Shashi Narayan

2 paper cards in Mova's library · 2016–2017

Shashi Narayan wrote 2 of the papers Mova reads, in 2016–2017, most of them on Machine translation; often with Claire Gardent, Anastasia Shimorina, Laura Perez-Beltrachini.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

The WebNLG Challenge: Generating Text from RDF Data (2017)
The WebNLG challenge maps sets of RDF triples taken from DBpedia to text, and is built to test microplanning: referring expressions, aggregation, lexicalisation, surface realisation and sentence segmentation chosen together.
Unsupervised Sentence Simplification Using Deep Semantics (2016)
The system simplifies sentences with neither hand-written rules nor an aligned training corpus. It parses each sentence into a discourse representation structure (DRS), a deep semantic graph whose nodes are events and entities, and applies substitution, reordering, splitting and deletion on that graph, not on words…