Abstract

MotivationPredicting the part of speech (POS) tag of an unknown word in a sentence is a significant challenge. This is particularly difficult in biomedicine, where POS tags serve as an input to training sophisticated literature summarization techniques, such as those based on Hidden Markov Models (HMM). Different approaches have been taken to deal with the POS tagger challenge, but with one exception – the TnT POS tagger - previous publications on POS tagging have omitted details of the suffix analysis used for handling unknown words. The suffix of an English word is a strong predictor of a POS tag for that word. As a pre-requisite for an accurate HMM POS tagger for biomedical publications, we present an efficient suffix prediction method for integration into a POS tagger.ResultsWe have implemented a fully functional HMM POS tagger using experimentally optimised suffix based prediction. Our simple suffix analysis method, significantly outperformed the probability interpolation based TnT method. We have also shown how important suffix analysis can be for probability estimation of a known word (in the training corpus) with an unseen POS tag; a common scenario with a small training corpus. We then integrated this simple method in our POS tagger and determined an optimised parameter set for both methods, which can help developers to optimise their current algorithm, based on our results. We also introduce the concept of counting methods in maximum likelihood estimation for the first time and show how counting methods can affect the prediction result. Finally, we describe how machine-learning techniques were applied to identify words, for which prediction of POS tags were always incorrect and propose a method to handle words of this type.Availability and ImplementationJava source code, binaries and setup instructions are freely available at http://genomes.sapac.edu.au/text_mining/pos_tagger.zip.

Highlights

  • Hidden Markov Models (HMM) have been used in Part-OfSpeech (POS) tagging of text for 30 years

  • We have shown how important suffix analysis can be for probability estimation of a known word with an unseen POS tag; a common scenario with a small training corpus

  • We introduce the concept of counting methods in maximum likelihood estimation for the first time and show how counting methods can affect the prediction result

Read more

Summary

Introduction

Hidden Markov Models (HMM) have been used in Part-OfSpeech (POS) tagging of text for 30 years. The existence of special characters (capitals, numbers, hyphens or symbols) is the first characteristic used to predict a word tag. If a new word does not contain any special characters, when that word is made of all alphabetic lower case characters, the best method to predict a word tag is to examine the lexical structure of the word, such as the suffix and postfix. In English and some other languages, the suffix is a strong predictive feature for word tagging. We used TnT’s suffix analysis method to handle new words. Subsequent testing of TnT system gave an unsatisfactory result for suffix analysis, prompting us to design and implement a novel method, which increased accuracy from 66 to 95 percent

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.