SentiMap - Sentence Handling Toolkit : exploit English sentences in your business applications

Sentence Analyzer - enabling business and enterprise applications to handle sentences and text

Get short facts from long text. Leaders read 20,000 lines of text in an 8-hour day. Or may soon have to. Everybody needs a mechanical secretary.

What is a summary, to a machine ? Declarative sentences yield machine processable "truths". Sentences represent what an inference engine would call "facts".

For machines, this collection of facts is the essence of a "crunching" process. Minimum noise for the inference engine, yet preserving the facts. When reviewing the below, please look at it in this light. Does this summary represent all the facts that a reasoning logic would need ? What model of "facts" does a downstream analyzer really need, and can the cruncher be fine-tuned to supply them without missing any ?

The staccato phrases (below) illustrate a dumb machine trying to get a grasp of English. The summary may not be what you as a human would expect, or worse, especially in the "terse" version of the summary. Be assured it will, at some point in the future, be mature enough to feed an inference engine with decent enough facts, and that extra "fullness" is doable by improved higher level rules, though it may increase the amount of "noise" a bit.

One thing that works in the favor of a mechanical secretary is this, that human speech and text has been shedding poetical structures, becoming simpler, terse and declarative. Two presidential speeches are included in this demo, separated by centuries, they seem to support this view. Please feel free to try out the below, and any other text. For questions : kinshuk_in @ yahoo dot. com

Note : The RESULTS shown are the human readable equivalent of Java/C# objects, and they have lots of additional information, like word meanings, group codes like colors and flavors etc., intended for further analytical/statistical treatment. This demo (created with no NLP APIs), stresses that with text, it is better to first maximize grammar based processing, and use statistics/math methods much later.

Sentences must be separated from each other by an ending period (. or ! or ?) and one space.

Skip the descriptive stuff and go directly to demo

Crunching sentences demo : two versions, a terse summary and a loose summary ( Click more samples : then Crunch)

Please enter a large text or paragraph. (upto 20 sentences, for now).
Once you have a list of prospective customers, there is still some work that needs to be done before you can create predictive models for customer acquisition. Unless you have data available from previous acquisition campaigns, you will need to send out a test campaign in order to collect data for analysis. Besides the customers you have selected for your prospect list, it is important to include some other customers in the campaign, so that the data is as rich as possible for future analysis. For example, assume that your prospect list (that you purchased from a list broker) was composed of men over age 30 who recently purchased a new car. If you were to market to these prospective customers and then analyze the results, any patterns found by data mining would be limited to sub-segments of the group of men over 30 who bought a new car. What about women or people under age 30? By not including these people in your test campaign, it will be difficult to expand future campaigns to include segments of the population that are not in your initial prospect list. The solution is to include a small random selection of customers whose demographics differ from the initial prospect list. This random selection should constitute only a small percentage of the overall marketing campaign, but it will provide valuable information for data mining. You will need to work with your data vendor in order to add a random sample to the prospect list.
(Please scroll down for the RESULTS)

This is a terse collection of facts.

A wider collection, somewhat differently collected.

Once have list# you have prospective# you have list# you have of# have list prospective# have list of# have list customers# list of customers# 
be done you predictive# you create predictive# you create for# you create models# create models for#

you have data# you have available# you have from# have data available# have data from# have data acquisition campaigns you# you need send to# send test campaign in# send test campaign order# test campaign in order# order collect data# order collect for# collect data analysis# collect data for#

customers you have selected# customers you have for# you have selected# you have for# prospect list it is to# prospect list it is important# include customers in# include customers campaign# 
data is rich#

example assume prospect list# 
you purchased from# you purchased list broker# purchased list broker broker# 
was men over# was men age# 
recently purchased car#

you were market# you were to# were market prospective# were market to# were market customers# customers analyze results# 
patterns found data mining# patterns found by# found data mining mining# found data mining be# data mining be to# data mining be limited# data mining be sub-segments# be sub-segments group# be sub-segments of# group of men#

solution is include to# solution to include# selection of customers# demographics differ from# demographics differ initial#

selection constitute small# selection constitute percentage# selection constitute only# selection constitute of# constitute only percentage# constitute percentage overall# constitute percentage of# constitute percentage marketing campaign# 
it provide valuable# it provide for# it provide information# provide information for# provide information data mining#

work data vendor in# work data vendor order# data vendor in order# order add sample# order add random# order add to# add sample prospect list# add sample to#

More view/try pages here.

Generic use cases

Back to home/basic analyzer

Comparing sentences, several modes

Find/search/sort/filter

Crunching a big text

Wildcard usages in pure structure mode

Business use cases

Handling Notes section in annual reports

Crunching of a Presidential speech

Executive profiles

Project statuses