| from transformers import TokenClassificationPipeline | |
| class UniversalDependenciesPipeline(TokenClassificationPipeline): | |
| def _forward(self,model_input): | |
| import torch | |
| v=model_input["input_ids"][0].tolist() | |
| with torch.no_grad(): | |
| e=self.model(input_ids=torch.tensor([v[0:i]+[self.tokenizer.mask_token_id]+v[i+1:]+[j] for i,j in enumerate(v[1:-1],1)])) | |
| return {"logits":e.logits[:,1:-2,:],**model_input} | |
| def postprocess(self,model_output,**kwargs): | |
| import numpy | |
| import ufal.chu_liu_edmonds | |
| e=model_output["logits"].numpy() | |
| 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] | |
| if [0 for i in h if i==0]!=[0]: | |
| m[:,0]+=numpy.where(m[:,0]<numpy.nanmax(m[:,0]),numpy.nan,0) | |
| h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0] | |
| v=[(s,e) for s,e in model_output["offset_mapping"][0].tolist() if s<e] | |
| q=[self.model.config.id2label[p[i,j]].split("|") for i,j in enumerate(h)] | |
| if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]=="simple": | |
| for i,j in reversed(list(enumerate(q[2:],2))): | |
| if j[-1]=="goeswith": | |
| h=[b if i>b else b-1 for a,b in enumerate(h) if i!=a] | |
| v[i-2]=(v[i-2][0],v.pop(i-1)[1]) | |
| q.pop(i) | |
| t=model_output["sentence"] | |
| u="# text = "+t+"\n" | |
| for i,(s,e) in enumerate(v,1): | |
| u+="\t".join([str(i),t[s:e],"_",q[i][0],"_","|".join(q[i][1:-1]),str(h[i]),q[i][-1],"_","_" if i<len(v) and e<v[i][0] else "SpaceAfter=No"])+"\n" | |
| return u+"\n" | |