Figures & data
Table 1. Example co-occurrence matrix.
Figure 1. Continuous bag-of-words and skip-gram architectures (Figure taken from: (Mikolov, Sutskever, et al. Citation2013)).
![Figure 1. Continuous bag-of-words and skip-gram architectures (Figure taken from: (Mikolov, Sutskever, et al. Citation2013)).](/cms/asset/e63f5694-b63a-4b3b-97e9-a8576b5bcf91/vhim_a_1760157_f0001_b.jpg)
Figure 2. The angle or cosine distance between words along two dimensions (latent factors) indicates how close they are in meaning.
![Figure 2. The angle or cosine distance between words along two dimensions (latent factors) indicates how close they are in meaning.](/cms/asset/7dd4fee0-10bc-4fae-baf5-1e219c60b46b/vhim_a_1760157_f0002_b.jpg)
Figure 3. Two-dimensional projection of vectors of countries and their capital cities. (Figure taken from: (Mikolov, Sutskever, et al. Citation2013).
![Figure 3. Two-dimensional projection of vectors of countries and their capital cities. (Figure taken from: (Mikolov, Sutskever, et al. Citation2013).](/cms/asset/844d4f83-d3bc-4dd7-9537-5e2eeaee1470/vhim_a_1760157_f0003_c.jpg)
Figure 4. Semantic Shifts of Individual Words in Dutch Newspapers (dashed line indicates the frequency and the solid line refers to cosine similarity.
![Figure 4. Semantic Shifts of Individual Words in Dutch Newspapers (dashed line indicates the frequency and the solid line refers to cosine similarity.](/cms/asset/ab879820-04e2-47b2-a422-f7d397c41f40/vhim_a_1760157_f0004_b.jpg)
Figure 6. Changes in local neighbors (k = 25) of two target words in embeddings trained on historical Dutch Newspapers.
![Figure 6. Changes in local neighbors (k = 25) of two target words in embeddings trained on historical Dutch Newspapers.](/cms/asset/5cd4a98c-4314-4988-8257-9bd641313997/vhim_a_1760157_f0006_b.jpg)