Maximum entropy markov models for information extraction and segmentation

DMCA

Maximum entropy markov models for information extraction and segmentation (2000)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Andrew McCallum , Dayne Freitag , Fernando Pereira

Citations:

552 - 17 self

BibTeX

@INPROCEEDINGS{McCallum00maximumentropy,
    author = {Andrew McCallum and Dayne Freitag and Fernando Pereira},
    title = {Maximum entropy markov models for information extraction and segmentation},
    booktitle = {},
    year = {2000},
    pages = {591--598},
    publisher = {Morgan Kaufmann}
}

OpenURL

Abstract

Hidden Markov models (HMMs) are a powerful probabilistic tool for modeling sequential data, and have been applied with success to many text-related tasks, such as part-of-speech tagging, text segmentation and information extraction. In these cases, the observations are usually modeled as multinomial distributions over a discrete vocabulary, and the HMM parameters are set to maximize the likelihood of the observations. This paper presents a new Markovian sequence model, closely related to HMMs, that allows observations to be represented as arbitrary overlapping features (such as word, capitalization, formatting, part-of-speech), and defines the conditional probability of state sequences given observation sequences. It does this by using the maximum entropy framework to fit a set of exponential models that represent the probability of a state given an observation and the previous state. We present positive experimental results on the segmentation of FAQ’s.

Keyphrases

information extraction maximum entropy markov model observation sequence discrete vocabulary new markovian sequence model powerful probabilistic tool part-of-speech tagging text segmentation state sequence previous state maximum entropy framework hidden markov model exponential model present positive experimental result sequential data hmm parameter multinomial distribution arbitrary overlapping feature conditional probability many text-related task

DMCA