-
conll2005.train.txt
conll2005.test.txt
conll2005.dev.txt
-
The UD guidelines say that words like _someone_ and _anybody_ should be PRON, but we still tag them as NOUN, because they're all NN in the Penn Treebank.
indefinite pronouns: somebody, something, som…
-
Refactoring the code of the Norwegian POS
-
Wordnet lemmatizer that depends on `nltk.corpus.wordnet._morphy()` doesn't handle exception words as expected,
``` python
>>> from nltk.stem import WordNetLemmatizer
>>> wnl = WordNetLemmatizer()
>>…
-
Hi,
Thanks a lot for making this code available. Can you please also add the data folder? I am getting errors such as
IOError: [Errno 2] No such file or directory: 'data/POS-penn/wsj/split1/wsj1.tra…
-
A sentence that works in SICK-SANE is
+# text = People are walking
+1 People people NOUN NNS _ 3 nsubj _ NNS|07942152-n|GroupOfPeople=
+2 are be VERB VBP _ 3 aux _ VBP|02604760-v|Entity+
+3 …
-
## Please let us know which model this issue is about (specify the top-level directory)
I tried to use the released model (Parsey McParseface) to parse PTB test set but only got 92.74% from the eval …
-
Dear Kevin,
Thank you for your tool and for comparison with other tools. I was actually looking for test cases for WBD and how different approaches perform on them. Though I have found the results of…
-
Since the first release of the UD guidelines in October 2014 copula verbs were to be tagged VERB and not AUX. But the stance was not unanimous in the core UD group. Should we revise the decision for v…
-
The tokenizer used in the PTB and UD corpora take this sentence:
Statford-upon-Avon is a junction on GWR.
and keeps the initial phrase as one token.
The Emory tokenizer splits it up, and then the …