BELLEVUE, Wash.--(BUSINESS WIRE)--AI techniques such as semantic parsing hold the promise of revolutionizing natural language processing. However acquiring training data for each domain in each supported language remains cumbersome and expensive. This limitation has become increasingly significant as companies demand intelligent, conversational voice applications to support their global product strategies.
Today, the Voicebox Advanced Technologies Team announced a significant innovation that reduces the burden of data collection while producing impressive, industry-leading results. More importantly, the innovation helps overcome the challenge of parsing multi-language utterances, known in linguistic circles as “code-switching.”
Voicebox’s approach applies the ‘learning’ of one language to another. The team evaluated utterances in German, English and a mix of both in a single utterance. They developed a neural network model, trained on both English- and German-only sentences. As part of a single semantic parsing process, this model transfers information from one language to the other, thus leveraging English data to reduce the amount of data needed for German.
As a result, performance on each language improved, yielding state-of-the-art accuracy comparable to the likes of Google. The team also evaluated utterances that could contain a mix of both languages and weren’t in any of the training data. Results were similarly impressive.
“We are excited to present this innovation at CoNLL,” said Dr. Phil Cohen, Chief Scientist, AI at Voicebox. “And we’re more excited about the ground-breaking benefits this innovation brings to users.” To date, voice navigation systems, for example, have struggled with multi-lingual use cases. This has been a serious usability issue in multi-language regions, such as Europe or Asia where code-switching is common. For example, a French person driving in Germany may say, “Wie viele Universitäten ont Paris?” (How many universities does Paris have?) Similarly, it is very common for a person in China to ask, “播放歌曲 Let It Be.” (Play the song Let It Be)
“At the end of the day,” Cohen added, “the goal of Voicebox Advanced Technologies research is to bring practical value and a better experience to users.”
If you’d like to read more on the Multilingual Semantic Parsing and Code-switching, please visit: http://aclweb.org/anthology/K17-1038.
About Voicebox – Voicebox provides award-winning voice technology for the automotive, mobile, home and IoT markets. It employs patented Context Management and is an early pioneer in Conversational Artificial Intelligence. Shipping in 23 languages across six continents, Voicebox’s flagship customers include Toyota and Samsung. Headquartered in Bellevue, WA, the Company has offices in Asia, Australia and Europe. See http://www.voicebox.com.
