Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison
Abstract
We investigate the problem of inducing word embeddings that are tailored for a particular bilexical relation. Our learning algorithm takes an existing lexical vector space and compresses it such that the resulting word embeddings are good predictors for a target bilexical relation. In experiments we show that task-specific embeddings can benefit both the quality and efficiency in lexical prediction tasks.
Cite
Text
Madhyastha et al. "Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison." International Conference on Learning Representations, 2015.Markdown
[Madhyastha et al. "Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison." International Conference on Learning Representations, 2015.](https://mlanthology.org/iclr/2015/madhyastha2015iclr-tailoring/)BibTeX
@inproceedings{madhyastha2015iclr-tailoring,
title = {{Tailoring Word Embeddings for Bilexical Predictions: An Experimental Comparison}},
author = {Madhyastha, Pranava Swaroop and Carreras, Xavier and Quattoni, Ariadna},
booktitle = {International Conference on Learning Representations},
year = {2015},
url = {https://mlanthology.org/iclr/2015/madhyastha2015iclr-tailoring/}
}