Template-based question answering over RDF data

By Christina Unger, Lorenz Bühmann, Jens Lehmann, Axel-Cyrille Ngonga Ngomo, Daniel Gerber, Philipp Cimiano. 2012

544 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Semantic Parsing on Freebase from Question-Answer Pairs (2013, methodology): “Previous work on semantic parsing on Freebase uses a combination of manual rules (Yahya et al., 2012; Unger et al., 2012), distant supervision (Krishnamurthy and Mitchell, 2012), and schema”
Compositional Semantic Parsing on Semi-Structured Tables (2015, methodology): “A lexicon can be automatically generated (Unger and Cimiano, 2011; Unger et al., 2012), learned from data (Zettlemoyer and Collins, 2007; Kwiatkowski et al.”
Question Answering with Subgraph Embeddings (2014, background): “e a broad set of candidate answers by querying the search API of KBs with a transformation of the question into a valid query and then use ne-grained detection heuristics to identify the exact answer [8,12,14]. On the other hand, semantic parsing methods focus on the correct interpretation of the me”
Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, background): “Recent efforts to build natural language interfaces to large databases, for example DBpedia (Yahya et al., 2012; Unger et al., 2012), have also used handengineered ontology matching techniques.”
Open Question Answering with Weakly Supervised Embedding Models (2014, methodology): “The earliest methods for open question-answering with KBs, based on hand-written templates [25,21], were not robust enough to such variability over possibly evolving KBs (addition/deletion of triples and entities).”
Explicit Knowledge-based Reasoning for Visual Question Answering (2015, methodology): “ailable. The advances in structured KBs, have driven an increasing interest in the NLP and AI communities in the problem of natural language question answering using structured KBs (refer to as KBQA) [4, 7, 8, 16, 23, 25, 41, 26, 38]. The VQA approach which is closest to KB-QA (and to our approach) ”
Information Extraction over Structured Data: Question Answering with Freebase (2014, methodology): “Finally, the KB community has developed other means for QA without semantic parsing (Lopez et al., 2005; Frank et al., 2007; Unger et al., 2012; Yahya et al., 2012; Shekarpour et al., 2013).”
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, methodology): “, 2016; Yao and Van Durme, 2014) or DBpedia (Lopez et al., 2010; Unger et al., 2012)) have been used for question answering (Yu and Lam, 2018).”
FVQA: Fact-Based Visual Question Answering (2016, background): “KBQA approaches can be divided into two categories: semantic parsing methods [37]–[47] that try to translate questions into accurate logical expressions and then map to KB queries, and information retrieval methods [48]–[54] that coarsely retrieve a set of answer candidates and then perform ranking.”
Adaptive Document Retrieval for Deep Question Answering (2018, neutral): “On the one hand, knowledge-based systems draw upon manual rules, ontologies and large-scale knowledge graphs in order to deduce answers (e. g. Berant et al., 2013; Lopez et al., 2007; Unger et al., 2012).”
SLiQA-I: Towards Cold-start Development of End-to-end Spoken Language Interface for Question Answering (2019, background): “QA engine: Most recent works [7, 8, 9, 10, 14] are designed based on predefined templates.”
ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters (2018, background): “This has two motivations: (i) it builds on the example of search engines that use Wikipedia as a primary way of answering entity-centric queries (e.g., through knowledge cards), and (ii) most modern KBs ground their entities in Wikipedia.”
Bridging the Semantic Gap with SQL Query Logs in Natural Language Interfaces to Databases (2019, background): “Such systems often utilize intermediate representations in the NLQ to SQL translation process, such as a parse tree [22], query sketch [37], [41], or an ontology [33].”
Paraphrase-Driven Learning for Open Question Answering (2013, background): “Some work has been made towards more general databases like DBpedia (Yahya et al., 2012; Unger et al., 2012), but these systems rely on hand-written templates for question interpretation.”
Question Answering on Freebase via Relation Extraction and Textual Evidence (2016, background): “While initial progress on structured QA started with small toy domains like GeoQuery (Zelle and Mooney, 1996), recent focus has shifted to large scale structured KBs like Freebase, DBPedia (Unger et al., 2012; Cai and Yates, 2013; Berant et al., 2013; Kwiatkowski et al., 2013; Xu et al., 2014), and ”
Core techniques of question answering systems over knowledge bases: a survey (2017, unknown): “This technique is for example used in TBSL (Unger et al. 2012).”
Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering (2018, background): “There has been interest in the natural language processing community in answering questions based on knowledge bases (KBs) using either semantic parsing [37,38,39,40,41,42,43,44,45,46,47] or information retrieval [48,49,50,51,52,53,54] methods.”
Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae (2014, methodology): “A system that does not rely on grammars but uses a linguistic component very close to the one presented in this chapter is TBSL [Unger et al., 2012], a template-based approach to the construction of SPARQL queries.”
DBpedia - A large-scale, multilingual knowledge base extracted from Wikipedia (2015, methodology): “Several QA systems, such as TBSL [41], PowerAqua [28], FREyA [9] and QAKiS [6] have been applied to DBpedia using the QALD benchmark questions.”