Word Semantic Representations using Bayesian Probabilistic Tensor Factorization

By Jingwei Zhang, Jeremy Salwen, Michael R. Glass, Alfio Massimiliano Gliozzo. 2014

47 citations recorded by the source corpus.

Many forms of word relatedness have been developed, providing different perspectives on word similarity. We introduce a Bayesian probabilistic tensor factorization model for synthesizing a single word vector representation and per-perspective linear transformations from any number of word similarity matrices. The resulting word vectors, when combined with the per-perspective linear transformation, approximately recreate while also regularizing and generalizing, each word similarity perspective. Our method can combine manually created semantic resources with neural word embeddings to separate synonyms and antonyms, and is capable of generalizing to words outside the vocabulary of any particular perspective. We evaluated the word embeddings with GRE antonym questions, the result achieves the state-ofthe-art performance.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Informing Unsupervised Pretraining with External Linguistic Knowledge (2019, methodology): “4 We obtain the set of constraints C for the L LRC term from the body of previous work on semantic specialization of static word embeddings (Zhang et al., 2014; Vuli´c et al., 2018; Ponti et al., 2018).”
Revisiting Word Embedding for Contrasting Meaning (2015, methodology): “…0.77 Encarta MRLSA (Yih et al., 2012) 0.87 0.82 0.84 0.82 0.74 0.78 WordNet lookup (Yih et al., 2012) 0.40 0.40 0.40 0.42 0.41 0.42 WordNet lookup (Zhang et al., 2014) 0.93 0.32 0.48 0.95 0.33 0.49 WordNet lookup 0.97 0.37 0.54 0.97 0.41 0.58 Roget lookup (Zhang et al., 2014) 1.00 0.35 0.52 0.99…”