Descripción del funcionamiento de una empresa de traducción, departamentos y procesos, tomando a www.pangeanic.es como ejemplo. Descripción de funciones, normas y flujo de trabajo con un énfasis en los procesos de traducción automática.
Pangeanic Cor-ActivaTM-Neural machine translation Taus Tokyo 2017Manuel Herranz
Presentation of Pangeanic language technologies as a result of EU and national R&D: Cor for web crawling and website translation, linked to Elastic Search-based ActivaTM and NeuralMT
Gestión proyectos traducción - Universitat Autònoma de BarcelonaManuel Herranz
Presentación sobre el modelo de gestión de proyectos en una empresa de traducción, sirviendo www.pangeanic.es como ejemplo. Descripción de departamentos y procesos.
First came rule-based machine translation, then the explosion of statistical engines, and the combination of rules and statistics with hybrid MT. But what's next? Deep learning is now everywhere in natural language processing, and Machine Translation is no exception. In this talk, we will present a practical scenario where statistical machine translation is compared to neural machine translation, and we will give hints on when and how to implement this new technology in real translation/localization process.
This presentation was given at various events in June 2017 on the current status of Neural Machine Translation development at Iconic.
Rule based, statistical, hybrid, neural - at the end of the day it's all machine translation. At Iconic, we've been "doing neural" for over 12 months in various guises but, frequently, we find that our clients don't care what we use once we get the job done. In these slides, we go through a number of case studies involving MT and show how fit for purpose translations were delivered, combining various different approaches to MT.
Past, Present, and Future: Machine Translation & Natural Language Processing ...John Tinsley
This was a presentation given at the European Patent Office's annual Patent Information Conference in Madrid, Spain on November 10th, 2016.
In it, we give an overview of how machine translation works, latest advances in neural MT, and how this can be applied to patents and intellectual property content, not only for translations but also information extraction and other NLP applications.
Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of transfer learning methods and architectures which significantly improved upon the state-of-the-art on pretty much every NLP tasks.
The wide availability and ease of integration of these transfer learning models are strong indicators that these methods will become a common tool in the NLP landscape as well as a major research direction.
In this talk, I'll present a quick overview of modern transfer learning methods in NLP and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks, focusing on open-source solutions.
Website: https://fwdays.com/event/data-science-fwdays-2019/review/transfer-learning-in-nlp
Methods for Handling Terminology in Machine TranslationKerstin Berns
Im Vortrag werden Möglichkeiten und Vor- und Nachteile verschiedener MÜ-Lösungen in der SDL-Language-Cloud vorgestellt. Besonderes Interesse weckt die sogenannte Adaptive MT, eine spezieller MÜ-System-Typ, welcher durch kontinuierliche Korrekturen bzw. nutzerspezifische Anpassungen von MÜ-Vorschlägen lernt, indem die Post-Edits des Nutzers zur Optimierung der Engine benutzt werden. Eine Technik, die auch im Rahmen der neuralen maschinellen Übersetzung bei SDL noch eine wichtige Rolle spielen wird.
Veranstaltung: ETUG 2017, Nürnberg
Pangeanic Cor-ActivaTM-Neural machine translation Taus Tokyo 2017Manuel Herranz
Presentation of Pangeanic language technologies as a result of EU and national R&D: Cor for web crawling and website translation, linked to Elastic Search-based ActivaTM and NeuralMT
Gestión proyectos traducción - Universitat Autònoma de BarcelonaManuel Herranz
Presentación sobre el modelo de gestión de proyectos en una empresa de traducción, sirviendo www.pangeanic.es como ejemplo. Descripción de departamentos y procesos.
First came rule-based machine translation, then the explosion of statistical engines, and the combination of rules and statistics with hybrid MT. But what's next? Deep learning is now everywhere in natural language processing, and Machine Translation is no exception. In this talk, we will present a practical scenario where statistical machine translation is compared to neural machine translation, and we will give hints on when and how to implement this new technology in real translation/localization process.
This presentation was given at various events in June 2017 on the current status of Neural Machine Translation development at Iconic.
