English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This article introduces a Turkish mobile assistant application which produces state-of-the art results for the Turkish language by using natural language processing (NLP) techniques. The voice-enabled mobile assistant application allows users to enter queries for nine pre-defined tasks; namely, making calls, sending sms messages and emails, getting directions, querying exchange rates, weather forecast and traffic information, searching on the internet and launching applications on the phone. Users’ queries are processed in a multi-stage approach (viz., NLP, query classification and parameter extraction). Either the requested task is performed or the requested information is displayed as the response of the application. The article presents the architecture of the introduced system, its comparison with some prominent mobile assistants as well as the newly created data resources (viz., two query datasets annotated for classification and parameter extraction, two specific datasets for domain adaptation of named entity recognition and syntactic parsing NLP modules) to be used in further research. The evaluations on the impact of NLP preprocessing layers to the query classification performances reveal that the added value by NLP may range from 0.2 to 10.7 percentage points depending on the preferred machine learning algorithm for the query classification stage. The impact of NLP for the parameter extraction stage is also crucial since the outputs of NLP modules are used systematically by the extraction rules. The overall performance of the introduced approach is measured as 70.8% which is very promising under the fact that the system is trained with very limited-size of annotated data. The technology introduced in this article is basically designed for the case of a mobile assistant but it can also be used for every voice-enabled control system to improve the user experience, such as smart homes or smart televisions.

Use of NLP Techniques for an Enhanced Mobile Personal Assistant: The Case of Turkish