Inconsistency between demo and github vectors
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Compare the 2019 downloaded vectors with the demo for “eyries” and “Beekeeping|VERB”, using the issue examples as the starting point. Determine why the available terms and associations differ, then document a reproducible explanation or resolution.
Written by the indexing model from the issue text.
Description
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!
- Dominant language
- Python
- Stars
- 1.7k
- Forks
- 236
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from explosion/sense2vec
-
import error Openusage
Difficulty 4/5 3-5 days Newbie friendliness 20/100
-
usage
Difficulty 3/5 1-2 days Newbie friendliness 30/100
-
provide citation Open
Difficulty 1/5 Under an hour Newbie friendliness 35/100
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
All issues in explosion/sense2vec
Similar issues
-
documentation help wanted
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
simonw/sqlite-utils#872 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100