Rule based, statistical, hybrid, neural - at the end of the day it's all machine translation. At Iconic, we've been "doing neural" for over 12 months in various guises but, frequently, we find that our clients don't care what we use once we get the job done. In these slides, we go through a number of case studies involving MT and show how fit for purpose translations were delivered, combining various different approaches to MT.
Past, Present, and Future: Machine Translation & Natural Language Processing ...John Tinsley
This was a presentation given at the European Patent Office's annual Patent Information Conference in Madrid, Spain on November 10th, 2016.
In it, we give an overview of how machine translation works, latest advances in neural MT, and how this can be applied to patents and intellectual property content, not only for translations but also information extraction and other NLP applications.
Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of transfer learning methods and architectures which significantly improved upon the state-of-the-art on pretty much every NLP tasks.
The wide availability and ease of integration of these transfer learning models are strong indicators that these methods will become a common tool in the NLP landscape as well as a major research direction.
In this talk, I'll present a quick overview of modern transfer learning methods in NLP and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks, focusing on open-source solutions.
Website: https://fwdays.com/event/data-science-fwdays-2019/review/transfer-learning-in-nlp
Methods for Handling Terminology in Machine TranslationKerstin Berns
Im Vortrag werden Möglichkeiten und Vor- und Nachteile verschiedener MÜ-Lösungen in der SDL-Language-Cloud vorgestellt. Besonderes Interesse weckt die sogenannte Adaptive MT, eine spezieller MÜ-System-Typ, welcher durch kontinuierliche Korrekturen bzw. nutzerspezifische Anpassungen von MÜ-Vorschlägen lernt, indem die Post-Edits des Nutzers zur Optimierung der Engine benutzt werden. Eine Technik, die auch im Rahmen der neuralen maschinellen Übersetzung bei SDL noch eine wichtige Rolle spielen wird.
Veranstaltung: ETUG 2017, Nürnberg
Machine Translation: The Neural FrontierJohn Tinsley
This was a pitch for Iconic's neural machine translation technology given at the TAUS Annual Conference in Portland, Oregan on October 24th, 2016.
There has been a lot of talk, and a lot of hype about neural machine translation in the press. But not a lot of practical application. Let's change the conversation
Delivered at the European Patent Office's Patent Information Conference.
November 11th 2015
Miami, Florida.
In this talk, we talk about recent advances in MT for patents and introduce our IPTranslator.com application for on-demand translation.
New Breakthroughs in Machine Transation Technologykantanmt
Tony O’Dowd takes us through some of the most innovative technologies offered on the KantanMT.com platform which are helping a growing community of KantanMT users to develop and self-manage custom Machine Translation engines in the cloud.
Maxim Khalilov then illustrates bmmt’s journey with Machine Translation on KantanMT. He discusses what they have achieved so far in terms of MT engine development and showcases the value that his team is bringing to their growing international client base through the use of Machine Translation.
Our statistical machine translation platform and hybrid features were presented at the European Commission offices in Luxembourg last Tuesday 22nd September. It is one of the tools that the European Union will consider, among other machine translation commercial solutions, as a tool to help its mandate for CEF (Connecting Europe Facility). Pangeanic’s CEO, Manuel Herranz, presented the current state-of-the-art that PangeaMT version 3 represents. Representatives from the EU were particularly interested in the solid data management features, machine translation engine retraining routines, data cleaning and automated engine training and creation features. One of key features with the new PangeaMT version is the possibility to change translation algorithms and use rule-based systems like Apertium and Thot as well as the default Moses. It is also compatible with 3rd-party calls from other systems. Its powerful API can also provide machine translated output to requests anywhere in the world, although the platform is designed for onsite use at translation companies and organizations. PangeaMT is also compatible with several popular translation formats like ttx, sdlxliff, memoq, memsource, and most xml-based Tikal formats.
Python vs MATLAB: Which one is the best languageStat Analytica
Let's find out which one is a better language for statistics. Here we have the best ever comparison between Python vs Matlab. Get to know which one is better and why we should use it?
