Unsupervised Large-Vocabulary Word Sense Disambiguation with Graph-based Algorithms for Sequence Data Labeling

Description:

This paper introduces a graph-based algorithm for sequence data labeling, using random walks on graphs encoding label dependencies. The algorithm is illustrated and tested in the context of an unsupervised word sense disambiguation problem, and shown to significantly outperform the accuracy achieved through individual label assignment, as measured on standard sense-annotated data sets.

Creator(s): Mihalcea, Rada, 1974-
Creation Date: October 2005
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 143
Past 30 days: 3
Yesterday: 0
Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas

Publisher Info:
Place of Publication: [Stroudsburg, Pennsylvania]
Date(s):
  • Creation: October 2005
Description:

This paper introduces a graph-based algorithm for sequence data labeling, using random walks on graphs encoding label dependencies. The algorithm is illustrated and tested in the context of an unsupervised word sense disambiguation problem, and shown to significantly outperform the accuracy achieved through individual label assignment, as measured on standard sense-annotated data sets.

Degree:
Physical Description:

8 p.

Language(s):
Subject(s):
Keyword(s): sequence data labeling | natural language processing | linguistic annotations
Source: Joint Conference on Human Language Technology / Empirical Methods in Natural Language Processing (HLT/EMNLP), 2005, Vancouver, British Columbia, Canada
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc30977
Resource Type: Paper
Format: Text
Rights:
Access: Public