = "Extrinsic evaluation, Intrinsic evaluation, Word embedding",
author = "Yuanyuan Qiu and Hongzheng Li and Shen Li and Yingdi Jiang and Renfen Hu and Lijiao Yang",
note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2018.; 17th China National Conference on Computational Linguistics, CCL 2018 and 6th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018 ; Conference date: 19-10-2018 Through 21-10-2018",
year = "2018",
doi = "10.1007/978-3-030-01716-3_18",
language = "English",
isbn = "9783030017156",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "209--221",
editor = "Xiaojie Wang and Ting Liu and Maosong Sun and Zhiyuan Liu and Yang Liu",
booktitle = "Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data - 17th China National Conference, CCL 2018, and 6th International Symposium, NLP-NABD 2018, Proceedings",
address = "Germany",
}