INNER CODE UNIT · Rust

tagger

bminixhofer/nlprule · python/src/lib.rs:340

    fn tagger(&self) -> PyTagger {
        self.tokenizer.tagger().clone().into()
    }

    /// Applies the full tokenization pipeline to the given text.
    /// This includes POS tagging, lemmatization, chunking and sentencization.
    ///
    /// Arguments:
    ///     text_or_texts (Union[str, List[str]]): The text(s) to tokenize.
    ///
    /// Returns:
    ///     tokens (Union[List[List[Token]], List[List[List[Token]]]]):
    ///         The analyzed tokens. A list of lists of tokens. The outer list corresponds to a sentence. Batched if the input is batched.
    #[text_signature = "(text_or_texts)"]
    fn pipe(&self, py: Python, text_or_texts: PyObject) -> PyResult<PyObject> {
        text_guard(py, text_or_texts, |text| {
            let tokens = self
                .tokenizer

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…