Comparing noun phrasing techniques for use with medical digital library tools

Abstract

In an effort to assist medical researchers and professionals in accessing information necessary for their work, the A1 Lab at the University of Arizona is investigating the use of a natural language processing (NLP) technique called noun phrasing. The goal of this research is to determine whether noun phrasing could be a viable technique to include in medical information retrieval applications. Four noun phrase generation tools were evaluated as to their ability to isolate noun phrases from medical journal abstracts. Tests were conducted using the National Cancer Institute's CANCERLIT database. The NLP tools evaluated were Massachusetts Institute of Technology's (MIT's) Chopper, The University of Arizona's Automatic Indexer, Lingsoft's NPtool, and The University of Arizona's AZ Noun Phraser. In addition, the National Library of Medicine's SPECIALIST Lexicon was incorporated into two versions of the AZ Noun Phraser to be evaluated against the other tools as well as a nonaugmented version of the AZ Noun Phraser. Using the metrics relative subject recall and precision, our results show that, with the exception of Chopper, the phrasing tools were fairly comparable in recall and precision. It was also shown that augmenting the AZ Noun Phraser by including the SPECIALIST Lexicon from the National Library of Medicine resulted in improved recall and precision.

A quantitative stock prediction system based on financial news

“…An improved representational system which addresses these shortcomings is Noun Phrases. This representation focuses on retaining only the nouns and noun phrases present within a document and has been found to adequately represent the important article concepts (Tolle & Chen, 2000). As a consequence of its noun-centric activity, this technique uses fewer terms and can handle article scaling better than Bag of Words.…”

“…To identify the proper nouns we chose a modified version of the Arizona Text Extractor (AzTeK) system which performs semantic/syntactic word level tagging as well as phrase-based aggregation. AzTeK works by using a syntactic tagger to identify and aggregate the document's noun phrases and was found to have an 85% F-measure for both precision and recall, which is comparable to other tools (Tolle & Chen, 2000). Although the AzTeK system was selected due to availability, it performs adequately for proper noun extraction.…”

Finding nuggets in documents: A machine learning approach

“…Measuring precision and recall against author keyphrases is easy to carry out, and it allows more precise comparison between different keyphrase extraction systems. Previous studies have used this measure and found it is an appropriate method to measure the effectiveness of a keyphrase extraction system (Jones & Paynter, 2002;Turney, 2000;Frank et al, 1999;Tolle & Chen, 2000). We used 50 papers as the test documents in this evaluation.…”

“…Jones and Paynter (2002) used six papers to evaluate Kea's precision and recall. Tolle and Chen (2000) tested 10 documents to compare their algorithm to NPtool. Frank et al (1999) used 20 journal articles and 35 FIPS Web pages to compare Kea and Extractor.…”

Supporting Multilingual Information Retrieval in Web Applications: An English-Chinese Web Portal Experiment

“…We built our own lexicon for the IT business domain in both English and Chinese in order to support query expansion using the Arizona Noun Phraser [12] and the Mutual Information technique [10]. The extracted terms were used as the lexicons for both preand post-translation query expansion.…”