-
Come up with heuristic to find optimal GADM level. Some countries have highly fine grained GADM districts down to 1km on average. These add computational cost since it adds thousands more files to pro…
-
Hi there, this is not as much of a Github issue as a question about whether this approach would work on any downstream NLU task, for example named entity recognition where each token's contextual vect…
aneof updated
2 years ago
-
I submitted the NER system output in the artifacts directory to the SDK. Below is the generated analysis. All buckets in "sentence_length" returned identical cases in bucket samples (a total of 1010).…
-
I found hard to understand the concept of module in Weaviate's documentation.
It seems a module encapsulates 2 concepts: Vectorizer (indexer) and Inference (reader)
- Vectorizers:
text2vec-tr…
-
Thank you for the awesome project.
Rubrix already support many NLP tasks which is great. It would be great if it support QA task as well.
As a community maintainer of [Haystack](https://github.c…
-
Happens with the following sentence, **under version 3.9.2, only when adding openIE annotator:**
> It was a long and stern face, but with eyes that twinkled in a kindly way.
stack trace:
`jav…
-
The documentation for Spacy v2 had a very useful page describing the various (coarse and fine-grained) tagsets used for POS tagging, NER, etc. (https://v2.spacy.io/api/annotation). I often used it …
-
I was wondering if in Stanza is possible to **add some new tags**, to the existing NER model.
I remember in **CORENLP** you can conditionate the output of the CRFs like expressed in this [link](ht…
-
spacy version 2.2.3
I have some gold standard annotated data set in spacy format like this
`("""jvc/3/21/2008 Dr. John V. Smithn.""",{'entities':[(4,13,'DATE'),(18,32,'PERSON')]})`
And I'm …
-
It would be really nice for StandardTokenizer to adhere straight to the standard as much as we can with jflex. Then its name would actually make sense.
Such a transition would involve renaming the ol…