文章起源 | 恒源云社区（一个专一 AI 行业的共享算力平台：恒源智享云)
原文地址 | SpaCy
最近分享了社区大佬们的一些语言解决类的论文，干货满满！
戳 可查看，兴许就有你须要的知识点哦～
恒源云 _比照学习，只须要 Dropout?
恒源云 _ 语音辨认与语义解决畛域之机器翻译 21.7 mRASP2
恒源云 _LLD: 外部数据领导的标签去噪办法【ACL 2022】
恒源云 _Y-Tuning: 通过对标签表征进行微调的深度学习新范式【ACL 2022】
恒源云 _ 语音辨认与语义解决畛域之 NAG 优化器
✨明天呢，就给大家分享一下如何在恒源云GPU服务器上如何应用spaCy。
置信很多小伙伴都晓得，spaCy 是一个自然语言解决库，包含分词、词性标注、词干化、命名实体辨认、名词短语提取等性能。
那如何装置呢？
# 装置 spaCy 3 For CUDA 11.2，依据镜像 CUDA 版本替换 [] 内版本pip install spacy[cuda112]==3.0.6# 装置 spaCy 2 For CUDA 11.2，依据镜像 CUDA 版本替换 [] 内版本pip install spacy[cuda112]==2.3.5# 通过 spacy 模块下载模型因为墙可能不可用，可通过上面 pip 装置形式装置python -m spacy download en_core_web_sm# 装置 3.0.0 en_core_web_smpip install https://mirror.ghproxy.com/https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0-py3-none-any.whl --no-cache# 装置 2.3.1 en_core_web_smpip install https://mirror.ghproxy.com/https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.3.1/en_core_web_sm-2.3.1.tar.gz --no-cache装置之后又如何应用呢？
import spacy# Load English tokenizer, tagger, parser and NERnlp = spacy.load("en_core_web_sm")# Process whole documentstext = ("When Sebastian Thrun started working on self-driving cars at " "Google in 2007, few people outside of the company took him " "seriously. “I can tell you very senior CEOs of major American " "car companies would shake my hand and turn away because I wasn’t " "worth talking to,” said Thrun, in an interview with Recode earlier " "this week.")doc = nlp(text)# Analyze syntaxprint("Noun phrases:", [chunk.text for chunk in doc.noun_chunks])print("Verbs:", [token.lemma_ for token in doc if token.pos_ == "VERB"])# Find named entities, phrases and conceptsfor entity in doc.ents: print(entity.text, entity.label_)以上就是明天所有的分享内容啦。对了，提前预祝大家除夕高兴呀～