Shoo the Spectre of Ignorance with QAASPR - An Open Domain Question Answering Architecture with Semantic Prioritisation of Roles

Open Domain Question Answering (ODQA) aims at automatically understanding and giving responses to general questions posed in natural language. Nowadays, the ability of a ODQA system is strictly dependent on how valuable information is effectively discovered and extracted from the huge amount of documents on the net – may it be structured (e.g., online datasets), or unstructured (e.g., free text of generic web pages). This, in turn, relies on a proper (i) identification of question keywords to isolate candidate answer passages from documents, and (ii) ranking of the candidate answers to decide which passage contains the correct answer. In this paper we introduce a Question Answering Architecture with Semantic Prioritisation of Roles (QAASPR) where a novel technique of prioritised semantic role labelling (PSRL) is used to optimise such phases. We also share the experimental results collected from a working prototype of QAASPR for the Italian language.