Language I/O leverages machine learning to process over 150 languages, including, it turns out, tech jargon.
What’s special about the company is that instead of offering a neural machine translation engine solution that needs to be trained, it leverages existing neural networks from Google, Facebook, and Amazon to choose the best translations.
“Basically what we do is machine translation,” said Diego Bartolome, CTO of Language I/O, who left Microsoft to join the company. “Essentially, we enable any customer, especially in the customer support space, to communicate with customers in any language and we do this by integrating multiple machine translation solutions like Google, Amazon, Microsoft , DeepL and others.”
CEO Heather Shoemaker, an engineer, founded the company in 2011 after building integrations with Oracle to take advantage of machine translation engines. She realized the multilingual customer support space was underserved and built a team to support building customer relationship management (CRM) integrations with machine translation engines, Bartolome said.
Language I/O adds a layer of machine learning and natural language processing to improve quality and ensure industry-specific terms are translated correctly. This allows it to be up and running in hours, he added, forgoing the weeks of training required by other approaches.
It integrates with CRM systems such as Oracle, Zendesk, and Salesforce to provide customer support to agents via chat, email, or real-time chatbot. Its clients include language platform Rosetta Stone, photo site Shutterstock and global sports entertainment platform DAZN. The company raised $12 million in four rounds, including the most recent Series A round in January, which raised $6.5 million, according to Crunchbase.
What programmers need to know
Machine translation systems work a bit like neural networks, he said. Building a new language requires creating a machine translation engine with a parallel textual source and a target language. Language I/O, he said, specializes in ensuring certain jargon is correct in translation.
“What we do on our end is a bit different, because essentially what we do is make sure the terminology is processed and that involves natural language processing – so detecting the term, making sure that it is correctly translated with the right form variation,” Bartolomé said.
Companies provide the initial glossary and Language I/O loads it into the system. Companies don’t need to spend time training artificial intelligence, he added: “They don’t have to do anything, it’s all based on active learning.
Language processing capabilities are also accessible through a publicly available API that can respond in any of the translated languages. A free trial is available on its website, Bartolome said, but for API access, the developer would need to discuss the use case with Language I/O.
Use cases include multilingual chatbots and enterprise support for IT and human resources, both text and voice. IT companies are among the customers who use Language I/O to ensure that glossaries are correctly translated into other languages, according to Bartolome. The pricing model is a scaled flat rate, based on support level, he added, with everything included.
“In programming, when you’re developing something these days, the multilingual aspect is key to going global – all users or customers, we want the interfaces or we want the code to be in our own language,” Bartolome said. “So I encourage everyone to think about their product or solutions holistically, because that will bring much more success than just thinking in one language.”
Feature image via Pixabay.