BME HLT | Measuring semantic similarity of words using concept networks

Measuring semantic similarity of words using concept networks

2016

Link to paper

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,
  author    = {Recski, G\'{a}bor  and  Ikl\'{o}di, Eszter  and  Pajkossy, Katalin  and  Kornai, Andras},
  title     = {Measuring Semantic Similarity of Words Using Concept Networks},
  booktitle = {Proceedings of the 1st Workshop on Representation Learning for NLP},
  year      = {2016},
  address   = {Berlin, Germany},
  publisher = {Association for Computational Linguistics},
  pages     = {193--200}
}