Natalia Silveira
Natalia Silveira wrote 4 of the papers Mova reads, in 2013–2016, most of them on Universal Dependencies, Treebanks, Part-of-speech tagging; often with Christopher D. Manning, Marie-Catherine de Marneffe, Filip Ginter.
Topics: Universal Dependencies 2 · Treebanks 1 · Part-of-speech tagging 1
Papers
- Universal Dependencies v1: A Multilingual Treebank Collection (2016)
The paper is the reference for the first UD release. It sets out the design principles: dependency-based and lexicalist annotation, the recoverability principle (every syntactic word must map back to the raw text), content words as the backbone of the tree with function words as dependents, and a closed inventory of… - Does Universal Dependencies need a parsing representation? An investigation of English (2015)
UD makes content words the heads and attaches function words (auxiliaries, copulas, subordinators, adpositions) to them. - Universal Stanford dependencies: A cross-linguistic typology (2014)
The paper reconstructs the typology behind Stanford Dependencies and proposes a two-layer taxonomy: 42 universal grammatical relations that are broadly attested across languages, with language-specific subtypes added under them. - More Constructions, More Genres: Extending Stanford Dependencies (2013)
The Stanford scheme was built on newswire and gives little analysis to constructions that are rare there but common in web text: tough adjectives, free relatives, comparatives, small clauses, questions, imperatives, fragments and lists.
Co-authors (16)
- Christopher D. Manning ×3
- Marie-Catherine de Marneffe ×3
- Filip Ginter ×2
- Joakim Nivre ×2
- Timothy Dozat ×2
- Christopher Manning
- Daniel Zeman
- Jan Hajič
- Katri Haverinen
- Miriam Connor
- Reut Tsarfaty
- Ryan McDonald
- Sampo Pyysalo
- Samuel R. Bowman
- Slav Petrov
- Yoav Goldberg
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/natalia-silveira/