text2vec

text2vec copied to clipboard

Multiple Errors Adapting GloVe Example to Project - Quanteda Related

3

Hello there, I am having what I believe are multiple issues adapting the GloVe word embeddings tutorial to my project. I am starting with a tokens object created in Quanteda...

sellociompi

WISH: Less aggressive parallelization by default (please don't use *all* CPU cores)

3

Hi, I noticed **text2vec** runs on _all_ CPU cores by default on Unix. This is from: https://github.com/dselivanov/text2vec/blob/9ddf836b995511d8747cc98f753e9cc706cf3c84/R/zzz.R#L6-L9 https://github.com/dselivanov/text2vec/blob/9ddf836b995511d8747cc98f753e9cc706cf3c84/R/mc_queue.R#L1-L4 Defaulting to all cores causes major problems on machines used by multiple...

HenrikBengtsson

[question] Topic number selection using Cross Validation

1

Hi, I'm quite new to topic modelling and I've been working on a particular project with a very large corpus. Performing LDA using gibb-sampler is out of the question (atleast...

j-aryan

Hello! I'm currently using text2vec to create embeddings for a dataset of tweets. Since each document is pretty short, I want to implement a Simple Word Embedding Model (SWEM), specifically...

raywyf

GlobalVectors object lost fit method?

3

Hey there. I find [your example](https://cran.r-project.org/web/packages/text2vec/vignettes/glove.html) from Feb no longer works for me (macOS 11.0.1, version 4.0.3, text2vec 0.6). ``` require(text2vec) #> Loading required package: text2vec glove = GlobalVectors$new(rank =...

geotheory

Loading pretrained Glove embeddings

4

This is related to #283 which was closed. I found seemingly working code able to load pretrained GloVe vectors to text2vec: https://gist.github.com/tjvananne/8b0e7df7dcad414e8e6d5bf3947439a9 I have not run this successfully due to...

kliegr

Added test for split_vector() from utils.R.

2

hxxr

Translation of your Guide into Chinese on text2vec.org

11

Hello! I find your package efficient compared with tm and others, so is it's structure. I want to recommend it to my students in China and have done some translation...

cmldyu

A Simple but Tough-to-Beat Baseline for Sentence Embeddings

9

Paper: http://104.155.136.4:3000/pdf?id=SyK00v5xx Blog post: http://www.offconvex.org/2016/02/14/word-embeddings-2/ Looks like an interesting idea

zachmayer

Norvig spell corrector

1

Taken from #73: - [original post](http://norvig.com/spell-correct.html) - [**2(!!!) lines**](http://www.sumsar.net/blog/2014/12/peter-norvigs-spell-checker-in-two-lines-of-r/) of code in R

dselivanov