Construction sentence embeddings using articles' titles

The main goal of this proyect is to obtain sentence embeddings of 450 abstract titles, apply hierarchical clustering to the resulting vectors and analyze the characteristics of the sentences from each group. We expect that sentences indicating an association between a gene and a disease end up clustered together.

Input data sets

\corpora

Sentence embeddings

\embeddings

Programs and commands used

\scripts

Results from clustering

\results