Ophélie Lacroix

3 paper cards in Mova's library · 2014–2018

Ophélie Lacroix wrote 3 of the papers Mova reads, in 2014–2018, most of them on Dependency parsing, Universal Dependencies, Treebanks; often with Denis Béchet, François Yvon, Guillaume Wisniewski.

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

Papers

Investigating NP-Chunking with Universal Dependencies for English (2018)
Chunks are normally taken from constituency trees, but UD has no chunk layer. The paper derives minimal noun-phrase chunks (B-NP, I-NP, O tags) from EWT dependency trees by rules over the core token (noun, proper noun, some pronouns) and its children, excluding prepositional phrases. A manual check of 233 chunks in…
Automatically Selecting the Best Dependency Annotation Design with Dynamic Oracles (2018)
Several conventions exist for the same dependency structure, for example whether a content word or a function word heads a case marker, a copula, a conjunction or a determiner.
Validation Issues induced by an Automatic Pre-Annotation Mechanism in the Building of Non-projective Dependency Treebanks (2014)
The CDG Lab builds dependency treebanks with a grammar-based parser. Before parsing, an annotator fills a long selection form, which is slow. The authors replace it with an automatic pre-annotation mechanism that segments the sentence and proposes lexical units, but this creates new validation problems: some false…