-
http://hdl.handle.net/11372/LRT-1249
- [ ] Missing input and output info
- [x] Missing licence info
-
First of all, thank you for a great job! I ran into a few issues while following the tutorial to reproduce:
I first follow [tutorial](https://github.com/FudanDISC/ReForm-Eval#create-your-own-model-…
-
Somehow when doing the decoding on CPU makes PyTorch unhappy.
So lets document how to fix this.
-
It seems that while there is support for tokenization with diacritics in spaCy, the project doesn't lemmatize/morph/pos tag correctly when they are used.
## How to reproduce the behaviour
```
imp…
mtak- updated
9 months ago
-
The consequence is that if a collection of documents is processed in a different order, the results may be different, sometimes correct and sometimes incorrect. One might say that SUTime is unstable.…
-
Dear all,
For my research I want to evaluate a new semantic coherence measure with the ones available in Palmetto, especially C_V and C_A. I'm trying to replicate some results described in your pap…
-
These are instances of nouns (`NN`) and proper nouns (`NNPS`) marked as plurals (`Number=Plur`) where the lemma is the plural form. Each of these (on a case by case basis) should either:
1. use the s…
-
For many applications, for example for the creation of lemmatization lists or dictionaries, it would be super useful to have a post-processed version of the inflections, or something like a function t…
-
Perfect tense is missing when parsing latin text.
```py
"Tense": {
"Fut": Tense.future,
"Imp": Tense.imperfect,
"Past": Tense.past,
"Pqp": Tense.pluperfect,…
-
Меня интересует повышение доли правильно лемматизированных санскритизмов (санскритских слов в кириллической записи) в русском языке с помощью морфологического анализа deeppavlov. Хуже всего анализатор…