Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L'Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available te
mporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.
One of the first building blocks to create a voice assistant relates to the task of tagging entities or attributes in user queries. This can be particularly challenging when entities are in the tenth of millions, as is the case of e.g. music catalogs
. Training slot tagging models at an industrial scale requires large quantities of accurately labeled user queries, which are often hard and costly to gather. On the other hand, voice assistants typically collect plenty of unlabeled queries that often remain unexploited. This paper presents a weakly-supervised methodology to label large amounts of voice query logs, enhanced with a manual filtering step. Our experimental evaluations show that slot tagging models trained on weakly-supervised data outperform models trained on hand-annotated or synthetic data, at a lower cost. Further, manual filtering of weakly-supervised data leads to a very significant reduction in Sentence Error Rate, while allowing us to drastically reduce human curation efforts from weeks to hours, with respect to hand-annotation of queries. The method is applied to successfully bootstrap a slot tagging system for a major music streaming service that currently serves several tens of thousands of daily voice queries.
Internet of Things plays a key role in our lives today from managing airport passenger traffic, smart houses and cities to taking care of the elderly, it aims to improve life in all areas, and the technological development we are seeing has contribut
ed to a wide spread in many domains.
Platforms are the supporting software that connects everything within the Internet of things system. The platform facilitates communication, data flow, device management, and application functionality.
The Thinger.io platform is an easy-to-use platform that provides a variety of services to users. The platform enables communication of various types of devices and chipsets.
The idea was to create a personal assistant that works via voice commands to control devices connected to the Thinger.io platform remotely over the Internet in real time, The aim of adding this possibility to the platform is to make it simpler to allow anyone of any age or experience to use it to facilitate their life the way they choose, whereas The Vinus Assistant - as we called it - has the flexibility, reliability and functionality to deal with any application.