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"Fwdays
In this talk I'll start by introducing the recent breakthroughs in NLP that resulted from the combination of Transfer Learning schemes and Transformer architectures. The second part of the talk will be dedicated to an introduction of the open-source tools released by Hugging Face, in particular our transformers, tokenizers, and NLP libraries as well as our distilled and pruned models.
5 challenges of scaling l10n workflows KantanMT/bmmt webinarkantanmt
In this joint presentation, Tony O’Dowd, Founder and Chief Architect of KantanMT and Maxim Khalilov, Technical Lead of bmmt deliver an overview of the MT technology currently available in the language technology market, the challenges of operating MT systems at scale and speed, and their opinions on the future trajectory of MT.
Each presentation will be grounded with client examples, and how they’ve successfully integrated MT into their localization workflows.
Finally, both presenters will finish off with a 5 point checklist for successful MT deployment based on both the MT provider and LSP point of view.
If you have any questions about this presentation or want to get in touch with either company please contact:
Louise Irwin, Marketing Specialist at KantanMT (louisei@kantanmt.com)
Peggy Linder, Operations Manager at bmmt (peggy.lindner@bmmt.eu)
New web-based statistical machine translation services are currently revolutionizing the market. These SaaS solutions allow users to customize an MT engine with their own translation memories. As most of these services follow the subscription model, launching a DIY MT project costs only a fraction of deploying a traditional machine translation tool, which makes this powerful technology affordable for even the smallest organization.
Webinar automotive and engineering content 16.06.16kantanmt
High quality translations that are delivered quickly are a result of a seamless and efficient translation process, but getting to this stage requires a well thought out plan, rigorous content preprocessing techniques and most importantly, clear and transparent communication between the automated translation vendor and language service provider.
In this webinar, Christian Taube and Brian Coyle discusses how the Matrix and KantanMT partnership delivers a high quality, scalable solution that increases translation productivity and supports engineering and automotive terminology standards. The webinar uses specific case study examples including a discussion on what types of content to focus on and preparing and managing Translation Memory data. Discussion includes:
• Managing content for best results
• Preparing TM data
• Tools that generate high quality results
Delivered at the 29th LocWorld conference.
October 16th 2015
Santa Clara, CA, USA.
In this talk, we describe how we carried out a successful large scale evaluation and deployment of machine translation at RWS.
Pangea Machine Translation platform from Pangeanic. A product presentation by Manuel Herranz, Elia Yuste, Andi Frank showcasing the best of automated cleaning cycles, automated engine retraining, machine translation engine creation.
MT best practices for price, speed AND quality, as well as Lexcelera’s machine translation case studies and services including training, integration, post-editing and hosted MT
Machine Translation: The Neural FrontierJohn Tinsley
This was a pitch for Iconic's neural machine translation technology given at the TAUS Annual Conference in Portland, Oregan on October 24th, 2016.
There has been a lot of talk, and a lot of hype about neural machine translation in the press. But not a lot of practical application. Let's change the conversation
Delivered at the European Patent Office's Patent Information Conference.
November 11th 2015
Miami, Florida.
In this talk, we talk about recent advances in MT for patents and introduce our IPTranslator.com application for on-demand translation.
New Breakthroughs in Machine Transation Technologykantanmt
Tony O’Dowd takes us through some of the most innovative technologies offered on the KantanMT.com platform which are helping a growing community of KantanMT users to develop and self-manage custom Machine Translation engines in the cloud.
Maxim Khalilov then illustrates bmmt’s journey with Machine Translation on KantanMT. He discusses what they have achieved so far in terms of MT engine development and showcases the value that his team is bringing to their growing international client base through the use of Machine Translation.
