Apertium is a free/open-source machine translation platform that provides an engine, linguistic data, and tools for rule-based machine translation of related languages. It supports over 40 language pairs and has an active international community of hundreds of developers. Apertium translations have been used successfully in localization projects, content translation on Wikipedia, and crisis translation for under-resourced languages.
Invited Talk at Summer School on Semantic Web, Bertinoro, 2015
Abstract:
Two decades ago one has discussed how to build seamless digital workflows
such that the medium for data in a workflow would not switch between paper, fax, phone,
and digital, because each transcription from one to another medium would
be laborious and cost-inefficient. Thus, the issue was avoiding *medium discontinuities*.
Today, we have all-digital data workflows, but we have still plenty of *semantic discontinuities*.
In this talk, I want first to describe reasons for this discontinuities including: autonomy of
data providers, need for agility and flexibility, or decentralized organizations in
the world-wide data spaces.
Then I want to describe several semantics discontinuities and some efforts to
ameliorate them by:
1. Semantic programming (Horizontal workflow paradigm)
2. Core ontologies (Vertical workflow paradigm)
3. Semantic data production and consumption (Sticky semantics)
How community software supports language documentation and data analysisPeter Bouda
Field linguists have increasingly adopted the latest technologies and tools for language documentation. Their needs have led to remarkable developments in software and archiving, exemplified by work at the MPI in Nijmegen, which leads the innovation cycles that take place in the digital working environments of field linguists. The next step in research is now the analysis and theoretical exploitation of the huge amount of data that has been collected in numerous language documentation projects that use these environments. This research will also rely on computer-based strategies, as data is instantly available in digital formats.
In this talk I will introduce some of the lesser known tools and software packages for annotation and analysis tasks. Some of these tools were created within DOBES projects and/or as community projects by small teams; they can be combined with well-known tools like ELAN or Toolbox to give researchers access to their data. I will focus on how a combination of simple, special purpose tools makes researchers more productive and how existing software libraries allow scientific projects to create their own, task-specific software tools that they can tailor to their own needs.
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NETNETFest
Задачи по обработке естественного языка сейчас встречаются практически в любом проекте. К сожалению, до недавнего времени, платформа .NET не сильно подходила для решения подобных задач. С выходом ML.NET ситуация стала меняться к лучшему, но все еще далека от идеала.
На этом докладе я расскажу про основные задачи, которые решаются методами Natural Language Processing и какие существуют способы решения этих задач на платформе .NET (сервисы, библиотеки, фреймворки).
Invited Talk at Summer School on Semantic Web, Bertinoro, 2015
Abstract:
Two decades ago one has discussed how to build seamless digital workflows
such that the medium for data in a workflow would not switch between paper, fax, phone,
and digital, because each transcription from one to another medium would
be laborious and cost-inefficient. Thus, the issue was avoiding *medium discontinuities*.
Today, we have all-digital data workflows, but we have still plenty of *semantic discontinuities*.
In this talk, I want first to describe reasons for this discontinuities including: autonomy of
data providers, need for agility and flexibility, or decentralized organizations in
the world-wide data spaces.
Then I want to describe several semantics discontinuities and some efforts to
ameliorate them by:
1. Semantic programming (Horizontal workflow paradigm)
2. Core ontologies (Vertical workflow paradigm)
3. Semantic data production and consumption (Sticky semantics)
How community software supports language documentation and data analysisPeter Bouda
Field linguists have increasingly adopted the latest technologies and tools for language documentation. Their needs have led to remarkable developments in software and archiving, exemplified by work at the MPI in Nijmegen, which leads the innovation cycles that take place in the digital working environments of field linguists. The next step in research is now the analysis and theoretical exploitation of the huge amount of data that has been collected in numerous language documentation projects that use these environments. This research will also rely on computer-based strategies, as data is instantly available in digital formats.
In this talk I will introduce some of the lesser known tools and software packages for annotation and analysis tasks. Some of these tools were created within DOBES projects and/or as community projects by small teams; they can be combined with well-known tools like ELAN or Toolbox to give researchers access to their data. I will focus on how a combination of simple, special purpose tools makes researchers more productive and how existing software libraries allow scientific projects to create their own, task-specific software tools that they can tailor to their own needs.
.NET Fest 2019. Сергей Корж. Natural Language Processing in .NETNETFest
Задачи по обработке естественного языка сейчас встречаются практически в любом проекте. К сожалению, до недавнего времени, платформа .NET не сильно подходила для решения подобных задач. С выходом ML.NET ситуация стала меняться к лучшему, но все еще далека от идеала.
На этом докладе я расскажу про основные задачи, которые решаются методами Natural Language Processing и какие существуют способы решения этих задач на платформе .NET (сервисы, библиотеки, фреймворки).
