Tag: NLP

Advertisement

Kynamics Secures DHS Translation Device Funding

Technology

Back in February, DHS released a solicitation for a robust multilingual translation device. It has awarded ASR and NLP company Kynamics with the opportunity.

Months after an industry-wide solicitation by the Department of Homeland Security (DHS), Kynamics has secured the Science and Technology Directorate’s (S&T) Silicon Valley Innovation Program (SVIP) language translation capabilities funding award. Based in Mountain View, Kynamics specializes in automatic speech recognition (ASR) and natural language processing (NLP) for mobile devices.

Regarding earlier devices, DHS stated, “the challenge of the USCG system is that it lacks the dynamic/agile robustness to effectively communicate across the spectrum of languages that are emerging across areas that were once more static.”

The award grants Kynamics $192,520 in Phase 1 funding to produce a portable, standalone translation system. The Language Translator solicitation aims to create a device capable of facilitating communication in real time with non-English speakers and those who are unable to communicate verbally. Ideally, the device will support at least 16 languages, including Arabic, Chinese, Mandarin, Persian-Iranian, French, German, Haitian-Creole, Indonesian, Japanese, Korean, Portuguese, Russian, Spanish, Tagalog, Thai, Ukrainian, and Vietnamese. The effort is in support of United States Coast Guard (USCG) missions.

“DHS S&T and SVIP have given the Coast Guard an opportunity to connect with innovative small businesses, such as Kynamics, to develop language translation technology that may enhance operational mission execution,” said Wendy Chaves, Chief of the Coast Guard Research, Development, Test and Evaluation, and Innovation Program.

While performing rescue and investigation missions, Coast Guard operators must be able to accurately communicate in real time with vessel occupants, many of whom are non-English speakers. Furthermore, since USCG personnel are often stationed at sea during extreme weather conditions with no Internet connection, the device must also be able to function offline and withstand temperatures ranging from 140ºF to -50ºF (60ºC to -5ºC).

“We’re excited to see how the Kynamics project unfolds as we move through this first proof-of-concept phase with USCG,” Melissa Oh, SVIP managing director, said. “We’re also delighted to include a minority female-founded company in our portfolio.”

Tags:, , , ,
+ posts

MultiLingual creates go-to news and resources for language industry professionals.

Advertisement
Weglot

Related News:

Advertisement

GreenKey Creates NLP Tool for Hedge Funds

AI

Focus Studio, the new application from GreenKey, will provide users with natural language processing workflows specific to hedge fund management.

Bank sales teams often turn to natural language processing (NLP) to find client insights — such as OTC quotes and trades — within emails, direct messages, and phone calls and manage increasing amounts of conversational data. This type of computational power is theoretically possible cross-linguistically as well, which has interesting implications for the language services industry. Specifically, the types of text processed might require unique needs to generate trade ideas. Addressing a specific need for hedge funds, GreenKey, creator of natural language processing (NLP) workflows for sales and trading, has released its latest version of the “Focus Studio” application.

Users of Focus Studio can customize NLP to go through various files and deliver highlighted insights as daily reports or power real-time automation, such as chatbots. This latest version of Focus Studio now includes NLP models designed specifically for hedge funds to help them cope with the amount of unstructured text they process.

Based in Chicago with offices in New York and London, GreenKey is the creator of a patented speech recognition (ASR) and NLP platform that recognizes complex jargon across real-time audio and text sources and transforms them into actionable insights. GreenKey converts disparate communications streams into structured data tools that help banks, trading firms, and emergency services operators automate complex workflows.

GreenKey trains the new NLP models on real sell-side human analysts to capture their insights and include the ability to rapidly customize those models through a quick annotation process. Traders will select from the base models called “trusted curators” and can even ask their favorite sell-side research analyst to create and contribute one. The custom model collection can be fed thousands of documents and will identify trending topics, intents, entities, and can even provide innovative raw sentiment scores such as “word disfluency.” The pre-trained models also include in-depth product knowledge across global fixed income, credit, equities, FX, and commodity markets.

