metadata

language:
  - en
tags:
  - english
  - token-classification
  - pos
  - dependency-parsing
datasets:
  - universal_dependencies
license: cc-by-sa-4.0
pipeline_tag: token-classification

roberta-base-english-ud-goeswith

Model Description

This is a RoBERTa model for POS-tagging and dependency-parsing (using goeswith for subwords), derived from roberta-base.

How to Use

class UDgoeswith(object):
  def __init__(self,bert):
    from transformers import AutoTokenizer,AutoModelForTokenClassification
    self.tokenizer=AutoTokenizer.from_pretrained(bert)
    self.model=AutoModelForTokenClassification.from_pretrained(bert)
  def __call__(self,text):
    import numpy,torch,ufal.chu_liu_edmonds
    w=self.tokenizer(text,return_offsets_mapping=True)
    v=w["input_ids"]
    x=[v[0:i]+[self.tokenizer.mask_token_id]+v[i+1:]+[j] for i,j in enumerate(v[1:-1],1)]
    with torch.no_grad():
      e=self.model(input_ids=torch.tensor(x)).logits.numpy()[:,1:-2,:]
    r=[1 if i==0 else -1 if j.endswith("|root") else 0 for i,j in sorted(self.model.config.id2label.items())]
    e+=numpy.where(numpy.add.outer(numpy.identity(e.shape[0]),r)==0,0,numpy.nan)
    m=numpy.full((e.shape[0]+1,e.shape[1]+1),numpy.nan)
    m[1:,1:]=numpy.nanmax(e,axis=2).transpose()
    p=numpy.zeros(m.shape)
    p[1:,1:]=numpy.nanargmax(e,axis=2).transpose()
    for i in range(1,m.shape[0]):
      m[i,0],m[i,i],p[i,0]=m[i,i],numpy.nan,p[i,i]
    h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
    u="# text = "+text+"\n"
    v=[(s,e) for s,e in w["offset_mapping"] if s<e]
    for i,(s,e) in enumerate(v,1):
      q=self.model.config.id2label[p[i,h[i]]].split("|")
      u+="\t".join([str(i),text[s:e],"_",q[0],"_","|".join(q[1:-1]),str(h[i]),q[-1],"_","_" if i<len(v) and e<v[i][0] else "SpaceAfter=No"])+"\n"
    return u+"\n"

nlp=UDgoeswith("KoichiYasuoka/roberta-base-english-ud-goeswith")
print(nlp("I saw a horse yesterday which had no name"))

ufal.chu-liu-edmonds is required.