spacy-models
healthsea
spacy-models | healthsea | |
---|---|---|
3 | 1 | |
1,515 | 84 | |
0.9% | - | |
9.2 | 3.2 | |
5 months ago | over 2 years ago | |
Python | Python | |
- | MIT License |
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.
spacy-models
-
spacy Can't find model 'en_core_web_sm' on windows 10 and Python 3.5.3 :: Anaconda custom (64-bit)
(C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder) C:\Users\nikhizzz>conda install -c conda-forge spacyFetching package metadata .............Solving package specifications: .Package plan for installation in environment C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder:The following NEW packages will be INSTALLED: blas: 1.0-mkl cymem: 1.31.2-py35h6538335_0 conda-forge dill: 0.2.8.2-py35_0 conda-forge msgpack-numpy: 0.4.4.2-py_0 conda-forge murmurhash: 0.28.0-py35h6538335_1000 conda-forge plac: 0.9.6-py_1 conda-forge preshed: 1.0.0-py35h6538335_0 conda-forge pyreadline: 2.1-py35_1000 conda-forge regex: 2017.11.09-py35_0 conda-forge spacy: 2.0.12-py35h830ac7b_0 conda-forge termcolor: 1.1.0-py_2 conda-forge thinc: 6.10.3-py35h830ac7b_2 conda-forge tqdm: 4.29.1-py_0 conda-forge ujson: 1.35-py35hfa6e2cd_1001 conda-forgeThe following packages will be UPDATED: msgpack-python: 0.4.8-py35_0 --> 0.5.6-py35he980bc4_3 conda-forgeThe following packages will be DOWNGRADED: freetype: 2.7-vc14_2 conda-forge --> 2.5.5-vc14_2Proceed ([y]/n)? yblas-1.0-mkl.t 100% |###############################| Time: 0:00:00 0.00 B/scymem-1.31.2-p 100% |###############################| Time: 0:00:00 1.65 MB/smsgpack-python 100% |###############################| Time: 0:00:00 5.37 MB/smurmurhash-0.2 100% |###############################| Time: 0:00:00 1.49 MB/splac-0.9.6-py_ 100% |###############################| Time: 0:00:00 0.00 B/spyreadline-2.1 100% |###############################| Time: 0:00:00 4.62 MB/sregex-2017.11. 100% |###############################| Time: 0:00:00 3.31 MB/stermcolor-1.1. 100% |###############################| Time: 0:00:00 187.81 kB/stqdm-4.29.1-py 100% |###############################| Time: 0:00:00 2.51 MB/sujson-1.35-py3 100% |###############################| Time: 0:00:00 1.66 MB/sdill-0.2.8.2-p 100% |###############################| Time: 0:00:00 4.34 MB/smsgpack-numpy- 100% |###############################| Time: 0:00:00 0.00 B/spreshed-1.0.0- 100% |###############################| Time: 0:00:00 0.00 B/sthinc-6.10.3-p 100% |###############################| Time: 0:00:00 5.49 MB/sspacy-2.0.12-p 100% |###############################| Time: 0:00:10 7.42 MB/s(C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder) C:\Users\nikhizzz>python -VPython 3.5.3 :: Anaconda custom (64-bit)(C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder) C:\Users\nikhizzz>python -m spacy download enCollecting en_core_web_sm==2.0.0 from https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.0.0/en_core_web_sm-2.0.0.tar.gz#egg=en\_core\_web\_sm==2.0.0 Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.0.0/en_core_web_sm-2.0.0.tar.gz (37.4MB) 100% |################################| 37.4MB ...Installing collected packages: en-core-web-sm Running setup.py install for en-core-web-sm ... doneSuccessfully installed en-core-web-sm-2.0.0 Linking successful C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder\lib\site-packages\en_core_web_sm --> C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder\lib\site-packages\spacy\data\en You can now load the model via spacy.load('en')(C:\Users\nikhizzz\AppData\Local\conda\conda\envs\tensorflowspyder) C:\Users\nikhizzz>
-
word similarity vs. sentence similarity
Well the medium model is using Glove (common crawl) for word vectors. There are only 685K keys so depending on the corpus you are working with, its possible lots of the words you are interested in don't have a corresponding vector and end up as zero vectors. Spacy Document/Span vectors are simply averages of the word vectors. So the higher performance of phrases may simply be because there is a higher chance of non Out of Vocabulary (OOV) words. So less chance of a zero vector.
-
SpaCy VS Transformers for NER
spaCy vs transformers isn't really a good comparison. You can plug a variety of things into spaCy's NLP pipelines, including Huggingface's transformer models. spaCy 3, in particular, has pre-built models with Huggingface's transformers, like en_core_web_trf.
healthsea
-
I built an NLP pipeline for analyzing supplement reviews called Healthsea 🐳
Github: https://github.com/explosion/healthsea
What are some alternatives?
flair - A very simple framework for state-of-the-art Natural Language Processing (NLP)
HanLP - 中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
spacy-llm - 🦙 Integrating LLMs into structured NLP pipelines
MAX-Toxic-Comment-Classifier - Detect 6 types of toxicity in user comments.
imbalanced-regression - [ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
thinc-apple-ops - 🍏 Make Thinc faster on macOS by calling into Apple's native Accelerate library
zshot - Zero and Few shot named entity & relationships recognition
pytextrank - Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
thinc - 🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
Dragonfire - the open-source virtual assistant for Ubuntu based Linux distributions
argilla - Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.