“NLP is already changing the way sales and trading occurs on the sell-side, enabling a wave of automation and insight generation across various workflows,” said GreenKey Founder and CEO Anthony Tassone. “Now the buy-side can begin to leverage NLP to automate and scale their analysis, while retaining the ‘trusted curator’ role of the sell-side research provider and analyst.”

Tags:, , ,
+ posts

MultiLingual creates go-to news and resources for language industry professionals.

Related News:

Venga Global Launches AI Program to Meet Data, ML Needs

Localization Technology

Leveraging human-assisted multilingual data collection, Venga AI will power natural language processing AI and machine learning.

Global leader in translation and localization Venga Global announced this week the launch of Venga AI to meet growing data transformation and machine learning needs. Expanding data annotation, collection, and validation for artificial intelligence (AI) and machine learning (ML) services, the company looks to improve localization approaches, especially for languages other than English.

“We started offering data services in 2016 focused around natural language processing and data translation,” says Venga chief sales and marketing officer Antoine Rey. “We have learned, adapted, and developed technology with great success to bring quality clean data to top AI and data companies. We are excited to now publicly offer our expanded roster of services including data annotation and validation for text, image, video, and audio.”

Working in translation, localization, and creative services in over 150 languages, Venga partners with clients to “streamline global communication.” With expertise in natural language processing (NLP), the company builds custom programs for enterprise clients to provide human-assisted clean data collection, annotation, and validation for ML. These programs are supported by a production team, innovative tools and technology, a specialized supply chain, and an ISO-certified quality assurance team.

The announcement of the AI program notes the growing need for clean data to feed into machine learning algorithms, especially in sectors producing medical diagnostics, autonomous vehicles, and voice search. With roots already in the translation industry, Venga has pivoted to providing data services in recent years, leveraging local human networks to create accurate data sets.

Venga chief operating officer Chris Phillips credited the company’s “ability to ramp up from zero to thousands of trained resources in very short time periods” as “key to our success. We achieve this through stringent vetting, testing, and training of quality resources and optimize our technology stack project by project to create efficient and controlled NLP data collection.”

Venga Global earned recognition last year by the National LGBT Chamber of Commerce (NGLCC) Supplier Diversity Initiative, gaining certification as an LGBT Business Enterprise (LGBTBE).

Tags:, , ,
+ posts

MultiLingual creates go-to news and resources for language industry professionals.

Related News:

Vive La French Tech! Chatbots, French Style

Language, Localization Technology, Personalization and Design

A Chat About Bots

Conversational UI, that natural interaction between human and technology, is a hot topic worldwide, and the localization requirements for creating a great contextual natural user experience are fascinating and challenging, none more so than in the case of chatbots.

La French Tech. See https://www.facebook.com/LaFrenchTechEN/ for more information!

La French Tech. See https://www.facebook.com/LaFrenchTechEN/ for more information on the French technology startup and investment community.

As Arle Lommel from CommonSense Advisory says: Chatbots pose challenges fundamentally different from what is seen with traditional content. The shift to conversational structures and the need to embrace “messy” terminology are among these. Click To Tweet

There are other challenges too. Plan ahead.

What’s Going On Globally?

Here’s a great example from France by way of an article featuring Amina Esselimani, a top French user experience design thinker, published on the Prototypr blog: Conversational interface for chatbot & voicebot: the French touch.

The article itself gives good insight into why chatbots should be used, and the methodologies involved. I was fascinated by the human-oriented design language used by Amina to describe her work, using phrases such as “happy path” and “repair conversations.”

Her comments about using the “Wizard of Oz” design requirements technique, engaging with conversational style content experts, and iterative testing with real users really resonated too. We've moved from user-centered design to human-centered design, and dealing with how humans actually communicate and simulating that kind of exchange can indeed be very messy in any language! Click To Tweet

I also checked out some of the chatbot solutions Amina worked on, such as the Oui.SNCF bot. I wondered if it had a French personality (personality is a critical design element in conversational UI) and what the tone would be my questions about the ongoing SNCF rolling strikes.

