Learning Numeral Embedding

Citations Over TimeTop 10% of 2020 papers

Abstract

Word embedding is an essential building block for deep learning methods for natural language processing. Although word embedding has been extensively studied over the years, the problem of how to effectively embed numerals, a special subset of words, is still underexplored. Existing word embedding methods do not learn numeral embeddings well because there are an infinite number of numerals and their individual appearances in training corpora are highly scarce. In this paper, we propose two novel numeral embedding methods that can handle the out-of-vocabulary (OOV) problem for numerals. We first induce a finite set of prototype numerals using either a selforganizing map or a Gaussian mixture model. We then represent the embedding of a numeral as a weighted average of the prototype number embeddings. Numeral embeddings represented in this manner can be plugged into existing word embedding learning approaches such as skip-gram for training. We evaluated our methods and showed its effectiveness on four intrinsic and extrinsic tasks: word similarity, embedding numeracy, numeral prediction, and sequence labeling.

Related Papers

• → How to Generate a Good Word Embedding(2016)316 cited
• → Computer Program to Aid in the Selection and Evaluation of Vocabularies for Word Recognizers(1963)
• → NMT Multi-Sense Embeddings per Word(2019)
• → Multi-Sense Embeddings per Word(2020)
• → Dual embedding with input embedding and output embedding for better word representation(2022)