Our statistical machine translation platform and hybrid features were presented at the European Commission offices in Luxembourg last Tuesday 22nd September. It is one of the tools that the European Union will consider, among other machine translation commercial solutions, as a tool to help its mandate for CEF (Connecting Europe Facility). Pangeanic’s CEO, Manuel Herranz, presented the current state-of-the-art that PangeaMT version 3 represents. Representatives from the EU were particularly interested in the solid data management features, machine translation engine retraining routines, data cleaning and automated engine training and creation features. One of key features with the new PangeaMT version is the possibility to change translation algorithms and use rule-based systems like Apertium and Thot as well as the default Moses. It is also compatible with 3rd-party calls from other systems. Its powerful API can also provide machine translated output to requests anywhere in the world, although the platform is designed for onsite use at translation companies and organizations. PangeaMT is also compatible with several popular translation formats like ttx, sdlxliff, memoq, memsource, and most xml-based Tikal formats.
Python vs MATLAB: Which one is the best languageStat Analytica
Let's find out which one is a better language for statistics. Here we have the best ever comparison between Python vs Matlab. Get to know which one is better and why we should use it?
Thomas Wolf "An Introduction to Transfer Learning and Hugging Face"Fwdays
In this talk I'll start by introducing the recent breakthroughs in NLP that resulted from the combination of Transfer Learning schemes and Transformer architectures. The second part of the talk will be dedicated to an introduction of the open-source tools released by Hugging Face, in particular our transformers, tokenizers, and NLP libraries as well as our distilled and pruned models.
5 challenges of scaling l10n workflows KantanMT/bmmt webinarkantanmt
In this joint presentation, Tony O’Dowd, Founder and Chief Architect of KantanMT and Maxim Khalilov, Technical Lead of bmmt deliver an overview of the MT technology currently available in the language technology market, the challenges of operating MT systems at scale and speed, and their opinions on the future trajectory of MT.
Each presentation will be grounded with client examples, and how they’ve successfully integrated MT into their localization workflows.
Finally, both presenters will finish off with a 5 point checklist for successful MT deployment based on both the MT provider and LSP point of view.
If you have any questions about this presentation or want to get in touch with either company please contact:
Louise Irwin, Marketing Specialist at KantanMT (louisei@kantanmt.com)
Peggy Linder, Operations Manager at bmmt (peggy.lindner@bmmt.eu)
New web-based statistical machine translation services are currently revolutionizing the market. These SaaS solutions allow users to customize an MT engine with their own translation memories. As most of these services follow the subscription model, launching a DIY MT project costs only a fraction of deploying a traditional machine translation tool, which makes this powerful technology affordable for even the smallest organization.
Webinar automotive and engineering content 16.06.16kantanmt
High quality translations that are delivered quickly are a result of a seamless and efficient translation process, but getting to this stage requires a well thought out plan, rigorous content preprocessing techniques and most importantly, clear and transparent communication between the automated translation vendor and language service provider.
In this webinar, Christian Taube and Brian Coyle discusses how the Matrix and KantanMT partnership delivers a high quality, scalable solution that increases translation productivity and supports engineering and automotive terminology standards. The webinar uses specific case study examples including a discussion on what types of content to focus on and preparing and managing Translation Memory data. Discussion includes:
• Managing content for best results
• Preparing TM data
• Tools that generate high quality results
Delivered at the 29th LocWorld conference.
October 16th 2015
Santa Clara, CA, USA.
In this talk, we describe how we carried out a successful large scale evaluation and deployment of machine translation at RWS.
Pangea Machine Translation platform from Pangeanic. A product presentation by Manuel Herranz, Elia Yuste, Andi Frank showcasing the best of automated cleaning cycles, automated engine retraining, machine translation engine creation.
MT best practices for price, speed AND quality, as well as Lexcelera’s machine translation case studies and services including training, integration, post-editing and hosted MT
This presentation is a part of the MosesCore project that encourages the development and usage of open source machine translation tools, notably the Moses statistical MT toolkit. MosesCore is supported by the European Commission Grant Number 288487 under the 7th Framework Programme.
For the latest updates go to http://www.statmt.org/mosescore/
or follow us on Twitter - #MosesCore
This presentation is a part of the MosesCore project that encourages the development and usage of open source machine translation tools, notably the Moses statistical MT toolkit. MosesCore is supported by the European Commission Grant Number 288487 under the 7th Framework Programme.
