AI Case Study
Pinterest enables its customer service team to offer international customer service in 28 different languages using machine translation
Pinterest is offered in 28 different languages and uses machine translation, nlp and machine learning to translate queries in various languages to and from English. This has enabled them to support international customers without adding more agents. All queries are answered by a team of 5 agents with the help of Unbabel's AI platform.
Internet Services Consumer
Pinterest approached Unbabel to automate customer service query translations using their artificial intelligence software.
"Unbabel's platform analyses source materials to detect elements such as locations, names and addresses, and estimate the tone and difficulty from vocabulary, length of sentences, grammatical patterns.
Depending on the context of the content the material is fed to a different Machine Translation engine. The translated material is reviewed by a human in most cases."
Expand offerings without scaling up customer service
"To start, Unbabel checks its Translation Memory — a huge, dynamic store of data that ensures that if a full sentence has already been done for the same client or same domain, it is retrieved and reused, allowing for a potential improvement in speed of delivery and translation consistency (although it can still be changed later on by human editors if the context is incorrect).
The next step is via the Machine Translation Router, which chooses the best specialised MT engines, based on content, domain and customer (a customer email versus product descriptions of handmade luxury watches have different requirements).
The machine-translated content then goes to the Automatic Post-Editor, where Unbabel is able to improve these translations automatically, by learning from what the human network has already done in the past. This produces a new version to be evaluated for quality (using our award-winning Quality Estimation system) and distributed to the right humans in Unbabel’s community.
Unbabel’s Smartcheck is like a supercharged version of Grammar Correction found in common document editors. It checks a range of potential errors with helpful suggestions for one-tap corrections, including spelling, tone, lexical consistency (subject and verb agreeing; pronouns matching; gender, etc) and more specific rules related to the customer’s stated requirements.
The magic of this whole process is that the more Unbabel translates, the better the outputs of the system become. Machine Translation engines can be retrained, Translation Memories can be enlarged, and the Automatic Post Editing improves with every pass of new text."
Technical And Product Support
Pinterest wanted to personalise the website experience for customers from all locations
"Sophisticated analyses on the source language are made, detecting hard-to-translate elements like locations, names and addresses, and estimating the overall difficulty of the text, based on vocabulary used, lengths of sentences and other grammatical patterns.
A model is built uniting this data with other insights on the document’s tone (formal vs. informal), as well as detecting its topic, which allows for smart routing of the content to certain editors by their stated interests (travel, sports, medical, entertainment, etc)."