From a30281b359bec76b4b578fa6fe76fa84c7afec8b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alina=20Wr=C3=B3blewska?= <alina@e-science.pl> Date: Mon, 8 May 2023 07:30:25 +0000 Subject: [PATCH] Update prediction.md --- docs/prediction.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/docs/prediction.md b/docs/prediction.md index 879f980..25b7df1 100644 --- a/docs/prediction.md +++ b/docs/prediction.md @@ -29,6 +29,18 @@ tokenized_sentence = ["Sentence", "to", "parse", "."] sentence = nlp([tokenized_sentence]) ``` +You can use COMBO with the [LAMBO](https://gitlab.clarin-pl.eu/syntactic-tools/lambo) tokeniser (Note: installing LAMBO is necessary, see [LAMBO installation](https://gitlab.clarin-pl.eu/syntactic-tools/lambo#installation) ). + +```python +# Import COMBO and lambo +from combo.predict import COMBO +from combo.utils import lambo + +# Download models +nlp = COMBO.from_pretrained("english-bert-base-ud29",tokenizer=lambo.LamboTokenizer("en")) +sentences = nlp("This is the first sentence. This is the second sentence to parse.") +``` + ## COMBO as a command-line interface ### CoNLL-U file prediction: Input and output are both in `*.conllu` format. -- GitLab