How to use the forte.processors.nltk_processors.NLTKWordTokenizer function in forte

To help you get started, we’ve selected a few forte examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github asyml / forte / examples / chatbot / chatbot_example.py View on Github external
query_pipeline.set_reader(
        reader=MultiPackTerminalReader(), config=config.reader)
    query_pipeline.add(
        component=MicrosoftBingTranslator(), config=config.translator)
    query_pipeline.add(
        component=BertBasedQueryCreator(), config=config.query_creator)
    query_pipeline.add(
        component=SearchProcessor(), config=config.searcher)

    top_response_pack_name = config.indexer.response_pack_name + '_0'

    query_pipeline.add(
        component=NLTKSentenceSegmenter(),
        selector=NameMatchSelector(select_name=top_response_pack_name))
    query_pipeline.add(
        component=NLTKWordTokenizer(),
        selector=NameMatchSelector(select_name=top_response_pack_name))
    query_pipeline.add(
        component=NLTKPOSTagger(),
        selector=NameMatchSelector(select_name=top_response_pack_name))
    query_pipeline.add(
        component=SRLPredictor(), config=config.SRL,
        selector=NameMatchSelector(select_name=top_response_pack_name))
    query_pipeline.add(
        component=MicrosoftBingTranslator(), config=config.back_translator)

    query_pipeline.initialize()

    return query_pipeline
github asyml / forte / examples / serialization / serialize_example.py View on Github external
def pack_example(input_path, output_path):
    """
    This example read data from input path and serialize to output path.
    Args:
        input_path:
        output_path:

    Returns:

    """
    print("Pack serialization example.")
    nlp = Pipeline[DataPack]()

    nlp.set_reader(OntonotesReader())
    nlp.add(NLTKSentenceSegmenter())
    nlp.add(NLTKWordTokenizer())
    nlp.add(NLTKPOSTagger())

    # This is a simple writer that serialize the result to the current
    # directory and will use the DocID field in the data pack as the file name.
    nlp.add(
        PackNameJsonPackWriter(),
        {
            'output_dir': output_path,
            'indent': 2,
            'overwrite': True,
        }
    )

    nlp.run(input_path)
github asyml / forte / examples / pipelines / process_string_example.py View on Github external
def main():
    pl = Pipeline[DataPack]()
    pl.set_reader(StringReader())
    pl.add(NLTKSentenceSegmenter())
    pl.add(NLTKWordTokenizer())
    pl.add(NLTKPOSTagger())

    pl.add(CoNLLNERPredictor(), config=config.NER)
    pl.add(SRLPredictor(), config=config.SRL)

    pl.initialize()

    text = (
        "So I was excited to see Journey to the Far Side of the Sun finally "
        "get released on an affordable DVD (the previous print had been "
        "fetching $100 on eBay - I'm sure those people wish they had their "
        "money back - but more about that in a second).")

    pack = pl.process_one(text)

    for sentence in pack.get(Sentence):
github asyml / forte / examples / pipelines / process_dataset_example.py View on Github external
def main(dataset_dir: str):
    config = yaml.safe_load(open("config.yml", "r"))
    config = Config(config, default_hparams=None)

    pl = Pipeline[DataPack]()
    pl.set_reader(PlainTextReader())
    pl.add(NLTKSentenceSegmenter())
    pl.add(NLTKWordTokenizer())
    pl.add(NLTKPOSTagger())
    pl.add(CoNLLNERPredictor(), config=config.NER)
    pl.add(SRLPredictor(), config=config.SRL)

    pl.initialize()

    for pack in pl.process_dataset(dataset_dir):
        print(colored("Document", 'red'), pack.meta.pack_name)
        for sentence in pack.get(Sentence):
            sent_text = sentence.text
            print(colored("Sentence:", 'red'), sent_text, "\n")
            # first method to get entry in a sentence
            tokens = [(token.text, token.pos) for token in
                      pack.get(Token, sentence)]
            entities = [(entity.text, entity.ner_type) for entity in
                        pack.get(EntityMention, sentence)]