Lynx Webinar #4: Lynx Services Platform (LySP) - Part 2 - The ServicesLynx Project
Free Webinar on the Lynx Services Platform LySP: Architecture and basic Services
The main objective of the Lynx research and innovation project is to create an ecosystem of smart cloud services to better manage compliance, based on a Legal Knowledge Graph (LKG) which integrates and links multilingual and heterogeneous compliance data sources including legislation, case law, standards, regulations and other private contracts, beside others.
This webinar will provide insights into all smart services of the Lynx Services Platform (LySP) including demos of these LySP services, as for instance: Named Entity Extraction (NER) by DFKI, Relation Extraction and Question-Answering by SWC, Machine Translation by Tilde or the Lexicala cross-lingual lexical data service by KDictionaries.
Apertium is a free/open-source platform for rule-based machine translation which was started in 2005 and is developed collaboratively. Apertium provides: a translation engine, linguistic data for a variety of language pairs, and a host of tools for developers and users. Anyone with reasonable computing skills and with good translation skills can join the Apertium community and, in no time, find themselves contributing to the building of machine translation systems for a language pair. Apertium is particularly suitable for related-language pairs (such as Spanish→Portuguese or Czech→Slovak) where its shallow transfer technology suffices to produce posteditable translations, but is also being used for less-related language pairs in gisting applications. A nice side effect is the development of monolingual language processors (lemmatizers, part-of-speech taggers) which are available to help statistical machine translation deal with languages having a challenging morphology. Apertium is a mature technology and, for instance, it is currently being used by the Spanish Government to provide on-the fly machine translation for public-service webpages, by the regional newspaper Levante-EMV to generate a Catalan online edition, or by Wikipedia to offer a service to translate articles.
Translating your content into other languages is one of the greatest challenges in the technical communication process. We as technical communicators can meet these challenges with the combination of single-sourcing and localization. This presentation covers a combination of tools, best practices, tips and tricks for managing your localization projects.
Certainly! Here's a detailed 3000-word description of Python:
# Python: A Comprehensive Overview
Python is a high-level, versatile, and dynamically-typed programming language known for its simplicity and readability. Created by Guido van Rossum in the late 1980s, Python has since become one of the most popular programming languages worldwide. In this comprehensive overview, we will delve into the key aspects of Python, from its history and design philosophy to its syntax, libraries, and real-world applications.
## **History and Evolution of Python**
Python's history dates back to December 1989 when Guido van Rossum, a Dutch programmer, began working on it as a side project during his Christmas holidays. His aim was to create a language that emphasized code readability and allowed developers to express their ideas in fewer lines of code compared to other languages like C++ or Perl.
The first official Python release, Python 0.9.0, was released in February 1991. Python's name was inspired by Guido's love for the British comedy group Monty Python. Despite its humorous origins, Python quickly gained popularity in the software development community.
Python's major versions include Python 1.0 (1994), Python 2.0 (2000), Python 3.0 (2008), and the subsequent 3.x releases. The transition from Python 2 to Python 3 was a significant milestone in Python's history, as it involved breaking compatibility with Python 2 to introduce improvements and address some language inconsistencies. Python 2 reached its end of life on January 1, 2020, and Python 3 is now the standard and recommended version for new projects.
## **Design Philosophy: The Zen of Python**
Python's success can be attributed, in part, to its clear and guiding design principles, often referred to as "The Zen of Python" or "PEP 20" (Python Enhancement Proposal 20). These principles encapsulate the language's philosophy and provide a framework for writing clean, readable, and maintainable code. Some notable principles from "The Zen of Python" include:
- **Readability Counts:** Code should be easy to read and understand. Python's syntax enforces this with its use of indentation for block structure.
- **Simple is Better Than Complex:** Python encourages simplicity in both code design and implementation. It favors straightforward solutions over convoluted ones.
- **Explicit is Better Than Implicit:** Code should be explicit and not rely on hidden or magical behavior. This principle promotes code clarity and predictability.
- **There Should Be One-- and Preferably Only One --Obvious Way to Do It:** Python aims to provide a single, clear way to perform a specific task to reduce confusion and make code more consistent.
- **Errors Should Never Pass Silently:** Python encourages robust error handling and reporting to help developers identify and fix issues promptly.
## **Python Syntax and Language Features**
Python's syntax is known for its simplicity and readability. Here are some key languag
Python is a versatile and widely-used high-level programming language known for its simplicity, readability, and extensive library support. Created by Guido van Rossum and first released in 1991, Python has since gained immense popularity across various domains, including web development, data science, scientific computing, artificial intelligence, and more. In this comprehensive description, we'll delve into Python's history, features, applications, and its vibrant community, highlighting why it continues to be a preferred choice for developers worldwide.
