Infrequently Asked Question (IFAQ) classification and answering

e-tornike commented 4 years ago

Many people have specific information needs, which may not be answered in FAQs (e.g. "How many people are infected with Corona in Berlin?").

A possible first step would be to classify the intent of the question (w/ Rasa or DeepPavlov).

Afterwards, slot filling can be used to extract semantic concepts (w/ Rasa or DeepPavlov).

The information can then be converted into database queries (e.g. COVID-19, Coronavirus Tracker API, Coronazaehler).

Extra: The result may be formatted for different intents.

Similar projects: Rasa project for answering simple COVID-19 questions. https://github.com/LuisMossburger/CoronaBibliothekar/tree/rasa-init

Combined COVID-19 cases database (RKI, JHU, ECDC) https://github.com/swildermann/COVID-19

Timoeller commented 4 years ago

I also talked to "Tobias Röddiger" who created this website: https://www.coronazaehler.de/

Maybe he can create an API for this data? As far as I understood him he collects the sources manually as well (there are csv files on official German sites with statistics...)

e-tornike commented 4 years ago

I also talked to "Tobias Röddiger" who created this website: https://www.coronazaehler.de/

Maybe he can create an API for this data? As far as I understood him he collects the sources manually as well (there are csv files on official German sites with statistics...)

Yeah, that's definitely more detailed. An API would be great!

e-tornike commented 4 years ago

I also talked to "Tobias Röddiger" who created this website: https://www.coronazaehler.de/

Maybe he can create an API for this data? As far as I understood him he collects the sources manually as well (there are csv files on official German sites with statistics...)

Any news on a possible API?

deepset-ai / COVID-QA

Infrequently Asked Question (IFAQ) classification and answering #20