Conversational Information Retrieval for Instructional Content – A Modeling Framework and an Implementation for Recipe Search
This is an incomplete backup of the coding part of my bachelor thesis which includes a prototype recipe search application as an Alexa skill and the crawling and mining of its dataset. However the dataset itself is not included in this repository.
The original source code repository of my thesis can be found online for webis students at:
https://git.webis.de/webisstud/wstud-thesis-qu
Git clone via HTTPS:
https://git.webis.de/webisstud/wstud-thesis-qu.git
Git clone via SSH:
git@webis.uni-weimar.de:webisstud/wstud-thesis-qu.git
The thesis and my defense presentation ppt are under material.
As commercial voice agents are becoming increasingly popular, conversational search is brought into focus. Being an emerging area of research, there are a lot of questions that remain unanswered.
In this thesis, we aim to provide some insight into what a speech-based conversational search system might look like, focusing on its application in recipe search, as cooking is a typical hands-off situation where voice interactions and information retrieval with an agent afford more convenience. Our contribution is two-fold: (1) a human-like conversational information retrieval model, and (2) a prototype of conversational recipe search.