Unsupervised POS Induction with Word Embeddings

Abstract

Unsupervised word embeddings have been shown to be valuable as features in supervised learning problems; however, their role in unsupervised problems has been less thoroughly explored. In this paper, we show that embeddings can likewise add value to the problem of unsupervised POS induction. In two representative models of POS induction, we replace multinomial distributions over the vocabulary with multivariate Gaussian distributions over word embeddings and observe consistent improvements in eight languages. We also analyze the effect of various choices while inducing word embeddings on "downstream" POS induction results.

NAACL 2015

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (6)

• A Tutorial on Deep Latent Variable Models of Natural Language
• Deep Semantic Dictionary Learning for Multi-label Image Classification
• Unsupervised Neural Hidden Markov Models
• Unsupervised Learning of Syntactic Structure with Invertible Neural Projections
• Named Entity Recognition Only from Word Embeddings
• Sparse Coding of Neural Word Embeddings for Multilingual Sequence Labeling