Table of Contents
Introduction to Python
Python's History and Evolution
Python's Key Features
3.1. Readability and Simplicity
3.2. High-level Language
3.3. Interpreted and Dynamic
3.4. Cross-platform Compatibility
3.5. Rich Standard Library
3.6. Community Support
Python's Application Domains
4.1. Web Development
4.2. Data Science and Machine Learning
4.3. Scientific Computing
4.4. Automation and Scripting
4.5. Game Development
4.6. Desktop Applications
Python Development Environments
5.1. IDLE
5.2. PyCharm
5.3. Jupyter Notebook
5.4. Visual Studio Code
Getting Started with Python
6.1. Installing Python
6.2. Your First Python Program
Python Syntax and Basic Concepts
7.1. Variables and Data Types
7.2. Conditional Statements
7.3. Loops
7.4. Functions
7.5. Exception Handling
Working with Python Libraries
8.1. NumPy
8.2. Pandas
8.3. Matplotlib
8.4. Scikit-Learn
Python and Web Development
9.1. Frameworks (Django, Flask)
9.2. Front-end Integration (HTML/CSS)
9.3. Database Interaction (SQL, NoSQL)
Python in Data Science
10.1. Data Analysis with Pandas
10.2. Data Visualization with Matplotlib and Seaborn
10.3. Machine Learning with Scikit-Learn
10.4. Deep Learning with TensorFlow and PyTorch
Scientific Computing with Python
11.1. Scientific Libraries (SciPy, SymPy)
11.2. Plotting and Visualization (Matplotlib)
Automation and Scripting
12.1. Automating Tasks
12.2. Scripting for System Administration
Game Development with Python
13.1. Pygame
13.2. Unity and Unreal Engine Integration
Desktop Applications with Python
14.1. Tkinter
14.2. PyQt
Python's Ecosystem and Package Management
Python Best Practices
16.1. Code Readability (PEP 8)
16.2. Documentation and Comments
16.3. Testing (Unit Testing, pytest)
16.4. Version Control (Git)
Python's Future and Trends
Conclusion
1. Introduction to Python
Python is a general-purpose, high-level programming language that was designed with a focus on code readability and simplicity. It uses an elegant and straightforward syntax that makes it easy for developers to express their ideas effectively, reducing the cost of program maintenance. Python's philosophy emphasizes the importance of code clarity and readability, which is encapsulated in the Zen of Python (PEP 20).
The language has gained immense popularity due to its versatility and a rich ecosystem of libraries and frameworks. Python is renowned for its vibrant community and extensive documentation, making it in p
Localization for Agile Teams, presented by Dimitris Glezos (Transifex) and Patrick McLoughlin (Eventbrite).
TAUS Translation Technology Showcase, 14 October 2015, Santa Clara, CA
APTRON. As a leading training institute, APTRON offers comprehensive and industry-oriented Python training programs to help individuals enhance their skills and excel in the field of programming. Python has gained immense popularity in recent years due to its simplicity, versatility, and extensive range of applications. Whether a beginner or an experienced professional, APTRON's Python Training in Gurgaon caters to all skill levels, providing you with the knowledge and expertise needed to thrive in the competitive job market.
Querix 4 gl app analyzer 2016 journey to the center of your 4gl applicationBeGooden-IT Consulting
if you run and maintain an Informix 4GL application, the documentation of this project may be a hot topic for different reasons. Check this presentation and find the solution you really need
It is easy contributing to Open Source - ECLIPSE CON 2020César Hernández
The problem developers new to open source have is joining the community, starting to contribute, and using common open source tools. In this session, attendees will learn how to contribute and become valuable a part of any open source community. Attendees will learn soft and hard skills based on two case studies: Eclipse MicroProfile and Apache TomEE projects. Attendees will learn to access the culture of open source projects, expected behavior and attitude toward new contributors; how to start small, take risks, ask lots of questions; and how to get started with common open source tools like Maven, Git, and JIRA. Students will leave this workshop the soft skills and the hard skills required to make meaningful contributions.
Welcome to APTRON Solutions, your ultimate destination for Python Training in Gurgaon. Whether you're a beginner or an experienced programmer, our comprehensive Python courses are designed to equip you with the knowledge and skills needed to excel in the world of programming.Looking for the best Python training in Gurgaon? APTRON Solutions offers comprehensive Python courses tailored to beginners and professionals alike. Gain hands-on experience and become a skilled Python developer. Enroll today!
Lynx Webinar #4: Lynx Services Platform (LySP) - Part 2 - The ServicesLynx Project
Free Webinar on the Lynx Services Platform LySP: Architecture and basic Services
The main objective of the Lynx research and innovation project is to create an ecosystem of smart cloud services to better manage compliance, based on a Legal Knowledge Graph (LKG) which integrates and links multilingual and heterogeneous compliance data sources including legislation, case law, standards, regulations and other private contracts, beside others.
