---
title: "Open Domain Short Text Conceptualization: A Generative + Descriptive Modeling Approach"
authors:
  - "Yangqiu Song"
  - "Shusen Wang"
  - "Haixun Wang"
doi: ""
url: "https://ijcai.org/proceedings/2015/537"
pdf: "https://ijcai.org/proceedings/2015/0537.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "3820-3825"
track: "Special Track on Machine Learning"
keywords:
---

# Open Domain Short Text Conceptualization: A Generative + Descriptive Modeling Approach

Yangqiu Song, Shusen Wang, Haixun Wang

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 3820-3825.

## Abstract

Concepts embody the knowledge to facilitate our cognitive processes of learning. Mapping short texts to a large set of open domain concepts has gained many successful applications. In this paper, we unify the existing conceptualization methods from a Bayesian perspective, and discuss the three modeling approaches: descriptive, generative, and discriminative models. Motivated by the discussion of their advantages and shortcomings, we develop a generative + descriptive modeling approach. Our model considers term relatedness in the context, and will result in disambiguated conceptualization. We show the results of short text clustering using a news title data set and a Twitter message data set, and demonstrate the effectiveness of the developed approach compared with the state-of-the-art conceptualization and topic modeling approaches.