Survey on challenges of Question Answering in the Semantic Web

Abstract

Abstract. Semantic Question Answering (SQA) removes two major access requirements to the Semantic Web: the mastery of a formal query language like SPARQL and knowledge of a specific vocabulary. Because of the complexity of natural language, SQA presents difficult challenges and many research opportunities. Instead of a shared effort, however, many essential components are redeveloped, which is an inefficient use of researcher's time and resources. This survey analyzes 62 different SQA systems, which are systematically and manually selected using predefined inclusion and exclusion criteria, leading to 72 selected publications out of 1960 candidates. We identify common challenges, structure solutions, and provide recommendations for future systems. This work is based on publications from the end of 2010 to July 2015 and is also compared to older but similar surveys.

A Glimpse into Babel

“…for topic mining in [11]. A possible use of multilingual data is Question Answering over Linked Data, as in [1,7]. [14] investigates how multilingual ontologies can facilitate question answering.…”

Core techniques of question answering systems over knowledge bases: a survey

“…Lexical gap, Vocabulary gap (Lopez et al 2011) 2004-11, (Lopez et al 2013), 2005-12, (Freitas et al 2012), 2004-11, (Freitas et al 2015, 2011-12, (Höffner et al 2016(Höffner et al ), 2011 Query and databases may not be expressed using the same vocabulary (synonymy) or at the same level of abstraction. It requires to bridge the gap between the vocabulary in the user query and the KB vocabulary Mapping Multilingual QA ) QALD-3, ) QALD-4, (Höffner et al 2016(Höffner et al ), 2011 Mediates between a user expressing an information need in her own language and the semantic data Question Analysis, Mapping Light expression Vagueness Lexical ambiguity (Cimiano & Minock 2009), 2004-07, (Lopez et al 2011), 2004-11, (Lopez et al 2013), 2005-12, (Freitas et al 2015), 2004-11, (Höffner et al 2016 Queries with words that can be interpreted through different ontological entities or semantically weak constructions.…”

“…Moreover, we point to some techniques used by QA systems evaluated over WebQuestions and SimpleQuestions. The existing QALD reports ) ) ) ) (Unger et al 2016), surveys on the challenges faced by open domain QA systems over KBs (Lopez et al 2011) (Freitas et al 2012) and the latest survey on the topic (Höffner et al 2016) gives short overviews for each QA system. They do not allow for a detailed comparison of the techniques used in each of the stages of the QA process.…”

“…It requires to bridge the gap between the vocabulary in the user query and the KB vocabulary Mapping Multilingual QA ) QALD-3, ) QALD-4, (Höffner et al 2016(Höffner et al ), 2011 Mediates between a user expressing an information need in her own language and the semantic data Question Analysis, Mapping Light expression Vagueness Lexical ambiguity (Cimiano & Minock 2009), 2004-07, (Lopez et al 2011), 2004-11, (Lopez et al 2013), 2005-12, (Freitas et al 2015), 2004-11, (Höffner et al 2016 Queries with words that can be interpreted through different ontological entities or semantically weak constructions. Relations that are expressed implicitly with the use of verbs such as be/have or light prepositions that can convey different meanings Disambiguation Semantic gap Conceptual complexity ), 2005-12, (Freitas et al 2012), 2004-11, (Freitas et al 2015 Queries that are not necessarily structured in the knowledge base in the same way than in the question.…”

MoRS at SemEval-2017 Task 3: Easy to use SVM in Ranking Tasks

“…In recent times, QA systems have attracted great interest in the information retrieval community, and also in the cQA (Höffner et al, 2016).…”