Improving Distributional Similarity with Lessons Learned from Word Embeddings

Omer Levy, Yoav Goldberg, Ido Dagan

Research output: Contribution to journalArticlepeer-review


Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these modifications can be transferred to traditional distributional models, yielding similar gains. In contrast to prior reports, we observe mostly local or insignificant performance differences between the methods, with no global advantage to any single approach over the others.
Original languageEnglish
Pages (from-to)211-225
Number of pages15
JournalTransactions of the Association for Computational Linguistics
StatePublished - 2015
Externally publishedYes


Dive into the research topics of 'Improving Distributional Similarity with Lessons Learned from Word Embeddings'. Together they form a unique fingerprint.

Cite this