deeplearning4j/deeplearning4j-examples

Convert string to vector in DataVec

Open

#877 opened on Aug 20, 2019

View on GitHub
 (2 comments) (1 reaction) (0 assignees)Java (2,395 stars) (1,841 forks)batch import
enhancementhelp wanted

Description

Please provide an example showing how to transform sentence (string) training data to vectors using a pre-populated word2vec object. Edourado mentioned we should be able to use an embedded layer to do this. Something about mapping word2vec to rows of vectors inside an embedded layer, then having the input layer contain indexes to those rows depending on what words the input data references.

Keep in mind the input contains sentences (multiple words). Thank you.

Contributor guide

Tech stack
java
Domain
machine learningdocumentation
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Java basicsDeeplearning4j fundamentalsWord2Vec concepts
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35
Research direction
Explore existing DataVec examples in the repository to understand the pattern for converting data. In particular, look at any word2vec or embedding layer examples. Also, search for the mention by Edourado in related issues or commits. The example should demonstrate using a pre populated Word2Vec object with an embedding layer to map sentence strings to vectors.