# Levy 2015: Improving Distributional Similarity with Lessons Learned from Word Embeddings

> Omer Levy, Yoav Goldberg, Ido Dagan, 2015. 1 records on Mysteries Department cite it. The inductive methods survey uses its PPMI-SVD embeddings as a…

Source: https://mysteriesdept.com/sources/SRC0D8MRWP4136A/improving-distributional-similarity-with-lessons-learned  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Voynich Manuscript](https://mysteriesdept.com/mysteries/voynich-manuscript)Levy 2015

**0**

# Improving Distributional Similarity with Lessons Learned from Word Embeddings

Omer Levy, Yoav Goldberg, Ido Dagan, 2015. _Transactions of the Association for Computational Linguistics_.

Shows that much of the advantage of neural word embeddings comes from design choices and hyperparameters, which can be carried over to traditional count-based models with similar gains.

**Voynich Manuscript** Articledoi: **[10.1162/tacl_a_00134](https://doi.org/10.1162/tacl_a_00134)** Checked against the original0

## What it's used for here

The inductive methods survey uses its PPMI-SVD embeddings as a stable choice for a small corpus in test N5.

## Cited by on this site 1 record

[1 methods surveys]

Inductive methods

SRC

## Cite it

```
Levy, O., Goldberg, Y., & Dagan, I. (2015). Improving Distributional Similarity with Lessons Learned from Word Embeddings. Transactions of the Association for Computational Linguistics. https://doi.org/10.1162/tacl_a_00134
```

[Read it free at doi.org](https://doi.org/10.1162/tacl_a_00134)[PDF stored here · 16 pages](https://mysteriesdept.com/sources/SRC0D8MRWP4136A/improving-distributional-similarity-with-lessons-learned/pdf)

The PDF is the copy doi.org gives away, kept here so the link can't break. Downloads are open to beta members.

Key

**SRC** 0D8MRWP4136A

Kind

Journal article

Rights

CC-BY-NC-SA-3.0

Checked

Against the published article

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC0D8MRWP4136A/improving-distributional-similarity-with-lessons-learned/csl.json)