This repository contains the code and data of the paper "Enhancing the Numeracy of Word Embeddings: a Linear Algebraic Perspective"
The video introduction of the paper
How to run experiments?
Put embeddings in data/embs/
dir to run main.py
(pre-trained embeddings are described in the paper)
Supplementary Materials
sub_mag_exp_data (password: ht8c)
How to cite?
If you find the paper or the code useful, please cite the paper.
@InProceedings{10.1007/978-3-030-60450-9_14,
author="Ren, Yuanhang
and Du, Ye",
editor="Zhu, Xiaodan
and Zhang, Min
and Hong, Yu
and He, Ruifang",
title="Enhancing the Numeracy of Word Embeddings: A Linear Algebraic Perspective",
booktitle="Natural Language Processing and Chinese Computing",
year="2020",
publisher="Springer International Publishing",
address="Cham",
pages="170--178",
abstract="To reason over the embeddings of numbers, they should capture numeracy information. In this work, we consider the magnitude aspect of numeracy information. We could find a vector in a high dimensional space and a subspace of original space. After projecting the original embeddings of numbers onto that vector or subspace, the magnitude information could be significantly enhanced. Therefore, this paper proposes a new angle to study numeracy of word embeddings, which is interpretable and has nice mathematical formulations.",
isbn="978-3-030-60450-9"
}