Measuring semantic similarity of words using concept networks
Gábor Recski, Eszter Iklódi, Katalin Pajkossy, András Kornai
In Proceedings of the 1st Workshop on Representation Learning for NLP,
2016
ACLWEB
ACLWEB
We present a state-of-the-art algorithm for measuring the semantic similarity of word pairs using novel combinations of word embeddings, WordNet, and the concept dictionary 4lang. We evaluate our system on the SimLex-999 benchmark data. Our top score of 0.755 is higher than any published system that we are aware of, well beyond the average inter-annotator agreement of 0.67, and close to the 0.78 average correlation between a human rater and the average of all other ratings, suggesting that our system has achieved near-human performance on this benchmark.
Citation
@inproceedings{Recski:2016c
title = "Measuring Semantic Similarity of Words Using Concept Networks",
author = "Recski, G{\'a}bor and
Ikl{\'o}di, Eszter and
Pajkossy, Katalin and
Kornai, Andr{\'a}s",
booktitle = "Proceedings of the 1st Workshop on Representation Learning for {NLP}",
month = aug,
year = "2016",
address = "Berlin, Germany",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/W16-1622",
doi = "10.18653/v1/W16-1622",
pages = "193--200",
}