For the latest updates go to http://www.statmt.org/mosescore/
or follow us on Twitter - #MosesCore
Working with MOSES and building high quality MT systems is not for the faint hearted. It requires a wide range of technical and linguistic based knowledge that is often difficult to find and develop within organisations. Consequently, only the biggest organisations have the financial muscle to invest and reap the awards of MT. This puts the small-to-medium sized organisations at a distinct disadvantage. KantanMT changes everything! KantanMT is a cloud-based implementation of MOSES which enables SMEs to embrace the advantages of MT - quickly and economically. This presentation will demonstrate the KantanMT approach to rapid engine training and tuning, data analytics used to predict MT quality and create tiered pricing structures and instantaneous engine deployment - all of which are driving the new MT Revolution!
Microservices and Prometheus (Microservices NYC 2016)Brian Brazil
If you'd like to learn more about Prometheus, contact us at prometheus@robustperception.io or follow us on twitter at https://twitter.com/RobustPerceiver
Prometheus is a next-generation monitoring system designed for microservices. This talk will look at what's the best way to monitor your microservices, which metrics you should care about, how to have useful alerts and how Prometheus empowers you to do things the right way.
Managing Translation Memories for Engineering and Automotive TranslationPoulomi Choudhury
High quality translations that are delivered quickly are a result of a seamless and efficient translation process, but getting to this stage requires a well thought out plan, rigorous content preprocessing techniques and most importantly, clear and transparent communication between the automated translation vendor and language service provider.
In this webinar, Christian Taube and Brian Coyle discusses how the Matrix and KantanMT partnership delivers a high quality, scalable solution that increases translation productivity and supports engineering and automotive terminology standards. The webinar uses specific case study examples including a discussion on what types of content to focus on and preparing and managing Translation Memory data. Discussion includes:
• Managing content for best results
• Preparing TM data
• Tools that generate high quality results
WeMT Tools and Processes Welocalize TAUS Showcase October 2013 Localization W...Welocalize
WeMT Tools and Processes, a presentation by Olga Beregovaya at Localization World 2013 in Silicon Valley. Presented during TAUS Showcase. Discussion of automation and machine translation programs. Welocalize is the leader in localization and translation solutions.
4 European machine translation companies joined forces to build something bigger than themselves: an intelligent platform capable of detecting domain, detecting languages, balancing load with a view to create a marketplace. The project was financed by the European Commission. This is the presentation by Pangeanic in Gala Boston 2018.
This presentation is a part of the MosesCore project that encourages the development and usage of open source machine translation tools, notably the Moses statistical MT toolkit.
MosesCore is supported by the European Commission Grant Number 288487 under the 7th Framework Programme.
For the latest updates, follow us on Twitter - #MosesCore
Business is all about Numbers & Speed, Professionalism is all about realization of Commitments. How to make these two ends meet.. is by reducing Waste.
Pangeanic presentation at Elia Together Athens - Manuel HerranzManuel Herranz
Our presentation at #Eliatogether in Athens was favored by many attendees. Will disintermediation be a force to reckon with in the translation industry as it has happened in the hotel and travel industries? What is the role of machine translation in all this? How does neural machine translation work?
Similar to Gestión proyectos traducción en la Universitat Autònoma de Barcelona (20)
Manuel Herranz presents at TMS Inspiration Days, on Pangeanic's use case, the application of MT to LSPs, the Pangeanic development case. Unveiling feature-rich PangeaMT Saas Power, Pangeanic's v3.
