Enabling Multilingual Conversational AI

Informacje na temat projektu

MultiConvAI

Identyfikator umowy o grant: 957356

DOI

10.3030/957356

Projekt został zamknięty

Data podpisania przez KE 14 Lipca 2020

Data rozpoczęcia 1 Stycznia 2021

Data zakończenia 30 Czerwca 2022

Finansowanie w ramach

• EXCELLENT SCIENCE - European Research Council (ERC)

Koszt całkowity

Brak danych

Wkład UE

€ 150 000,00

Koordynowany przez

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE
United Kingdom

Periodic Reporting for period 1 - MultiConvAI (Enabling Multilingual Conversational AI)

Okres sprawozdawczy: 2021-01-01 do 2022-06-30

Podsumowanie kontekstu i ogólnych celów projektu

In recent past, Conversational Artificial Intelligence (AI) has made major advances, thanks to the availability of big data and
increasingly powerful deep learning. Task-based statistical dialogue systems (SDS) are now viable, embedded in popular commercial
applications (e.g. the Apple’s Siri, Amazon’s Echo, Google’s Assistant) and cost-effective in many scenarios (e.g. customer support,
call centre service, searching, booking). Yet current SDSs are only available for a handful of resource-rich languages, leaving the
majority of the worlds languages and their speakers behind. Our project has developed the first prototype system for scaling
conversational AI to multiple languages. This is based on new methodology that learns multilingual representations
without the need for expensive training data, using a process called semantic specialisation that complements
representations with common-sense and linguistic knowledge in external knowledge graphs. Building on our promising pilot studies,
we have developed Natural Language Understanding (NLU) modules for SDS via using more effective semantic specialisation
based on joint multisource multi-target training and have focussed on typologically-diverse languages.
We have proposed new methods for selective sharing and structural adaptation and optimisation for the target languages
guided by typological knowledge. The best resulting technology was integrated in a demo prototype system which can generate multilingual
NLU input for more widely portable SDS. On a larger scale, extending the multilingual scope of SDSs can have major socioeconomic benefits:
it can broaden the global reach of conversational AI and it can enhance its commercial viability.