Thanks for providing the code for sense2vec! We noticed that for several examples, the output of the vectors we downloaded on sense2vec was different than the demo (we're using the 2019 version). For instance, the word "eyries" has no embedding when using the downloaded vectors, but the demo shows associations for this word. Additionally, the associations for "Beekeeping|VERB" in the downloaded vectors are available, but they are not available on the demo (Beekeeping|auto leads to weird associations, like "Throats").
If there are any insights behind this inconsistency, we would greatly appreciate it!
Hi,
Thanks for providing the code for sense2vec! We noticed that for several examples, the output of the vectors we downloaded on sense2vec was different than the demo (we're using the 2019 version). For instance, the word "eyries" has no embedding when using the downloaded vectors, but the demo shows associations for this word. Additionally, the associations for "Beekeeping|VERB" in the downloaded vectors are available, but they are not available on the demo (Beekeeping|auto leads to weird associations, like "Throats").
If there are any insights behind this inconsistency, we would greatly appreciate it!