This webinar will provide insights into all smart services of the Lynx Services Platform (LySP) including demos of these LySP services, as for instance: Named Entity Extraction (NER) by DFKI, Relation Extraction and Question-Answering by SWC, Machine Translation by Tilde or the Lexicala cross-lingual lexical data service by KDictionaries.
Apertium is a free/open-source platform for rule-based machine translation which was started in 2005 and is developed collaboratively. Apertium provides: a translation engine, linguistic data for a variety of language pairs, and a host of tools for developers and users. Anyone with reasonable computing skills and with good translation skills can join the Apertium community and, in no time, find themselves contributing to the building of machine translation systems for a language pair. Apertium is particularly suitable for related-language pairs (such as Spanish→Portuguese or Czech→Slovak) where its shallow transfer technology suffices to produce posteditable translations, but is also being used for less-related language pairs in gisting applications. A nice side effect is the development of monolingual language processors (lemmatizers, part-of-speech taggers) which are available to help statistical machine translation deal with languages having a challenging morphology. Apertium is a mature technology and, for instance, it is currently being used by the Spanish Government to provide on-the fly machine translation for public-service webpages, by the regional newspaper Levante-EMV to generate a Catalan online edition, or by Wikipedia to offer a service to translate articles.
Translating your content into other languages is one of the greatest challenges in the technical communication process. We as technical communicators can meet these challenges with the combination of single-sourcing and localization. This presentation covers a combination of tools, best practices, tips and tricks for managing your localization projects.
Certainly! Here's a detailed 3000-word description of Python:
# Python: A Comprehensive Overview
Python is a high-level, versatile, and dynamically-typed programming language known for its simplicity and readability. Created by Guido van Rossum in the late 1980s, Python has since become one of the most popular programming languages worldwide. In this comprehensive overview, we will delve into the key aspects of Python, from its history and design philosophy to its syntax, libraries, and real-world applications.
## **History and Evolution of Python**
Python's history dates back to December 1989 when Guido van Rossum, a Dutch programmer, began working on it as a side project during his Christmas holidays. His aim was to create a language that emphasized code readability and allowed developers to express their ideas in fewer lines of code compared to other languages like C++ or Perl.
The first official Python release, Python 0.9.0, was released in February 1991. Python's name was inspired by Guido's love for the British comedy group Monty Python. Despite its humorous origins, Python quickly gained popularity in the software development community.
Python's major versions include Python 1.0 (1994), Python 2.0 (2000), Python 3.0 (2008), and the subsequent 3.x releases. The transition from Python 2 to Python 3 was a significant milestone in Python's history, as it involved breaking compatibility with Python 2 to introduce improvements and address some language inconsistencies. Python 2 reached its end of life on January 1, 2020, and Python 3 is now the standard and recommended version for new projects.
## **Design Philosophy: The Zen of Python**
Python's success can be attributed, in part, to its clear and guiding design principles, often referred to as "The Zen of Python" or "PEP 20" (Python Enhancement Proposal 20). These principles encapsulate the language's philosophy and provide a framework for writing clean, readable, and maintainable code. Some notable principles from "The Zen of Python" include:
- **Readability Counts:** Code should be easy to read and understand. Python's syntax enforces this with its use of indentation for block structure.
- **Simple is Better Than Complex:** Python encourages simplicity in both code design and implementation. It favors straightforward solutions over convoluted ones.
- **Explicit is Better Than Implicit:** Code should be explicit and not rely on hidden or magical behavior. This principle promotes code clarity and predictability.
- **There Should Be One-- and Preferably Only One --Obvious Way to Do It:** Python aims to provide a single, clear way to perform a specific task to reduce confusion and make code more consistent.
- **Errors Should Never Pass Silently:** Python encourages robust error handling and reporting to help developers identify and fix issues promptly.
## **Python Syntax and Language Features**
Python's syntax is known for its simplicity and readability. Here are some key languag
Python is a versatile and widely-used high-level programming language known for its simplicity, readability, and extensive library support. Created by Guido van Rossum and first released in 1991, Python has since gained immense popularity across various domains, including web development, data science, scientific computing, artificial intelligence, and more. In this comprehensive description, we'll delve into Python's history, features, applications, and its vibrant community, highlighting why it continues to be a preferred choice for developers worldwide.
