-
In "Galileo, Sedereus Nuncius, r5," although Heder generally did a good job parsing the text that "nuncius" is just "nuntius."
https://hederaproject.org/lemmatized_text/50/
We need a way to do t…
-
I have identified a group of words that are incorrectly stemmed. Please assist me. I don't know how to patch [swedish.sbl](https://github.com/snowballstem/snowball/blob/master/algorithms/swedish.sbl).…
-
the sample code , after adding $nbProcess = 6; gives an empty array.
-
Resolve to most frequent lemma
-
## How to reproduce the behaviour
```python
import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp("cameras, fungi")
for token in doc:
print(token._lemma)
# return cameras, fungi, e…
-
- [x] Tokenisation and sentence segmentation
- [x] Lemmatisation and UD morphological features
- [x] UD syntactic annotations
- [ ] NER marking (PER, LOC, ORG, MISC)
-
Hi, I am trying to train a new model using the ufal.udpipe package on Python. The Trainer.train() command works so far as to selecting the best options for the tagger, the tokenizer and the parser, bu…
-
**Describe the problem**
I am not able to validate or lemmatise my ATF files. I get the "project code not found in ATF" error. The files work fine in NAMMU. My colleague is having the same issue.
…
-
Using spacy to extract nouns, propn or verbs from the advisory and the commits messages and then looking for matches seems a good start to treat difficult candidates that do not match any other rule.
…
-
[`ADV`](https://universaldependencies.org/u/pos/ADV.html) claims Germanic verb particles are `ADV` (and not `PART`).
[`ADP`](https://universaldependencies.org/u/pos/ADP.html) claims they are `ADP`.…