NickAcosta / HuggingFacePipelines1 / 1.1.0


Transformers' pipeline module is developed by Hugging Face and provides a high-level, easy to use, API for doing inference over a variety of downstream-tasks

Applicable Scenarios and Problems

  • Sentiment Analysis
  • Named Entity Recognition
  • Question Answering
  • Mask Filling
  • Summarization
  • Translation
  • Text Generation
  • Features Extraction



Describe the input fields for your algorithm. For example:

tasktask describes the type of nlp operation you would like to perform
inputthe input you would like the nlp operation to be performed on
questionOptional use for Q-A only, use input as context

Table of tasks

UsageTask NameDescription
'sentiment-analysis'Sentiment AnalysisIndicate if the overall sentence is either positive or negative, i.e. binary classification task or logitic regression task.
'ner'Named Entity RecognitionFor each sub-entities (tokens) in the input, assign them a label, i.e. part-of-speech tagging
'question-answering'Question AnsweringProvided a tuple (question, context) the model should find the span of text in content answering the question.
'fill-mask'Mask FillingSuggests possible word(s) to fill the masked input with respect to the provided context. - mask last work only
'summarization'SummarizationSummarizes the input article to a shorter article.
'translation_xx_to_yy'TranslationTranslates the input from a language to another language.
'feature-extraction'Feature ExtractionMaps the input to a higher, multi-dimensional space learned from the data.


Provide and explain examples of input and output for your algorithm.