Table of Contents
Introduction to Python
Python's History and Evolution
Python's Key Features
3.1. Readability and Simplicity
3.2. High-level Language
3.3. Interpreted and Dynamic
3.4. Cross-platform Compatibility
3.5. Rich Standard Library
3.6. Community Support
Python's Application Domains
4.1. Web Development
4.2. Data Science and Machine Learning
4.3. Scientific Computing
4.4. Automation and Scripting
4.5. Game Development
4.6. Desktop Applications
Python Development Environments
5.1. IDLE
5.2. PyCharm
5.3. Jupyter Notebook
5.4. Visual Studio Code
Getting Started with Python
6.1. Installing Python
6.2. Your First Python Program
Python Syntax and Basic Concepts
7.1. Variables and Data Types
7.2. Conditional Statements
7.3. Loops
7.4. Functions
7.5. Exception Handling
Working with Python Libraries
8.1. NumPy
8.2. Pandas
8.3. Matplotlib
8.4. Scikit-Learn
Python and Web Development
9.1. Frameworks (Django, Flask)
9.2. Front-end Integration (HTML/CSS)
9.3. Database Interaction (SQL, NoSQL)
Python in Data Science
10.1. Data Analysis with Pandas
10.2. Data Visualization with Matplotlib and Seaborn
10.3. Machine Learning with Scikit-Learn
10.4. Deep Learning with TensorFlow and PyTorch
Scientific Computing with Python
11.1. Scientific Libraries (SciPy, SymPy)
11.2. Plotting and Visualization (Matplotlib)
Automation and Scripting
12.1. Automating Tasks
12.2. Scripting for System Administration
Game Development with Python
13.1. Pygame
13.2. Unity and Unreal Engine Integration
Desktop Applications with Python
14.1. Tkinter
14.2. PyQt
Python's Ecosystem and Package Management
Python Best Practices
16.1. Code Readability (PEP 8)
16.2. Documentation and Comments
16.3. Testing (Unit Testing, pytest)
16.4. Version Control (Git)
Python's Future and Trends
Conclusion
1. Introduction to Python
Python is a general-purpose, high-level programming language that was designed with a focus on code readability and simplicity. It uses an elegant and straightforward syntax that makes it easy for developers to express their ideas effectively, reducing the cost of program maintenance. Python's philosophy emphasizes the importance of code clarity and readability, which is encapsulated in the Zen of Python (PEP 20).
The language has gained immense popularity due to its versatility and a rich ecosystem of libraries and frameworks. Python is renowned for its vibrant community and extensive documentation, making it in p
Localization for Agile Teams, presented by Dimitris Glezos (Transifex) and Patrick McLoughlin (Eventbrite).
TAUS Translation Technology Showcase, 14 October 2015, Santa Clara, CA
APTRON. As a leading training institute, APTRON offers comprehensive and industry-oriented Python training programs to help individuals enhance their skills and excel in the field of programming. Python has gained immense popularity in recent years due to its simplicity, versatility, and extensive range of applications. Whether a beginner or an experienced professional, APTRON's Python Training in Gurgaon caters to all skill levels, providing you with the knowledge and expertise needed to thrive in the competitive job market.
Querix 4 gl app analyzer 2016 journey to the center of your 4gl applicationBeGooden-IT Consulting
if you run and maintain an Informix 4GL application, the documentation of this project may be a hot topic for different reasons. Check this presentation and find the solution you really need
It is easy contributing to Open Source - ECLIPSE CON 2020César Hernández
The problem developers new to open source have is joining the community, starting to contribute, and using common open source tools. In this session, attendees will learn how to contribute and become valuable a part of any open source community. Attendees will learn soft and hard skills based on two case studies: Eclipse MicroProfile and Apache TomEE projects. Attendees will learn to access the culture of open source projects, expected behavior and attitude toward new contributors; how to start small, take risks, ask lots of questions; and how to get started with common open source tools like Maven, Git, and JIRA. Students will leave this workshop the soft skills and the hard skills required to make meaningful contributions.
Welcome to APTRON Solutions, your ultimate destination for Python Training in Gurgaon. Whether you're a beginner or an experienced programmer, our comprehensive Python courses are designed to equip you with the knowledge and skills needed to excel in the world of programming.Looking for the best Python training in Gurgaon? APTRON Solutions offers comprehensive Python courses tailored to beginners and professionals alike. Gain hands-on experience and become a skilled Python developer. Enroll today!
Similar to Apertium: a unique free/open-source MT system for related languages [but not only] (20)
State of ICS and IoT Cyber Threat Landscape Report 2024 previewPrayukth K V
The IoT and OT threat landscape report has been prepared by the Threat Research Team at Sectrio using data from Sectrio, cyber threat intelligence farming facilities spread across over 85 cities around the world. In addition, Sectrio also runs AI-based advanced threat and payload engagement facilities that serve as sinks to attract and engage sophisticated threat actors, and newer malware including new variants and latent threats that are at an earlier stage of development.
