Generation of Zero Pronouns Based on the Centering Theory and Pairwise Salience of Entities

2006 ◽  
Vol E89-D (2) ◽  
pp. 837-846 ◽  
Author(s):  
J.-E. ROH
2001 ◽  
Vol 27 (4) ◽  
pp. 579-587 ◽  
Author(s):  
Rodger Kibble

The standard preference ordering on the well-known centering transitions Continue, Retain, Shift is argued to be unmotivated: a partial, context-dependent ordering emerges from the interaction between principles dubbed cohesion (maintaining the same center of attention) and salience (realizing the center of attention as the most prominent NP). A new formulation of Rule 2 of centering theory is proposed that incorporates these principles as well as a streamlined version of Strube and Hahn's (1999) notion of cheapness. It is argued that this formulation provides a natural way to handle “topic switches” that appear to violate the canonical preference ordering.


2002 ◽  
Vol 8 (1) ◽  
pp. 69-89 ◽  
Author(s):  
ÖZGÜR YÜKSEL ◽  
CEM BOZSAHIN

We describe a system for contextually appropriate anaphor and pronoun generation for Turkish. It uses binding theory and centering theory to model local and nonlocal references. We describe the rules for Turkish, and their computational treatment. A cascaded method for anaphor and pronoun generation is proposed for handling pro-drop and discourse constraints on pronominalization. The system has been tested as a stand-alone nominal expression generator, and also as a reference planning component of a transfer-based MT system.


2015 ◽  
Vol 71 (1-2) ◽  
pp. 69-87
Author(s):  
Radoslava Trnavac

The aim of the paper is to map various types of anaphor to the centering transitions in the corpus of Serbian newspaper articles. Centering Theory (WALKER, JOSHI ET AL. 1998) is a theory of local coherence in which four types of transitions are used as parameters of coherence. As is hypothesized in the previous literature based on various languages, the CONTINUE transition is mostly characterized by a minimal form (a zero form of the topic), while the SMOOTH and ROUGH shifts are found with a full noun phrase topic. The analysis shows that the ?Ordering Rule? of Centering Theory is not fully followed in the written corpus of the Serbian language since SMOOTH SHIFT has been identified as a prevalent type of transition in the corpus. The following two reasons were identified for that: (1) the genre of the newspaper articles, and (2) the way clauses are combined within a complex sentence in the Serbian written corpus.


2009 ◽  
Vol 35 (1) ◽  
pp. 29-46 ◽  
Author(s):  
Nikiforos Karamanis ◽  
Chris Mellish ◽  
Massimo Poesio ◽  
Jon Oberlander

In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclusively on NOCB transitions) sets a robust baseline that cannot be outperformed by other metrics which make use of additional centering-based features. This baseline can be used for the development of both text-to-text and concept-to-text generation systems.


Sign in / Sign up

Export Citation Format

Share Document