Hofstede's six dimensions of national culture. A useful starting point, but real users doing real jobs in real places are the best way to determine the appropriate bot personality for the job to be done.

Hofstede’s six dimensions of national culture, in this case comparing France with Ireland and the United States of America. Hofstede’s work is a useful starting point when developing a bot personalit, but real users doing real jobs in real places are the best way to determine the appropriate bot personality for the job to be done.

All utterances were handled very diplomatically, I must say, even making sense of my mangled French language utterances!

Out.SNCF chatbot available in multiple languages too.

Out.SNCF chatbot is available in multiple languages too. I stuck with French!

Alexa en Français

You might also like to read Wired’s fascinating, and sometimes humorous artlcle, Inside Amazon’s Painstaking Pursuit to Teach Alexa French in the run up to its launch in France.

Amazon Echo (Alexa) launch advertisement.

Amazon Echo voice assistant was launched in France in June 2018. Alexa was trained to be speak and act “French”.


Cultural differences create conversational landmines. And you just can’t be sure that everyone will like you. As it turns out, that as true for people as it is for Amazon’s Alexa voice assistant. Click To Tweet

More information on globalization methods for conversational UIs and chatbots?

To understand more of the challenges presented by chatbot and conversational UI design and the cultural considerations involved, then check out my SF Globalization presentation and handy checklist on the subject of chatbot design for  global and local audiences: “Alexa, Tell Me About Global Chatbot Design and Localization!”

All images by Utan O’Broin

Tags:, , , , , , , , , , , , ,
+ posts

Ultan Ó Broin (@localization), is an independent UX consultant. With three decades of UX and L10n experience and outreach, he specializes in helping people ensure their global digital transformation makes sense culturally and also reflects how users behave locally.

Any views expressed are his own. Especially the ones you agree with.

Related News:

Conversational UI Language Design at LocWorld35

Language in Business, Language in the News, Personalization and Design, Translation Technology

Oracle Applications User Experience (OAUX) team member (and Microsoft Alum) Karen Scipi (@karenscipi) presented on the subject of Conversational UI in the Enterprise at #LocWorld35 Silicon Valley. Karen covered the central importance of  language design for chatbots and other conversational user interfaces (CUIs) for global work use cases.

Karen Scipi presenting on Conversational UIs in the Enterprise at Localization World in Silicon Valley 2017 (Image credit: Olga)

Karen Scipi presenting on Conversational UIs in the Enterprise at Localization World in Silicon Valley 2017 (Image credit: Olga)

Karen even developed two chatbot integrations for Slack introducing her topic. One was in English, the other was in Italian.

Italian LocWorld Chatbot Conversation Example

Italian LocWorld Chatbot Conversation Example (Source: Karen Scipi)

What’s a Conversational UI?

Chatbots and the alike are a very hot topic, wrapped up in the artificial intelligence (AI), machine learning (ML), natural language processing (NLP), and robotics part of technology’s evolution. However, user experience design insight and an empathy for how people interact with each other through technology in work, at play, or in everyday life makes the difference when creating a great user experience in any language.What could be more 'natural' than talking to a computer? Click To Tweet

CUI means we moved from a “user”-centric concept of design to a human-centric one. After all, what could be more “natural” that talking to a computer? Both humans and computers “converse” in dialog, and it’s the language design knowledge for such a conversation that’s critical to delivering a natural, human-like interaction between the two.

Examples of CUIs include Facebook Messenger, Slack bots, TelegramAmazon Echo and Alexa devices, and so on. Interaction can be via voice, SMS messaging, typing text on a keyboard, and so on.