The latest edition of the OT/ICS and IoT security Threat Landscape Report 2024 also covers:
State of global ICS asset and network exposure
Sectoral targets and attacks as well as the cost of ransom
Global APT activity, AI usage, actor and tactic profiles, and implications
Rise in volumes of AI-powered cyberattacks
Major cyber events in 2024
Malware and malicious payload trends
Cyberattack types and targets
Vulnerability exploit attempts on CVEs
Attacks on counties – USA
Expansion of bot farms – how, where, and why
In-depth analysis of the cyber threat landscape across North America, South America, Europe, APAC, and the Middle East
Why are attacks on smart factories rising?
Cyber risk predictions
Axis of attacks – Europe
Systemic attacks in the Middle East
Download the full report from here:
https://sectrio.com/resources/ot-threat-landscape-reports/sectrio-releases-ot-ics-and-iot-security-threat-landscape-report-2024/
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. What’s changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
JMeter webinar - integration with InfluxDB and GrafanaRTTS
Watch this recorded webinar about real-time monitoring of application performance. See how to integrate Apache JMeter, the open-source leader in performance testing, with InfluxDB, the open-source time-series database, and Grafana, the open-source analytics and visualization application.
In this webinar, we will review the benefits of leveraging InfluxDB and Grafana when executing load tests and demonstrate how these tools are used to visualize performance metrics.
Length: 30 minutes
Session Overview
-------------------------------------------
During this webinar, we will cover the following topics while demonstrating the integrations of JMeter, InfluxDB and Grafana:
- What out-of-the-box solutions are available for real-time monitoring JMeter tests?
- What are the benefits of integrating InfluxDB and Grafana into the load testing stack?
- Which features are provided by Grafana?
- Demonstration of InfluxDB and Grafana using a practice web application
To view the webinar recording, go to:
https://www.rttsweb.com/jmeter-integration-webinar
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
Generating a custom Ruby SDK for your web service or Rails API using Smithyg2nightmarescribd
Have you ever wanted a Ruby client API to communicate with your web service? Smithy is a protocol-agnostic language for defining services and SDKs. Smithy Ruby is an implementation of Smithy that generates a Ruby SDK using a Smithy model. In this talk, we will explore Smithy and Smithy Ruby to learn how to generate custom feature-rich SDKs that can communicate with any web service, such as a Rails JSON API.
UiPath Test Automation using UiPath Test Suite series, part 4DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 4. In this session, we will cover Test Manager overview along with SAP heatmap.
The UiPath Test Manager overview with SAP heatmap webinar offers a concise yet comprehensive exploration of the role of a Test Manager within SAP environments, coupled with the utilization of heatmaps for effective testing strategies.
Participants will gain insights into the responsibilities, challenges, and best practices associated with test management in SAP projects. Additionally, the webinar delves into the significance of heatmaps as a visual aid for identifying testing priorities, areas of risk, and resource allocation within SAP landscapes. Through this session, attendees can expect to enhance their understanding of test management principles while learning practical approaches to optimize testing processes in SAP environments using heatmap visualization techniques
What will you get from this session?
1. Insights into SAP testing best practices
2. Heatmap utilization for testing
3. Optimization of testing processes
4. Demo
Topics covered:
Execution from the test manager
Orchestrator execution result
Defect reporting
SAP heatmap example with demo
Speaker:
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Apertium: a unique free/open-source MT system for related languages [but not only]
1. #LocWorld34
Apertium: a Unique
Free/Open-Source MT System
for Related Languages
[but not only]
Gema Ramírez Sánchez1
Mikel L. Forcada1,2
1
Prompsit Language Engineering, Elx, Spain
1,2
Universitat d’Alacant, Alacant, Spain
2. #LocWorld34
Outline
● Apertium components
● Ready-to-use Apertium products
● Machine translation — but not only!
● Licensing — free/open-source
● The Apertium community
● Research and business with Apertium
● Languages and language pairs
● Success cases
● Funding
4. #LocWorld34
Apertium components: the
engine /1
● A fast, free/open-source, modular,
shallow-transfer, language-independent
machine translation engine with:
○ text format management,
○ translation memory querying,
○ finite-state lexical processing,
○ statistical and constraint-based lexical
disambiguation, and
○ shallow structural transfer based on
finite-state pattern matching
5. #LocWorld34
Apertium components: the
engine /2
● Most of the engine was developed inside the
Apertium project but some external
technologies are used:
○ Helsinki Finite-State toolkit (for some
morphologically-rich languages),
○ VISL CG-3 (constraint grammars for
rule-based lexical disambiguation).
6. #LocWorld34
Apertium components: the data
● Free/open-source language data in
well-specified XML formats for a variety of
languages and language pairs.
7. #LocWorld34
Apertium components: the data.
A typical language pair
Language pair organization
2 monolingual packages (A, B)
▪ 1 monolingual dictionary
(monodix)
▪ 1 tagset + probabilities
▪ 1 plain/tagged corpus
▪ 1 postgeneration “dictionary”
1 bilingual package (A–B)
▪ 1 bilingual dictionary
(bidix)
▪ 2 sets of structural transfer
(grammar) rules (levels 1–3)
Format: typically XML-based (sometimes text-based) files
Sizes:
Monodixes: 10k–90k lemmata; 100k–23M surf. forms, 85–97% cover.
