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
Recommended Citation
Yao, Shibo; Yu, Dantong; and Xiao, Keli, "Enhancing domain word embedding via latent semantic imputation" (2019). Faculty Publications. 7442.
https://digitalcommons.njit.edu/fac_pubs/7442