In the enterprise there are a broad range of considerations and stakeholders that localization and UX pros must to consider. Fundamentally though, enterprise CUIs are about increasing participation in the user experience of work, making things simpler.

 

Oracle Conversational UI image showing the interaction and participation of humans and the cloud - in any language! (Source: OAUX)

Oracle Conversational UI image showing the interaction and participation of humans and the cloud – in any language! (Source: OAUX)

Localization of Conversational UIs

To an extent, the localization or language part of the CUI interaction is determined by the NLP support of the chatbot or other platform used: what languages it supports, how good the AI and ML parts are, and so on. However, language skills are at the heart of the conversational UI design, whether it’s composing that  user storyline for design flows or creating the prompts and messages seen by the human involved.

This kind of communication skill is much in-demand: It is a special type of talent: a mix of technical writing, film script or creative writing, transcreation, and interpreting. It’s a domain insight that gets right down to the nitty-gritty of replicating and handling how humans really speak and write: slang, errors, typos, warts and all. CUI language designers must even decide how emoji and personality can or should be localized in different versions of a chatbot.

Where’s the Conversation Headed?

The conversational UI market is growing globally as messenger apps take over. Localization and language pros cannot ignore the conversational UI space.

Karen will be speaking next at the Seattle Localization User Group (SLUG) in December (2017) about Conversational UIs in the Enterprise.Localization and language pros cannot ignore the conversational UI space. Click To Tweet

 

Tags:, , , , , , , , , , , , , , , , ,
+ posts

Ultan Ó Broin (@localization), is an independent UX consultant. With three decades of UX and L10n experience and outreach, he specializes in helping people ensure their global digital transformation makes sense culturally and also reflects how users behave locally.

Any views expressed are his own. Especially the ones you agree with.

Related News:

Boaty McBoatface: Man versus Machine at Localization World

Language in Business, Translation Technology

Yes, the whole Boaty McBoatface thing has now entered the language space too.

Boaty McBoatface: Your future of translation may lie in machine learning and related technology

Boaty McBoatface: Your future of translation may lie in machine learning and related technology.

Parsey McParseface, part of Google’s SyntaxNet, an open-source neural network framework implemented in TensorFlow that provides a foundation for Natural Language Understanding (NLU) systems is out there:

Parsey McParseface is built on powerful machine learning algorithms that learn to analyze the linguistic structure of language, and that can explain the functional role of each word in a given sentence. Because Parsey McParseface is the most accurate such model in the world, we hope that it will be useful to developers and researchers interested in automatic extraction of information, translation, and other core applications of NLU.

I wonder could Parsey McParseface have a role in determining if a translation was correct or incorrect, given the context (or as the UK’s Daily Telegraph newspaper would so earthily have it, act as a “bolloxometer“)? Whither the QA or real-time interpretation possibilities.

This is all fascinating stuff sure, and definitely machine learning is a driver of smart user experiences, along with other areas. The Globalization, Internationalization, Localization, and Translation (or GILT) industry needs to be onboard with these emerging technologies and explore their possible application.

It’s the kind of thing I had intended to talk about at Localization World 31 in Dublin (yes, I even included Parsey McParseface). Alas, personal circumstances intervened and I did not speak. Some other time perhaps.

In the meantime, I am sharing the slides I had intended as a backdrop to the discussion. Perhaps they will help you orient yourself to the differences between machine learning, artificial intelligence, NLP, Big Data, robots, and more. They may even help you figure out if you have a future in the GILT industry and what that might look like.

Enjoy:

Smart UX in the World of Work

Context is King: Smart UX in the World of Work

Smart User Experiences and the World of Work: Context is King from Ultan O’Broin

Comments welcome.

Tags:, , , , , , ,
+ posts

Ultan Ó Broin (@localization), is an independent UX consultant. With three decades of UX and L10n experience and outreach, he specializes in helping people ensure their global digital transformation makes sense culturally and also reflects how users behave locally.

Any views expressed are his own. Especially the ones you agree with.

Related News: