Links to various experimental interfaces and approaches, none of which is completely ready for public consumption. We offer them as examples of the kinds of things we’ve been thinking about.

Word embeddings and chunk searches

An example of using word2vec to identify similar words.

An example of using word2vec to identify similar word + pos combinations.

Solr chunk search.

Solr-Word2Vec chunk search. There’s also another version. I’m not sure how they’re different.

Text reuse

Text reuse pages.

The Genesis Viewer, an experiment in using Blacklab to find text reuse.

Rhyme and the poetry sub-corpus

Topic modeling the poetry corpus.

A list of what I think rhymes with what. This is quite old . . .

Rhyme finder output from October, 2021.