Bidixes: 8k--–90k bilingual lema correspondences
Rules: 100 (one level) – 300 (3 level) per translation direction
8. #LocWorld34
Apertium components: the
tools
● Free/open-source tools:
○ compilers to turn linguistic data into a fast
and compact form used by the engine
and
○ software to learn disambiguation or
translation rules from corpora.
9. #LocWorld34
Ready-to-use Apertium
products
● A stand-alone Java application for the
desktop: apertium-caffeine.
● An Android version for handhelds.
● A stand-alone version (Apertium Simpleton)
for Windows and MacOS.
● Plug-ins and support for CAT platforms:
OmegaT, MateCat, MemoQ, Trados Studio.
● Available as a PPA repository for GNU/Linux
users.
12. #LocWorld34
No need to install: web access
www.apertium.org
● Text box: short plain texts
● Document translation:
○ plain text
○ HTML, XML (.xliff)
○ OpenDocument (.odt, .odp, .ods)
○ Office “-x” formats: .docx, .xlsx, .pptx
○ LaTeX
● A nice feature: with/without marks for
unknown words
13. #LocWorld34
No need to install: web/API
access
● Other portals with all Apertium languages:
○ Prompsit’s portal: + TMX +
navigate&translate
○ iTranslate4.eu portal: multiengine
● Other portals with some Apertium languages:
○ UOC, UPV, UA (+ TMX + terminology support
+ more formats)
○ GiellaTekno portal
○ etc.
● Also API access and connectors to translation
tools are marketed
15. #LocWorld34
Machine translation — but
not only! /2
Monodix
Tagset+prob
Rules
Monodix
Bidix
t
o
o
l
s
t
o
o
l
s
Post-dix
Morphological
analyser
PoS tagger
Lexical transfer
Full MT
Morphological
generator
Structural transfer
Post-generator
16. #LocWorld34
Machine translation — but
not only! /3
● Apertium is a rule-based machine translation
system but the pipeline contains many
monolingual modules that can be used for other
human-language technology tasks (such as
anonymization or factored output)
● Most modules are based on finite-state
technology; HMMs are used for part-of-speech
tagging and an interpreted language is used to
write structural transfer rules.
17. #LocWorld34
Licensing: free/open-source /1
Apertium language data and code are both
licensed under the GNU General Public License:
● a free/open-source license allowing free
distribution of unmodified and modified
versions
● a copylefted license: it avoids private
appropriation and encourages giving
improvements back to the project (it creates
a software commons).
18. #LocWorld34
Licensing: free/open-source /2
● The free/open-source model creates a
community which effectively connects
researchers, developers, vendors, and users
in a continuum.
19. #LocWorld34
The Apertium community
● Very active group of hundreds of developers
● Contributions to Apertium at Sourceforge
● Wiki documentation (wiki.apertium.org)
● Easy entry: Apertium linguistic modelling is
simple, no need to program.
● IRC channel #apertium in freenode.net
● Mailing lists: apertium-stuff@lists.sf.net and
other lists
23. #LocWorld34
The Apertium community:
activities
● President and project management
committee election according to bylaws
● Support: mail, chat, online meetings
● Maintenance: pairs, web, mobile app
● Manuals & documentation: wiki, manuals,
how-to’s, training materials
● Organization of Google Summer of Code and
Google Code-In activity
● Outreach activities: conferences, workshops
● Language-related groups
24. #LocWorld34
Research and business with
Apertium
Apertium is already an active research and
business platform:
● Research: 40+ publications, 2 PhD thesis, 4
master's theses.
● Business: companies (Prompsit, Eleka,
Imaxin Software, etc.) offering services to
customers such as Autodesk, Adobe, the
Government of Catalonia, 2 daily newspapers
in Spain, freelancers and LSPs
25. #LocWorld34
Languages and language pairs
/1
● Language data is encoded mostly in XML,
but some language pairs contain data
encoded in other text-based formats.
● Stable language pairs (bilingual data) are
currently more than 40.
