Natural language generation evaluation metrics

衡量生成文本质量的方法集 快速开始 把待检测文件整理成如下格式: [ {“ref”: str, “hyps”: [str, str, …]}, {…}, … ] 命令行方法 查看用法 或者查看run.sh的例子 python run.py –input=input_path –output=output_path –metrics=”[‘rouge-1’, ‘bleu’, ‘self-bleu’]” 当前支持的方法有rouge-l, rouge-2, rouge-l, bleu, self-bleu, meteor, ppl。 其中,如果选择ppl,则需要增加命令行参数–ppl_model_path=model_path,这个path为模型文件(bert模型) 如果第一次使用meteor,需要去nltk 下载带中文的wordnet数据 Open Multilingual Wordnet (omw)以及 wordnet ,放入/root/nltk_data/corpora/中解压 python调用 from metrics import Metrics inputs = json.load(…) model = Metrics(metrics

Read more

Fetch fund data from Avanza using Python

Fetch fund data from avanza.se using Python and some web scraping with bs4. The default way is to display the data in the terminal, apply –json for json output. How does it work? Provide this script with the fund id (can be found in the url of the fund, example below). The script is scraping the funds page and displays the output. How is this useful? You can use this data for your own project, perhaps on a Raspberry Pi […]

Read more

Change desktop background image with python

Alfred workflow: change mac desktop background image Installation Download latest version from releases Double click and fill env named with image_base_path Manual Input cim $id, id range is [0, 1, 2, 3, 4, 5, 6, 7], means [today, yesterday, …] You Can visit here for detail. Features Crawling pic links from bing Saveing pic into filepath config image_base_path Setting current pic as desktop background image Acknowledgement Thanks bing. GitHub View Github    

Read more

An audio track separator in tensorflow that successfully separates Vocals and Drums from an input audio song track

Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals). Basically, splitting a song into separate vocals and instruments. In this Repository, We developed an audio track separator in tensorflow that successfully separates Vocals and Drums from an input audio song track. We trained a U-Net model with two output layers. One output layer predicts the Vocals and the other predicts the Drums. The […]

Read more

Obtain Site Plugins with the requests Library in Python v3

Obtain Site Plugins with the requests Library in Python v3 Python Install Python from here. Pip How to run? 🚀 Install Plugins In Windows In PowerShell git clone https://github.com/I3L4CK-H4CK3l2/Plugins.git In Linux In Terminal git clone https://github.com/I3L4CK-H4CK3l2/Plugins.git Requirements Install requests Usage In Windows python plugins.py [domain] In Linux python3 plugins.py [domain] Example python3 plugins.py instagram.com    

Read more

Improving Neural Cross-lingual Abstractive Summarization via Employing Optimal Transport Distance for Knowledge Distillation

This repository contains the implementation of the paper Improving Neural Cross-lingual Abstractive Summarization via Employing Optimal Transport Distance for Knowledge Distillation. Thong Nguyen, Luu Anh Tuan (AAAI 2022) In this paper, we propose a novel Knowledge Distillation framework to tackle Neural Cross-Lingual Summarization for morphologically or structurally distant languages. In our framework, we propose a novel Knowledge Distillationframework to tackle Neural Cross-Lingual Summarization for morphologically or structurally distant languages. Extensive experiments in both high and low-resourced settings on multiple Cross-Lingual […]

Read more

Earth observation framework for scaled-up processing in Python

Earth observation framework for scaled-up processing in Python. Analyzing Earth Observation (EO) data is complex and solutions often require custom tailored algorithms. In the EO domain most problems come with an additional challenge: How do we apply the solution on a larger scale? Working with EO data is made easy by the eo-learn package, while the eo-grow package takes care of running the solutions at a large scale. In eo-grow an EOWorkflow based solution is wrapped in a pipeline object, […]

Read more
1 251 252 253 254 255 927