Pangeanic presentation at Japan Translation Federation, detailing history of MT, productivity gains with MT at LSPs, data from Autodesk and CSA, description of PangeaMT system
machine translation manuel herranz PangeaMT TAUS BarcelonaManuel Herranz
how machine translation is about empowering users and how users can be empowered using DIY SMT technology to build their own statistical machine translation solutions
kerstin bier, localization world barcelona, manuel herranz, mt, pangeanic, sy...Manuel Herranz
Co-presentation by Kerstin Bier and Manuel Herranz in Localization World Barcelona 2011 on the achievement and progress made by a customized PangeaMT engine at Sybase. Initial machine translation implementation, machine translation customization for Sybase, use of client's data for training and productivity results.
presentation on history of MT and how language resources have helped to develop MT (particularly statistical MT) with an emphasis in Pangeanic's experience
Unveiling the Secrets How Does Generative AI Work.pdfSam H
At its core, generative artificial intelligence relies on the concept of generative models, which serve as engines that churn out entirely new data resembling their training data. It is like a sculptor who has studied so many forms found in nature and then uses this knowledge to create sculptures from his imagination that have never been seen before anywhere else. If taken to cyberspace, gans work almost the same way.
What are the main advantages of using HR recruiter services.pdfHumanResourceDimensi1
HR recruiter services offer top talents to companies according to their specific needs. They handle all recruitment tasks from job posting to onboarding and help companies concentrate on their business growth. With their expertise and years of experience, they streamline the hiring process and save time and resources for the company.
Cracking the Workplace Discipline Code Main.pptxWorkforce Group
Cultivating and maintaining discipline within teams is a critical differentiator for successful organisations.
Forward-thinking leaders and business managers understand the impact that discipline has on organisational success. A disciplined workforce operates with clarity, focus, and a shared understanding of expectations, ultimately driving better results, optimising productivity, and facilitating seamless collaboration.
Although discipline is not a one-size-fits-all approach, it can help create a work environment that encourages personal growth and accountability rather than solely relying on punitive measures.
In this deck, you will learn the significance of workplace discipline for organisational success. You’ll also learn
• Four (4) workplace discipline methods you should consider
• The best and most practical approach to implementing workplace discipline.
• Three (3) key tips to maintain a disciplined workplace.
Putting the SPARK into Virtual Training.pptxCynthia Clay
This 60-minute webinar, sponsored by Adobe, was delivered for the Training Mag Network. It explored the five elements of SPARK: Storytelling, Purpose, Action, Relationships, and Kudos. Knowing how to tell a well-structured story is key to building long-term memory. Stating a clear purpose that doesn't take away from the discovery learning process is critical. Ensuring that people move from theory to practical application is imperative. Creating strong social learning is the key to commitment and engagement. Validating and affirming participants' comments is the way to create a positive learning environment.
Taurus Zodiac Sign_ Personality Traits and Sign Dates.pptxmy Pandit
Explore the world of the Taurus zodiac sign. Learn about their stability, determination, and appreciation for beauty. Discover how Taureans' grounded nature and hardworking mindset define their unique personality.
Buy Verified PayPal Account | Buy Google 5 Star Reviewsusawebmarket
Buy Verified PayPal Account
Looking to buy verified PayPal accounts? Discover 7 expert tips for safely purchasing a verified PayPal account in 2024. Ensure security and reliability for your transactions.
PayPal Services Features-
🟢 Email Access
🟢 Bank Added
🟢 Card Verified
🟢 Full SSN Provided
🟢 Phone Number Access
🟢 Driving License Copy
🟢 Fasted Delivery
Client Satisfaction is Our First priority. Our services is very appropriate to buy. We assume that the first-rate way to purchase our offerings is to order on the website. If you have any worry in our cooperation usually You can order us on Skype or Telegram.
24/7 Hours Reply/Please Contact
usawebmarketEmail: support@usawebmarket.com
Skype: usawebmarket
Telegram: @usawebmarket
WhatsApp: +1(218) 203-5951
USA WEB MARKET is the Best Verified PayPal, Payoneer, Cash App, Skrill, Neteller, Stripe Account and SEO, SMM Service provider.100%Satisfection granted.100% replacement Granted.
As a business owner in Delaware, staying on top of your tax obligations is paramount, especially with the annual deadline for Delaware Franchise Tax looming on March 1. One such obligation is the annual Delaware Franchise Tax, which serves as a crucial requirement for maintaining your company’s legal standing within the state. While the prospect of handling tax matters may seem daunting, rest assured that the process can be straightforward with the right guidance. In this comprehensive guide, we’ll walk you through the steps of filing your Delaware Franchise Tax and provide insights to help you navigate the process effectively.