28. #LocWorld34
Languages and language pairs
/4
Year Milestone Language pairs
2004 The Spanish Ministry of Industry funds a consortium
to build FOSS MT for the languages of Spain ----------------------------
2005 Apertium RBMT plaftorm is launched providing
engine, tools and data under free licenses
3 pairs: es–ca, es–gl
and es–pt
2005-2009 Language pair-driven innovation, still very
European-focused language pairs
+19: fr, en, eo, ro, eu,
oc, cy, nn, nb, sv, da, is,
mk, bg, ast, br
2010 Five years on! 22 pairs!!!
2011-2015 Consolidated community, support for non-European
languages, new tools and reorganisation of data
+19: af, nl, hr, sr, mt, sl,
arg, sme, urd, hin, kaz,
tat, id, ms, ar
2017 Twelve years on! 43 pairs!!!
29. #LocWorld34
Apertium loves small
languages
● Breton→French
● Aragonese↔Spanish/Catalan
● Occitan↔Catalan/Spanish
● Italian→Sardinian
● North Sámi↔Norwegian
● Icelandic↔Swedish
● Spanish→Spanish Sign Language
30. #LocWorld34
Language pairs with approx.
95% text coverage
Language Lemmata Inflection models Surface forms
HBS 97,445 1,429 23,348,650
English 60,543 312 108,119
Spanish 46,003 442 4,737,777
Catalan 41,116 559 7,088,585
Galician 29,818 333 14,247,591
Asturian 46,550 443 18,541,752
Occitan 21,602 527 6,084,575
Aragonese 26,068 544 12,870,976
Portuguese 14,436 316 10,514,672
31. #LocWorld34
Apertium language-pair
life cycles
● For new pairs:
○ resource compilation
○ basic system creation (85% coverage, most
frequent structural phenomena)
○ evaluation
○ typically takes 3–6 months
● For existing pairs:
○ testing, enhancement, evaluation
○ typically takes 1–3 months
32. #LocWorld34
A related-languages pair
performance: apertium-es-pt
From Masselot et al., 2010 (Using the Apertium
Spanish–Brazilian Portuguese MT system for
localization):
● Post-editing effort (word error rate): 20%
● Post-editing speed: average 4,500 words/day
Updated 2017 (also for software localisation):
● Post-editing effort (word error rate): 14%
● Post-editing speed: average 6,500 words/day
34. #LocWorld34
Related language-pair
post-editing experience /2
Original Spanish Apertium output Portuguese final
Cree documentación
y dibujos 2D con un
completo conjunto
de herramientas de
dibujo, edición y
anotación.
Crê documentação e
desenhos 2D com
um completo
conjunto de
ferramentas de
desenho, edição e
anotação.
Produza desenhos e
documentação 2D
com um conjunto
abrangente de
ferramentas de
desenho, edição e
anotação.
Apertium output for closely-related languages is:
● Easy and fast to post-edit
● Rather mechanical, but reliable
● Predictable
35. #LocWorld34
Nearby LocWorld Barcelona...
● Apertium makes two daily newspaper
bilingual: Levante (Catalan) and La Voz de
Galicia (Galician).
● Universities in the Catalan speaking area
use Apertium to help in the generation of
courseware and academic information;
● Apertium is used in PLATA, the Spanish
government platform for webpage
translation.
Some success cases /1
36. #LocWorld34
Also by-products:
● Same-language machine translation for
local flavours/flavors: AltLang.net
○ available for English, Spanish, French and
Portuguese varieties.
○ performs spelling, lexical, grammar and
style changes.
Some success cases /2
Based on Apertium
38. #LocWorld34
Wikimedia Content Translation
into Norwegian Nynorsk
Co-funded project on MT
for Scandinavian
languages including
community outreach starts
Most of the translations are
from Norwegian Bokmål.
85% are done using Apertium.
40. #LocWorld34
● Translators Without Borders develop
crisis-specific, portable machine translation
from English to Kurdish languages (Kurmanji,
Sorani) on Apertium.
● Apertium and language experts help promote a
unified standard for Occitan by defining and
selecting it for Spanish→Occitan and
Catalan→Occitan MT
Other success cases involving
interaction with other
communities
41. #LocWorld34
Funding /1
● The Ministry of Industry, Tourism and
Commerce of Spain (also, the Ministries of
Education and Science and of Science and
Technology of Spain)
● The Secretariat for Technology and the
Information Society of the Government of
Catalonia
● The European Commission (DGT training and
Abu-Matran project)
● The Ministry of Foreign Affairs of Romania
42. #LocWorld34
Funding /2
● Universitat d'Alacant and Universitat Oberta
de Catalunya
● Ofis Publik ar Brezhoneg (Breton Language
Board)
● Ministry of Education and Science of the
Republic of Kazakhstan
● Google Summer of Code scholarships
(2009–2014, 2016, 2017) and Google Code-In
donations (2010–2016).
● And many other private companies
43. #LocWorld34
● If you want to build, integrate, or customize
fast, reliable, predictable machine translation for
your application.
● If you’d rather understand application-oriented
dictionaries and rules rather than deal with the
“magic” of embeddings, decoders, phrase tables,
convolutions, or probabilities.
● If there’s no way you can amass and curate
millions of translated words to train a system
for your language or application.
Then come and talk to us
(we are at booth 121).
You can be part of it!