Talking Open Data

Abstract

Enticing users into exploring Open Data remains an important challenge for the whole Open Data paradigm. Standard stock interfaces often used by Open Data portals are anything but inspiring even for tech-savvy users, let alone those without an articulated interest in data science. To address a broader range of citizens, we designed an open data search interface supporting natural language interactions via popular platforms like Facebook and Skype. Our data-aware chatbot answers search requests and suggests relevant open datasets, bringing fun factor and a potential of viral dissemination into Open Data exploration. The current system prototype is available for Facebook 1 and Skype 2 users.

Open Data Chatbot

“…Chatbots were introduced as an alternative interface able to provide a more user-friendly and engaging experience, while also serving as an effective information access point to structured data sources, such as Open Data repositories [2,6,7] and knowledge graphs [1]. DBpedia chatbot [1], for example, relies on a handful of pre-defined rules, which prevents from a more fine-grained query analysis, requires continuous engineering efforts and makes the approach difficult to scale and incorporate new conversational patterns.…”

“…We leverage these insights and demonstrate how semantic geo-information linked data sources can help to enhance user experience with automated dialogue systems. Our work is a followup on the previously proposed Open Data chatbot architectures [2,6]. The main difference to the previously proposed architecture [6] is providing support for dataset discovery functionality beyond conversational search towards enabling conversational browsing of the underlying data structures.…”

“…Our work is a followup on the previously proposed Open Data chatbot architectures [2,6]. The main difference to the previously proposed architecture [6] is providing support for dataset discovery functionality beyond conversational search towards enabling conversational browsing of the underlying data structures. The mode switch is triggered by the intent detection component of our system.…”

Conversational Browsing

“…Similarly, we also started earlier by designing a simple conversational search interface, which allows a user to submit a query and returns a list of matching datasets [36]. The chatbot attracted a lot of attention but many users were not able to formulate adequate queries since they were not aware of the structure and terminology of the underlying repository.…”

TableQA: Question Answering on Tabular Data

“…We attempt to remedy this situation through development of the information retrieval tools tailored specifically to the end users without technical background. Our Open Data Assistant chatbot (Neumaier et al, 2017) offers an unconventional interface for cross-lingual data search via Facebook and Skype messaging applications enabling a quick overview of the available datasets collected from various open data portals. However, the current version of the chatbot supports only metadata-based search.…”