The world of search engine optimization (SEO) is buzzing with discussions after Google confirmed that around 2,500 leaked internal documents related to its Search feature are indeed authentic. The revelation has sparked significant concerns within the SEO community. The leaked documents were initially reported by SEO experts Rand Fishkin and Mike King, igniting widespread analysis and discourse. For More Info:- https://news.arihantwebtech.com/search-disrupted-googles-leaked-documents-rock-the-seo-world/
Personal Brand Statement:
As an Army veteran dedicated to lifelong learning, I bring a disciplined, strategic mindset to my pursuits. I am constantly expanding my knowledge to innovate and lead effectively. My journey is driven by a commitment to excellence, and to make a meaningful impact in the world.
3.0 Project 2_ Developing My Brand Identity Kit.pptxtanyjahb
A personal brand exploration presentation summarizes an individual's unique qualities and goals, covering strengths, values, passions, and target audience. It helps individuals understand what makes them stand out, their desired image, and how they aim to achieve it.
Attending a job Interview for B1 and B2 Englsih learnersErika906060
It is a sample of an interview for a business english class for pre-intermediate and intermediate english students with emphasis on the speking ability.
4. MT Usage
MT for assimilation: “gisting” or
“understanding“
• Practically unlimited demand; but free web-based
services reduce incentive to improve technology
• Coverage + important. Instant quality
MT for dissemination: “publication“
MT for direct communication
• Publishable quality that can only be achieved by
humans. MT & tools a productivity booster
• Current R&D, Military uses systems
for spoken MT, first applications for
smartphones
5. Machine translation
Language Model (Fluency)Translation Model (Adequacy)
Monolingual
Corpus
Phrase
Table
Parallel
Corpus
nGram-
Model
Alignment,
Phrase
Extraction
Counting,
Smoothing
Decoder
(translator)
Source
Text
Target
Text
N-best
Lists
Basic Architecture for Statistical MT
7. Unrest is continuing in Cairo as protesters set up their demand for Egypt’s
military rulers to resign
How does Statistical MT work?
8. • SMT can be seen as a generalisation of Translation
Memory to sub-segmental level
• The phrases are text snippets (n-grams) taken from real-
world translations (= as good as the source you entered)
• Re-combination of those phrases for out-of-context
translation may lead to significant problems :
– Alignment errors spurious/lost meaning
– Bad morphology (declensions)
– Grammatical errors
– Wrong disambiguation
• SMT will not recover implicit information from source text
nor handle structural mismatches, it needs more info.
}
SMT from a translator’s perspective?
9. Strengths and Weaknesses of pure SMT
(RBMT:translate pro SMT:Koehn 2005, examples from EuroParl)
EN: I wish the negotiators continued success with their work
in this important area.
RBMT: Ich wünsche, dass die Unterhändler Erfolg mit ihrer
Arbeit in diesem wichtigen Bereich fortsetzten.
continued: Verb instead of adjective
SMT: Ich wünsche der Verhandlungsführer fortgesetzte Erfolg
bei ihrer Arbeit in diesem wichtigen Bereich.
three wrong inflectional endings
This has consequences in the fair PE payment model
10. Strengths and Weaknesses of pure SMT
In the early 90s and early
00’s, strong support and
advocacy for either of the
two technologies: SMT vs
RBMT.
But we have learn to
combine the best of both
worlds. Google ditched
Systran (Och, 2005), went
all statistical and now SMT
plus linguistic models.
Microsoft (Chris Wendt)
also uses 2 technologies
11. Examples of Hybrid MT architectures
= SMT Module
= RBMT ModuleThe search for integrated (hybrid) methods is now seen
as natural extension of both approaches
12. How does PangeaMT work?
It can bring together syntactically distant languages from
different families
This has consequences in the fair PE payment model
13. SYNTAX (LINGUISTIC)-BASED HYBRID SMT
When available, the company plans to offer the following:
available When , the company the following : plans to offer :
(VBPt3) (to) (VBinf) (DET)
(NN)
(Predicate)
Nipponization module
Translation & Cleaning
(Subject) (VBPt) (to)
(ADV) (ADJ)
(Punct)
(DET)
(NNSing)
(Cond clause),
How does PangeaMT work?
