Header

UZH-Logo

Maintenance Infos

A Hybrid Entity-Mention Pronoun Resolution Model for German Using Markov Logic Networks


Tuggener, Don; Klenner, Manfred (2014). A Hybrid Entity-Mention Pronoun Resolution Model for German Using Markov Logic Networks. In: KONVENS 2014, Hildesheim, 8 October 2014 - 10 October 2014, 21-29.

Abstract

This paper presents a hybrid pronoun reso- lution system for German. It uses a simple rule-driven entity-mention formalism to in- crementally process discourse entities. An- tecedent selection is performed based on Markov Logic Networks (MLNs). The hy- brid architecture yields a cheap problem formulation in the MLNs w.r.t. inference complexity but pertains their expressive- ness. We compare the system to a rule- driven baseline and an extension which uses a memory-based learner. We find that the MLN hybrid outperforms its competi- tors by large margins.

Abstract

This paper presents a hybrid pronoun reso- lution system for German. It uses a simple rule-driven entity-mention formalism to in- crementally process discourse entities. An- tecedent selection is performed based on Markov Logic Networks (MLNs). The hy- brid architecture yields a cheap problem formulation in the MLNs w.r.t. inference complexity but pertains their expressive- ness. We compare the system to a rule- driven baseline and an extension which uses a memory-based learner. We find that the MLN hybrid outperforms its competi- tors by large margins.

Statistics

Altmetrics

Downloads

193 downloads since deposited on 16 Oct 2014
78 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:Coreference Resolution Pronoun Resolution
Language:English
Event End Date:10 October 2014
Deposited On:16 Oct 2014 21:22
Last Modified:18 Aug 2017 10:33
Publisher:s.n.
ISBN:3-934105-46-7

Download

Preview Icon on Download
Preview
Filetype: PDF
Size: 224kB