Chatbots and Machine Translation

Industry Challenge 

Machine Translation (MT) systems typically translate sentences independently of each other, however, certain textual elements cannot be correctly translated without a wider conversational context, which may appear outside the current sentence. ADAPT was challenged to create an MT system that can take context from previous sentences into consideration in the translation of application in conversational e-commerce, Voice-UI, for localisation managers.

ADAPT Solution

Adapt developed a Neural translation system that was attentive to the wider conversational context for a seamless multi-language experience using inputs from current sentences and previous source sentences.

Adapt Technology

Our novel combination of contextual strategies greatly outperforms existing models. This strategy uses the previous sentence as an auxiliary input and decodes both the current and previous sentence. Previous source sentences are integrated as contexts when translating the current sentence.

Results & Benefits

Our system improves translation quality by 20% and speed by 15% compared to the baseline.

Use Cases

Chatbots – international customer support
Cultural sensitisation
Voice – UI

Watch Dr. Resende discuss the Mtrill project

Download PDF