Comparing Knowledge Sources for Nominal Anaphora Resolution

@article{Markert2005ComparingKS,
  title={Comparing Knowledge Sources for Nominal Anaphora Resolution},
  author={Katja Markert and Malvina Nissim},
  journal={Computational Linguistics},
  year={2005},
  volume={31},
  pages={367-402}
}
We compare two ways of obtaining lexical knowledge for antecedent selection in other-anaphora and definite noun phrase coreference. Specifically, we compare an algorithm that relies on links encoded in the manually created lexical hierarchy WordNet and an algorithm that mines corpora by means of shallow lexico-semantic patterns. As corpora we use the British National Corpus (BNC), as well as the Web, which has not been previously used for this task. Our results show that (a) the knowledge… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 50 CITATIONS

Using Lexical and Encyclopedic Knowledge

  • Anaphora Resolution - Algorithms, Resources, and Applications
  • 2016
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Coreference Semantics from Web Features

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Modelling Entity Instantiations

VIEW 6 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

ELERFED: Final Report

VIEW 18 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Using the Web to Resolve Coreferent Bridging in German Newspaper Text

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Surface Web Semantics for Structured Natural Language Processing

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Automatic lexico-semantic acquisition for question answering

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2004
2016

CITATION STATISTICS

  • 8 Highly Influenced Citations