Timothy Dozat

4 paper cards in Mova's library · 2013–2017

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

Papers

Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task (2017)
The Stanford system is a biaffine graph parser: a BiLSTM encoder, separate ReLU layers for the head and dependent roles of arcs and labels, and biaffine scorers for arcs and labels.
Deep Biaffine Attention for Neural Dependency Parsing (2016)
The paper builds on the neural graph-based parser of Kiperwasser and Goldberg. It uses a larger and more heavily regularised BiLSTM encoder, passes the top recurrent states through dimension-reducing MLPs, and replaces the MLP attention and the affine label classifier with biaffine ones: one for arc scores over all…
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.