Enhancing domain word embedding via latent semantic imputation

Document Type

Conference Proceeding

Publication Date

7-25-2019

Abstract

We present a novel method named Latent Semantic Imputation (LSI) to transfer external knowledge into semantic space for enhancing word embedding. The method integrates graph theory to extract the latent manifold structure of the entities in the affinity space and leverages non-negative least squares with standard simplex constraints and power iteration method to derive spectral embeddings. It provides an effective and efficient approach to combining entity representations defined in different Euclidean spaces. Specifically, our approach generates and imputes reliable embedding vectors for low-frequency words in the semantic space and benefits downstream language tasks that depend on word embedding. We conduct comprehensive experiments on a carefully designed classification problem and language modeling and demonstrate the superiority of the enhanced embedding via LSI over several well-known benchmark embeddings. We also confirm the consistency of the results under different parameter settings of our method.

Identifier

85071148237 (Scopus)

ISBN

[9781450362016]

Publication Title

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

External Full Text Location

https://doi.org/10.1145/3292500.3330926

First Page

557

Last Page

565

This document is currently not available here.

Share

COinS