NeuralSpace & Lingy Boost Global Logistics Efficiency: Customer Story

Ayushman Dash

In 2021, the TSL (transport services and logistics) industry experienced a significant leap in development, with a 22.6% increase in revenues compared to 2020. The surge was fueled by growing product demands and the evolution of trade, particularly e-commerce, driven by the COVID-19 pandemic. 

With online shopping becoming a norm, TSL companies faced the need for an efficient solution to translate and transliterate data across a multitude of languages.

About Lingy

Lingy offers comprehensive language solutions, delivering translations by humans, powered by technology. Their services include written and oral translation for global enterprises.

Challenge

Lingy, was approached by a global logistics company with operations spanning 100 countries, across sea, air and road forwarding. Employing over  80,000 staff - they are one of the largest TSL companies in the world. The exponential rise in e-commerce and global trade posed a challenge for the client’s logistics operations. This client sought a customized solution for translating and transliterating data, particularly shipping labels. 

Project Requirements

  • Languages: Translation with Transliteration covering a total of 71 languages with mutually agreed equivalents in the case of very rare languages
  • Automatic Language Detection: Auto detection of the source language if not specified. 
  • Translation Acceptance Criteria: The accuracy of translation or transcription to be validated, by ensuring that the English data and address prominently display in search results on Google, Google Maps or other relevant search engines. This validation is important for anti-terror screening, helping to filter fraudulent addresses.
  • Security: Cloud deployment, in accordance with ISO standards set for digital data security, considering the involvement of sensitive data.
  • User Interface: Creation of an interactive user-interface to facilitate the seamless sharing of results and feedback.

To address these challenges, Lingy explored the possibility of creating a solution from scratch. This would involve a combination of in-house expertise and external resources. However, hiring an expert team to develop a comprehensive solution was prohibitively expensive. Moreover, assembling a team with proficiency in multiple languages was a daunting task.

NeuralSpace provided a solution that not only enabled faster implementation but also proved remarkably more cost-effective, leveraging existing cutting-edge technologies.

In collaboration with NeuralSpace, Lingy created a personalized translation and transliteration engine, complete with automatic language detection support. This initiative aimed to significantly improve operations for the client. 

Understanding Transliteration

Transliteration is the process of converting text from one script or writing system into another while preserving the pronunciation of the original language. It involves representing the sounds of words in a different script, often using similar or corresponding characters.

Let’s take an example to understand the function of transliteration in a global logistics operation. Consider a Japanese customer providing a delivery address in Japanese characters, such as “東京都渋谷区” (pronounced as “Tokyo-to Shibuya-ku”). The logistics computer system operates in English and is not designed to read Japanese characters. Transliteration in this context would convert the Japanese address into a Latin-based script compatible with the logistics system, resulting in something like “Tokyo-to Shibuya-ku.” This allows for automated processing of global addresses, ensuring accurate and efficient handling of shipping and delivery data across different languages and scripts.

NeuralSpace’s Solution

Our solution supported all 71 required languages including Arabic, Azeri, Bengali, and Polish. The API seamlessly translates non-Latin script languages into English and transliterates Latin script languages, handling diacritics like the German umlaut “ä,” converted to “ae.”

In addition to the extensive language coverage, our solution offered flexibility to meet the needs of the client. The implementation included the enablement of ‘human-in-the-loop’ feedback from agents on the performance of the model, which continuously improved the accuracy of translations. This flexibility ensured an agile and responsive framework for ongoing improvements and adjustments.

For automatic language detection, the engine uses predictive algorithms to identify the five most likely languages based on the provided sample address. It then selects the language with the most common features with the source language. However, if the desired language is specified, the detection process is bypassed to speed up the translation.

The solution was deployed on cloud following ISO digital security standards to protect sensitive data.

Results

“Our experience of working with NeuralSpace has been very positive. NeuralSpace stands out among other providers for their flexibility and clear communication.”

- Marcel Chmielewski, Business Development Manager at Lingy

NeuralSpace's sophisticated language AI capabilities guarantee accurate translation and transliteration, enhancing global operations. The commitment from Lingy to utilize NeuralSpace's solution for an extended three-year period underscored the strategic vision and long-term impact of this solution on their clients global logistics needs. 

“NeuralSpace helped us improve anti-terror screening and delivery efficiency for our global logistics client. We greatly value our collaboration with NeuralSpace.”

At NeuralSpace, we’re committed to propelling businesses forward with the best language AI solutions. We can help drive growth for your business with flexible solutions, tailored to your requirements. Contact our team of experts to explore our services.

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

  • JKDV
  • EVEV
  • EV
  • dfdb
  • dfb

Subscribe to our newsletter

Featured

Why Going Global Without AI Localization is Like Driving Without a GPS
Audiences are eager to explore global content - but can media companies keep pace without adopting AI?
May 30, 2024
Enhancing Call Center Efficiency with Advanced Speech Analytics
Customer finds solution in NeuralSpace's VoiceAI analytics API, to significantly transform their speech analytical capabilities.
May 24, 2024
Leading the way in Tagalog Speech Recognition
Our model outperforms Google, Azure, and OpenAI, with an 81.55% higher accuracy than Google.
May 20, 2024
Maximizing Localization Efficiency with LocAI Analytics
Delve into how LocAI addresses challenges of team management, time zones, and freelancing to empower teams in the dynamic subtitling landscape
May 3, 2024