Xiulin Yang

Hi, just wondering, is it possible to parse the pretokenized sentences and also get other lexical information like lemma, pos, etc. at the same time? I tried the nltk method...

Is there a way to convert the generated AMRs to the original format?

1

Hi I was just wondering if there is a way to convert the generated AMR (with pointer: 1, 2, ...) to the conventional AMRs (p1/ person ...). I checked the...

Including CONLL-UA format

1

Hey, thanks for this useful tool! I'm just curious if you will do some work to include the universal anaphora format in your project. If so, I'd like to contribute...

[Question]: I got different results when I loaded a trained model to do the inference task on the same test data

9

### Question Hi, I'm training a SequenceTagger to do the NER task using my customed dataset with the customed features. After training was done, I got a file named test.tsv...

[Question]: Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 99 column 3

1

### Question Hi, I tried to load the trained model from huggingface using the following lines. ``` from flair.models import SequenceTagger tagger = SequenceTagger.load("xiulinyang/deberta_srl") ``` It worked on Colab, but...

https://openreview.net/pdf?id=Oduxsr6QKW