MITA: An Information-Extraction Approach to the Analysis of Free-Form Text in Life Insurance Applications

By Glasgow, Barry; Mandell, Alan et al. | AI Magazine, Spring 1998 | Go to article overview

MITA: An Information-Extraction Approach to the Analysis of Free-Form Text in Life Insurance Applications


Glasgow, Barry, Mandell, Alan, Binney, Dan, Ghemri, Lila, Fisher, David, AI Magazine


MetLife's insurance application is designed to elicit the maximum amount of information relating to the client so that a fair contract can be reached between the client and Metlife. The application contains questions that can be answered by structured data fields (yes-no or pick lists) as well as questions that require free-form textual answers.

Currently, MetLife's Individual Business Personal Insurance unit employs over 120 underwriters and processes in excess of 260,000 life insurance applications a year. MetLife's goal is to become more efficient and effective by allowing the underwriters to concentrate on the unusual and difficult aspects of a case and automate the more mundane and mechanical aspects. A 10-percent improvement in productivity for MetLife, while it still maintains the already existing high quality of the underwriting processing, or an increase in the consistency of the process will have sizable effects.

The use of expert systems to improve the insurance underwriting process has been the "holy grail" of the insurance industry, and many insurance companies have developed expert systems for this purpose with moderate success. A daunting problem has been the presence of textual fields.

MetLife's intelligent text analyzer (MITA) is an attempt to solve this problem using information extraction. Using this technique on the textual portion of the application allows the automation of underwriting review to a greater extent than previously possible.

Extracting information from free-form textual fields is a recurring problem in many information systems. Senator et al. (1995) discuss the need to analyze textual fields containing occupations and business types to detect financial crimes.

Mita Overview

Previous attempts have been made to understand the text fields on MetLife's insurance applications by means of keywords or simple parsing. These attempts have been inadequate. The application of full semantic natural language processing (NLP) was deemed too complex and unnecessary because the text often contains details that are not directly relevant to the decision making. A happy compromise -- information extraction -- was recently developed.

The MITA free-form text analyzers take in unstructured text, identify any concepts that might have underwriting significance, and return a categorization of the concepts for interpretation and analysis for risk assessment by subsequent domain-specific analyzers. By localizing the natural language processing of the input text in MITA, other domain-specific analyzers can focus on codifying underwriting domain knowledge.

The fields analyzed by MITA include a Physician Reason field that describes the reason a proposed insured last visited a personal physician, a Family History field that describes a proposed insured's family medical history, a Major Treatments and Exams field that describes any major medical event within the last five years, a Not Revealed field that includes any important medical information not provided in other questions, and an Occupation Title and Duty field that describes the proposed insured's employment.

AI in Mita

The information-extraction approach of NLP was chosen for use in MITA. The system was engineered based on a corpus of actual application texts. This approach was intended to provide an information-extraction system optimized for MetLife's insurance application text-processing needs.

Information Extraction

Analysis of free-form text has been pursued mainly from three viewpoints: (1) a keyword approach, (2) an in-depth natural language-analysis approach, and (3) an information-extraction approach.

The keyword approach, whereby the input text is scanned for words that are deemed highly relevant to the application at hand, has the advantage of being relatively easy to implement. However, it is of limited usefulness for accurate data extraction, which is a requirement of MITA. …

The rest of this article is only available to active members of Questia

Already a member? Log in now.

Notes for this article

Add a new note
If you are trying to select text to create highlights or citations, remember that you must now click or tap on the first word, and then click or tap on the last word.
One moment ...
Default project is now your active project.
Project items
Notes
Cite this article

Cited article

Style
Citations are available only to our active members.
Buy instant access to cite pages or passages in MLA 8, MLA 7, APA and Chicago citation styles.

(Einhorn, 1992, p. 25)

(Einhorn 25)

(Einhorn 25)

1. Lois J. Einhorn, Abraham Lincoln, the Orator: Penetrating the Lincoln Legend (Westport, CT: Greenwood Press, 1992), 25, http://www.questia.com/read/27419298.

Note: primary sources have slightly different requirements for citation. Please see these guidelines for more information.

Cited article

MITA: An Information-Extraction Approach to the Analysis of Free-Form Text in Life Insurance Applications
Settings

Settings

Typeface
Text size Smaller Larger Reset View mode
Search within

Search within this article

Look up

Look up a word

  • Dictionary
  • Thesaurus
Please submit a word or phrase above.
Print this page

Print this page

Why can't I print more than one page at a time?

Help
Full screen
Items saved from this article
  • Highlights & Notes
  • Citations
Some of your highlights are legacy items.

Highlights saved before July 30, 2012 will not be displayed on their respective source pages.

You can easily re-create the highlights by opening the book page or article, selecting the text, and clicking “Highlight.”

matching results for page

    Questia reader help

    How to highlight and cite specific passages

    1. Click or tap the first word you want to select.
    2. Click or tap the last word you want to select, and you’ll see everything in between get selected.
    3. You’ll then get a menu of options like creating a highlight or a citation from that passage of text.

    OK, got it!

    Cited passage

    Style
    Citations are available only to our active members.
    Buy instant access to cite pages or passages in MLA 8, MLA 7, APA and Chicago citation styles.

    "Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn, 1992, p. 25).

    "Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn 25)

    "Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences." (Einhorn 25)

    "Portraying himself as an honest, ordinary person helped Lincoln identify with his audiences."1

    1. Lois J. Einhorn, Abraham Lincoln, the Orator: Penetrating the Lincoln Legend (Westport, CT: Greenwood Press, 1992), 25, http://www.questia.com/read/27419298.

    Cited passage

    Thanks for trying Questia!

    Please continue trying out our research tools, but please note, full functionality is available only to our active members.

    Your work will be lost once you leave this Web page.

    Buy instant access to save your work.

    Already a member? Log in now.

    Search by... Author
    Show... All Results Primary Sources Peer-reviewed

    Oops!

    An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.