Algebra with Words: Difference between revisions
From Algolit
| Line 3: | Line 3: | ||
Word embeddings are language modelling techniques that through multiple mathematical operations of counting and ordering, plot words into a multi-dimensional vector space. When embedding words, they transform from being distinct symbols into mathematical objects that can be multiplied, divided, added or substracted. | Word embeddings are language modelling techniques that through multiple mathematical operations of counting and ordering, plot words into a multi-dimensional vector space. When embedding words, they transform from being distinct symbols into mathematical objects that can be multiplied, divided, added or substracted. | ||
| − | While distributing the words along the many diagonal lines of the vector space, the visibility of their new geometrical placements | + | While distributing the words along the many diagonal lines of the multi-dimensional vector space, the visibility of their new geometrical placements is impossible to perceive by humans. However, what is gained are multiple, simultaneous ways of ordering. Algebraic operations make the relations between vectors graspable again. |
| − | This exploration is using [https://radimrehurek.com/gensim/index.html gensim], an open source vector space and topic modelling toolkit implemented in Python, to manipulate text | + | This exploration is using [https://radimrehurek.com/gensim/index.html gensim], an open source vector space and topic modelling toolkit implemented in Python, to manipulate text using the mathematical relationships that emerge between the words, once they have been plotted in a vector space. |
------------------------------------------ | ------------------------------------------ | ||
Revision as of 15:34, 9 March 2019
by Algolit
Word embeddings are language modelling techniques that through multiple mathematical operations of counting and ordering, plot words into a multi-dimensional vector space. When embedding words, they transform from being distinct symbols into mathematical objects that can be multiplied, divided, added or substracted.
While distributing the words along the many diagonal lines of the multi-dimensional vector space, the visibility of their new geometrical placements is impossible to perceive by humans. However, what is gained are multiple, simultaneous ways of ordering. Algebraic operations make the relations between vectors graspable again.
This exploration is using gensim, an open source vector space and topic modelling toolkit implemented in Python, to manipulate text using the mathematical relationships that emerge between the words, once they have been plotted in a vector space.
Concept & interface: Cristina Cochior
Technique: word embeddings, word2vec
Original model: Radim Rehurek and Petr Sojka