Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Aidana Karipbayeva

A Critique of the Smooth Inverse Frequency Sentence Embeddings

Sep 30, 2019
Aidana Karipbayeva, Alena Sorokina, Zhenisbek Assylbekov

Figure 1 for A Critique of the Smooth Inverse Frequency Sentence Embeddings

Figure 2 for A Critique of the Smooth Inverse Frequency Sentence Embeddings

We critically review the smooth inverse frequency sentence embedding method of Arora, Liang, and Ma (2017), and show inconsistencies in its setup, derivation, and evaluation.

* 2 pages, 2 figures, Abstract

Via

Access Paper or Ask Questions

Low-Rank Approximation of Matrices for PMI-based Word Embeddings

Sep 21, 2019
Alena Sorokina, Aidana Karipbayeva, Zhenisbek Assylbekov

Figure 1 for Low-Rank Approximation of Matrices for PMI-based Word Embeddings

Figure 2 for Low-Rank Approximation of Matrices for PMI-based Word Embeddings

Figure 3 for Low-Rank Approximation of Matrices for PMI-based Word Embeddings

Figure 4 for Low-Rank Approximation of Matrices for PMI-based Word Embeddings

We perform an empirical evaluation of several methods of low-rank approximation in the problem of obtaining PMI-based word embeddings. All word vectors were trained on parts of a large corpus extracted from English Wikipedia (enwik9) which was divided into two equal-sized datasets, from which PMI matrices were obtained. A repeated measures design was used in assigning a method of low-rank approximation (SVD, NMF, QR) and dimensionality of the vectors (250, 500) to each of the PMI matrix replicates. Our experiments show that word vectors obtained from the truncated SVD achieve the best performance on two downstream tasks, similarity and analogy, compare to the other two low-rank approximation methods.

* 10 pages, 4 figures, CICLing 2019, Springer "Lecture Notes in Computer Science"

Via

Access Paper or Ask Questions