15. How do you manage a translation project?
Typical order workflow at an LSP
http://pangeanic.es/norma-calidad-en15038-gestion-de-ofertas-pedidos-y-contratos/
16. How do you manage a translation project?
EN15038 - Typical translation job project management at a translation
company
17. How do you manage a translation project?
• Main tool for language professionals
• TMs-based retrieval
• Shows similar (hight percent match)
translations stored in the TM for each
segment of translation
• 100% matches: perfect, identical
segments from the TM
• Fuzzy matches: there are no 100%
matches, but there are similar
segments. Generally, matches below
70% require full human “PE”.
• Mean productivity: 2000-3000 words/
day. E.g.:
• Proprietary software: SDL Trados,
MemoQ, Deja Vu, Memsource
• Semi-free: WordFast
• Opensource software: OmegaT
Advantages:
Higher productivity in professional
translation
Very popular, low-entry threshold, not
so expensive
Friendly GUI
Easy Quality Check (QC)
Latest versions: can integrate MT as
suggestion
Disadvantages:
Translation is not scalable = production
is directly related to available
translators/hour/day
If there isn't any TM available, there is
no productivity improvement
18. How do you manage a translation project?
Advantages:
Translation becomes scalable, millions
of words can be translated per day
More productivity in non-professional
translations
Disadvantages:
A lot of data is needed to create a
engine (SMT)
A lot of time is needed to create an
engine (RBMT)
MT alone is not useful for professional
translation, only for gisting
• Production enhancement tools
• Full, complex systems
• Multilanguage
• Full translation
• “Gisting”
• Translate content which otherwise
would be ignored, not accessible or
not understood.
19. How do you manage a translation project?
• Already available in the 90s between
Trados and Systran
• The CAT tool shows similar translations
from TM and a suggestion or
suggestions from MT, and the user
chooses what to postedit.
E.g.:
translate segments with matches
above 70-%75% with TM
translate segments with matches
below 70-75% with MT
• If custom-built, very good results, but
professional translators are reluctant to
become post-editors (price pressures)
• Average productivity: +5000 words/day
Advantages:
Postediting is faster than translating
from scratch
The future of the translation industry?
Enable faster, HQ translations
Fast postediting if the MT output
reaches certain Q levels
Disadvantages:
If the MT output is bad, better to
translate from scratch
24. How do you manage a translation project?
+: Fast if we have no TM
QC difficult (cannot use XBench or QA Distiller)
- : Slightly slower (minutes) if we have TM as file
translation is a checking/retrieval exercise
25. How do you manage a translation project?
How it works:
- During pre-analysis, export unknown segment (segments under XX percent match) into bilingual file
- Translate bilingual file with MT
- Import MT translated bilingual le into the TM
- Select a penalty for MT
- We can choose TM or MT (like a “bad TM”)
+ :
Fast postediting
- :
A few steps more to do preparing the project
26. How do you manage a translation project?
How it works:
-
- Import MT translated bilingual le into the TM
- Select a penalty for MT
- We can choose TM or MT suggestion
+ :
Fast post-editing
- :
If internet-based, latency depends on the Internet
32. EXERCISE
Work in pairs, one is PM, one is “expert translator”:
PM tries to convince the translator to accept a lower rate for large volume of work (say 5000 words) to be
done in one day as post-editor of an already pre-translated text.
PM sees the aver on a “day salary basis”, offering a likelihood of the text being OK and spending half of the
time the translator would spend, so the translator earns the same in terms of time
TRANSLATOR says MT still requires reading, understanding, correcting, sometimes needs to be done from
scratch.
Use your own experience with online tools
SHARE THE RESULTS WIT THE TEAM / WHO WINS ? / WHAT LESSONS HAVE YOU LEARNT?