Finding needles in the haystack: Search and candidate generation

69 citations recorded by the source corpus.

How researchers see this paper

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

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (2019, background): “Most previous work on open-domain QA has focused on mitigating error propagation of re-triever models in a pipelined setting (Chu-Carroll et al., 2012).”
Information Extraction over Structured Data: Question Answering with Freebase (2014, methodology): “Heuristics and manual templates were also commonly used (Chu-Carroll et al., 2012).”
Modeling of the Question Answering Task in the YodaQA System (2015, methodology): “For informational retrieval, we use Apache Solr 7 and include the document and title-in-clue strategies described in DeepQA [5].”
YodaQA: A Modular Question Answering System Pipeline (2015, methodology): “Full-text search [7] runs a full-text clue search in the article texts and titles, considering the top six results.”
Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering (2017, background): “These raw data are also indexed in search clusters to support user queries (Fan et al. 2012; Chu-Carroll et al. 2012).”
Natural Language Questions for the Web of Data (2012, background): “…Freebase (Bollacker et al., 2008), and Yago (Suchanek et al., 2007)) are used for both answering parts of questions that can be translated to structured form (Chu-Carroll et al., 2012) and typechecking possible answer candidates and thus filtering out spurious results (Kalyanpur et al., 2011).”