Dan Jurafsky

4 paper cards in Mova's library · 2010–2013

Dan Jurafsky wrote 4 of the papers Mova reads, in 2010–2013, most of them on Coreference resolution, Dependency parsing; often with Heeyoung Lee, Mihai Surdeanu, Nathanael Chambers.

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

Papers

Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules (2013) measured
This journal article is the full description of the Stanford multi-pass sieve coreference system, which won the CoNLL-2011 shared task.
Stanford's Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task (2011)
The system is a sequence of deterministic sieves, ordered from highest to lowest precision. Each sieve links clusters, not single mentions, and the clusters share attributes such as gender, number and animacy. The authors add a high-recall mention-detection sieve in front. Its exclusion rules remove pleonastic "it"…
A Multi-Pass Sieve for Coreference Resolution (2010) measured
The paper proposes an unsupervised, deterministic coreference system built as a sequence of "sieves": independent rule-based passes applied from the most precise to the least precise.
Parsing to Stanford Dependencies: Trade-offs between Speed and Accuracy (2010)
The authors compare ways of producing Stanford Dependencies quickly. One group is constituency parsers (Stanford, Charniak, Charniak-Johnson reranker, Bikel, Berkeley) followed by a conversion to dependencies; the other is dependency parsers trained directly on the basic dependencies (MaltParser's Nivre variants…