Blei et al, 2002

Citation

Blei, D., Bagnell, J., & McCallum, A. ͑2002͒. Learning with scope, with application to information extraction and classification. In Proceedings of the 2002 Conference on Uncertainty in Artificial Intelligence.

Online version

[[1]]

Summary

This paper introduces a novel hierarchical probabilistic model that combines both global and local features in the learning process. They have applied their technique for extracting structured data from webpages. In this problem, word count can be considered as a traditional iid feature (i.e. global feature) and word formatting in the web page can also be considered as local features. These local features are called in this paper also as scope limited features.

The intuition behind their technique is to use global features to infer rules about the local features. For example suppose that we know the name of a set of books. Then by looking at webpages of Amazon.com and by searching the name of the books that we already have we can infer the position and font of the book title. We can then use these two features (position and font of book title in web pages) to extract new book titles from other web pages.

They have described both generative and discriminative approaches for classification and extraction tasks. Global features are governed by the parameters that are shared by all the data and local features are shared only by a subset of data. For example in information extraction task, all the words in a webpage (without considering formatting) can be considered as global features. On the other hand, features such as position of a text or color of text are local features.

In generative model they have modeled each document by introducing a random variable that governs local feature. The parameters of the model are:

- N words of the documents are shown by $w=\{w_{1},w_{2},...,w_{N}\}$

- Formatting features are shown by $f=\{f_{1},f_{2},...,f_{N}\}$

- Class labels are shown by $c=\{c_{1},c_{2},...,c_{N}\}$

They have tested their method on two different datasets. The first dataset contains 1000 HTML documents. Each document is automatically divided into a set of words with similar layout characteristics and then are hand-labeled as containing or not containing a job title. The local and global features for this domain are the same as what we explained above. The second dataset contains 42,548 web pages from 330 web sites which each web page is hand-labeled as if it is a press release or not press release. The global feature is a set of word in each webpage and local feature is the URL of the webpage. Their experimental result have shown that this approach can obtain high precision and low/moderate recall.