0
Improving Distributional Similarity with Lessons Learned from Word Embeddings
Omer Levy, Yoav Goldberg, Ido Dagan, 2015. Transactions of the Association for Computational Linguistics.
Shows that much of the advantage of neural word embeddings comes from design choices and hyperparameters, which can be carried over to traditional count-based models with similar gains.
What it's used for here
The inductive methods survey uses its PPMI-SVD embeddings as a stable choice for a small corpus in test N5.
Cited by on this site 1 record
1 methods surveys
SRCInductive methods
Cite it
Levy, O., Goldberg, Y., & Dagan, I. (2015). Improving Distributional Similarity with Lessons Learned from Word Embeddings. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00134
@article{levy2015improving,
author = {Levy, Omer and Goldberg, Yoav and Dagan, Ido},
title = {Improving Distributional Similarity with Lessons Learned from Word Embeddings},
journal = {Transactions of the Association for Computational Linguistics},
year = {2015},
doi = {10.1162/tacl_a_00134},
url = {https://doi.org/10.1162/tacl_a_00134}
}TY - JOUR TI - Improving Distributional Similarity with Lessons Learned from Word Embeddings AU - Levy, Omer AU - Goldberg, Yoav AU - Dagan, Ido PY - 2015 JO - Transactions of the Association for Computational Linguistics DO - 10.1162/tacl_a_00134 UR - https://doi.org/10.1162/tacl_a_00134 ER -
Levy, Omer et al.. “Improving Distributional Similarity with Lessons Learned from Word Embeddings.” Transactions of the Association for Computational Linguistics (2015). https://doi.org/10.1162/tacl_a_00134.