Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Skip-gram model.

The three-layer neural network architecture of a skip-gram model. An example input word, families, is depicted with a one-hot representation as well as example weight coefficient matrices used to produce an output value prediction for the word happy.

More »

Fig 1 Expand

Fig 2.

Histogram of course equivalency scores.

Distribution of course equivalency validation scores from 400 model experiments, calculated as the median similarity rank of each pair. Lower is better. Scores > 50 omitted due to high skew.

More »

Fig 2 Expand

Table 1.

Best models by overall validation score (median rank) for each validation set and cross-list collapse percentage.

More »

Table 1 Expand

Fig 3.

PCA analogy visualization.

PCA of vector offsets with a Sequence and Honors constellation depicted using Physics courses.

More »

Fig 3 Expand

Table 2.

A selection of analogy results from each of the six relationship categories.

More »

Table 2 Expand

Fig 4.

Conceptual decompositions.

Conceptual decompositions of courses in the Subjects of (A) Mathematics and Education, (B) Economics, Public Policy, and Statistics and (C) all subject vectors.

More »

Fig 4 Expand

Table 3.

Exemplar subject compositions.

More »

Table 3 Expand

Fig 5.

t-SNE 2-d projections.

(A) all course vectors with close-ups of the departments of (B) History and (C) Near Eastern Studies.

More »

Fig 5 Expand

Fig 6.

Close-up of race & gender studies cluster.

More »

Fig 6 Expand

Fig 7.

Close-up of Asian languages & culture cluster.

More »

Fig 7 Expand

Table 4.

Results of predicting attributes from course vectors.

More »

Table 4 Expand

Table 5.

Rules for preprocessing the semantic model training corpus.

More »

Table 5 Expand

Table 6.

Semantic model descriptions of subject vectors using biases of 0.5 and 1.

More »

Table 6 Expand

Table 7.

Semantic model description of missing subjects, the origin vector, and course vector differences (0.5 bias).

More »

Table 7 Expand