- Describe (e.g .: "describe ISWC")
- Count (e.g .: "count the papers on machine learning")
- List (e.g .: "list the top 5 conferences with papers on rdf graph sorted by publications").
You can enter a query all at once in natural language or through a wizard by entering one of the three activation words: describe, count or list. The audio functions use the Web Speech API which is defined as experimental technology and may not work correctly depending on the compatibility of the browser used, therefore the options to activate them are only available on fully compatible browsers (Google Chrome, Microsoft Edge, Apple Safari: all functions - Mozilla Firefox: only the speech syntetizer).
To import AIDA Alexa-hosted skill (see https://youtu.be/7ANn_u-zX1Q)- Open the Alexa developer console and log in.
- Click Create Skill. The Create a new skill page appears.
- For Skill name, type a name.
- For Default language, choose a language (en.US).
- For Choose a model to add to your skill, select Custom.
- For Choose a method to host your skill's backend resources, select Alexa-Hosted (Node.js).
- Click Create Skill. The Choose a template to add to your skill page appears.
- Click Import skill. The Import skill dialog appears.
- Enter the .git link to the Git repository that contains the skill that you want to import (https://github.com/infovillasimius/aida.git).
- Click Continue. The message Creating your Alexa-hosted skill appears. If Alexa validates that the Git repository contains an Alexa skill that it can import, Alexa creates your Alexa-hosted skill.
- install elasticsearch on a Linux machine with an ip address reachable from the web server (point 5)
- download sample data from https://github.com/infovillasimius/aidaBot/tree/main/data_sample (the authors data for index "authors" are in a splitted zip file which has to be unzipped only once before use with import_dsc_authors_zip.py script)
- create five indexes named authors, authors2, aida2, conferences and organizations
- index data on elasticsearch using the five python scripts provided (you have to install elasticsearch python client)
- run the web server, provided at https://github.com/infovillasimius/aidaBot/tree/main/data_server, on a Linux machine - with an ip address reachable from the internet and elasticsearch python client installed - by launching web_server.py script (configuration options are in config.py and conf.js)
A paper about AidaBot is available at IEEE: Integrating Conversational Agents and Knowledge Graphs Within the Scholarly Domain