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

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

Notes to Consolidated Financial Statements Financial statements often have useful data in a text section, that ought to be read. Or machine scanned.

This demo illustrates picking data from formal documents. Highlighting specific sentences for you to read, or to extract data by further machine processes.

Scenario : A large amount of information exists in the "Notes to Consolidated Financial Statements" section of 10-K Annual Reports filed by companies. The high resolution document extractor at text2data.net will extract most tables and structured data. For deeper digging you can use this sentence analyzer.

There is an advantage in formal documents, because inventive phrasing is curtailed. And even with variations of expression, a combination of a structural extraction and a grammatical extraction can be quite effective.

Try out the below , and sometimes, explore the "Compare less tightly" and other options. 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

Notes Section in Financial docs : finding data ( Click more samples : then Find/Collect)

Enter DESIRED benchmark sentence(s), or click one of the sample buttons above.. Max. 5 sentences.

Enter TARGETed sentence(s) or a paragraph. [See a Notes extract below]. This is what you want compared against the benchmark(s). Max. 20 sentences.

On the acquisition date of TD Waterhouse, the Company entered into equity swap agreements with an affiliate of TD to offset changes in TD's common stock price. During December 2007, most of the restricted stock units vested and were settled and all the equity swap agreements expired. In May 2008, the remaining restricted share units vested and were settled. The Company incurred $0.2 million and $0.3 million of interest expense to the TD affiliate to finance the swap agreements during fiscal 2007 and fiscal 2006, respectively. There were 181,059 restricted share units outstanding as of September 30, 2007 with an approximate value of $13.9 million. The Company recorded a loss on fair value adjustments to the equity swap agreements of $0.8 million in fiscal 2008 and gains of $3.2 million and $1.7 million for fiscal 2007 and fiscal 2006, respectively, which are included in fair value adjustments of compensation-related derivative instruments on the Consolidated Statements of Income. Because the swap agreements were not designated for hedge accounting, the fair value adjustments are not recorded in the same category of the Consolidated Statements of Income as the corresponding compensation expense, which is recorded in the employee compensation and benefits category.

(Please scroll down for the RESULTS)

Summary results : Searched and sorted among 7 target sentences. Highest co-relation 14.6 percent. Appears low. Target may not have anough similar sentences. Try less tight comparison mode.

Best matching content + structure after a find/collect operation

All sorted matches (Best finds on top, degrades towards the end, and very bad matches ignored)

Options for comparing, or finding and selecting (i.e. change default settings)
Compare less tightly	Use frequently, if find results are not OK
More structural than content	and
Tree depth (deeper into structure)