-
## Summary
For the project, we need to test tools for automated lemmatization, stemming and morphology induction. Please try to get them running on and evaluate against ETCSL CoNLL data. If you run i…
-
When running first chunk of `absa.ipynb`
```
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last…
-
### Description
why not use all gpu memory - t2t training?
nvidia-smi reports low GPU
![image](https://user-images.githubusercontent.com/32744746/64552801-fc0db500-d372-11e9-8864-5104b5c16b59.p…
-
e.g. in https://github.com/metanorma/stepmod-utils/issues/23
The directive of `term:[individual products]` is provided but the actual term is "individual product".
By using word stemmers we coul…
-
Cf https://github.com/nltk/nltk/issues/2421
I propose that we add a `stem=False` flag to `wn.synsets()`.
It means that default behaviour for English will change, but I see no other option, given…
-
```
Building a wrapper for the MATE pipeline for processing several documents and
without loading each model for every document, one needs to call the out()
methods of the respective tools (after in…
-
```
Building a wrapper for the MATE pipeline for processing several documents and
without loading each model for every document, one needs to call the out()
methods of the respective tools (after in…
-
```
Building a wrapper for the MATE pipeline for processing several documents and
without loading each model for every document, one needs to call the out()
methods of the respective tools (after in…
-
WordNet (and wordnet lemmatizer) allow specifying a `pos` as an optional argument. For example:
```python
from nltk.corpus import wordnet as wn
# Synsets
print(wn.synsets("run", pos='n'))
#…
-
Hello! I am running into a word-sense disambiguation issue where CoreNLP seems to be systematically struggling with adverbs that share a surface form with different words. For example, "number" (as in…