---
title: "Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge"
authors:
  - "Massimiliano Ciaramita"
  - "Thomas Hofmann"
  - "Mark Johnson"
doi: ""
url: "https://ijcai.org/proceedings/2003/118"
pdf: "https://ijcai.org/proceedings/2003/0118.pdf"
venue: "Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence"
year: 2003
pages: "817-821"
track: ""
keywords:
---

# Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge

Massimiliano Ciaramita, Thomas Hofmann, Mark Johnson

*Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence*, pages 817-821.

## Abstract

We present a learning architecture for lexical semantic classification problems that supplements task-specific training data with background data encoding general "world knowledge". The model compiles knowledge contained in a dictionaryontology into additional training data, and integrates task-specific and background data through a novel hierarchical learning architecture. Experiments on a word sense disambiguation task provide empirical evidence that this "hierarchical classifier" outperforms a state-of-the-art standard "flat" one.