Extracting statistical mentions from textual claims to provide trusted content

Abstract : Claims on statistic (numerical) data, e.g., immigrant populations , are often fact-checked. We present a novel approach to extract from text documents, e.g., online media articles, mentions of statistic entities from a reference source. A claim states that an entity has certain value, at a certain time. This completes a fact-checking pipeline from text, to the reference data closest to the claim. We evaluated our method on the INSEE dataset and show that it is efficient and effective.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-02121389
Contributor : Tien-Duc Cao <>
Submitted on : Monday, May 6, 2019 - 3:16:41 PM
Last modification on : Friday, September 6, 2019 - 1:28:41 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02121389, version 1

Citation

Tien Duc Cao, Ioana Manolescu, Xavier Tannier. Extracting statistical mentions from textual claims to provide trusted content. NLDB, Jun 2019, Salford, United Kingdom. ⟨hal-02121389⟩

Share

Metrics

Record views

164

Files downloads

1040