Stanza
BERT-NER
| Stanza | BERT-NER | |
|---|---|---|
| 8 | 1 | |
| 7,337 | 1,206 | |
| 0.4% | - | |
| 9.7 | 0.0 | |
| 3 days ago | over 3 years ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stanza
- Down and Out in the Magic Kingdom
-
Parts of speech tagged for German
I use Python's spacy library: https://spacy.io/models/de or stanza: https://stanfordnlp.github.io/stanza/ each with their respective language models.
-
Off the shelf sentence parsers?
stanza has a constituency parser. There's a model compatible with the dev branch with an accuracy of 95.8 on PTB, using Roberta as a bottom layer, so it's pretty decent at this point. (The currently released model is not as accurate, but it's easy to get the better model to you.) There's also Tregex as a Java addon which can very easily search for a noun phrase highest up in the tree: NP !>> NP will search for a noun phrase which is not dominated by any higher up noun phrase.
- The Spacy NER model for Spanish is terrible
- Spacy vs NLTK for Spanish Language Statistical Tasks
-
Stanza not tokenising sentences as expected
I am using Stanza to tokenise the sentences:
- Stanza β A Python NLP Package for Many Human Languages
BERT-NER
What are some alternatives?
spaCy - π« Industrial-strength Natural Language Processing (NLP) in Python
NLTK - NLTK Source
flair - A very simple framework for state-of-the-art Natural Language Processing (NLP)
Jieba - η»ε·΄δΈζεθ―
haystack - AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
pytext - A natural language modeling framework based on PyTorch
deepsparse - Sparsity-aware deep learning inference runtime for CPUs
FARM - :house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
polyglot - Multilingual text (NLP) processing toolkit
sparktorch - Train and run Pytorch models on Apache Spark.