Detecting overnegation in text

• US 10,275,517 B2
• Filed: 05/31/2016
• Issued: 04/30/2019
• Est. Priority Date: 05/29/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Barsukova, Agnia, Curran, David M., Kelly, Amelia C.
• Primary Examiner(s): Abebe, Daniel
• Application Number:
  US15/168,678
• Publication Number:
  US 20160350407A1
• Time in Patent Office: 1,064 Days
• Field of Search: 704 9
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Detecting overnegation in text is provided. A plurality of word lists are compiled. An input text is received. One or more combined weightings are determined, wherein each combined weighting is based, at least in part, on a portion of the input text and the plurality of word lists. A total overnegation score of the input text is generated based, at least in part, on a statistical aggregation of the one or more combined weightings. In response to determining that the total overnegation score exceeds a pre-determined threshold, it is determined that the input text contains a logical error. In response to the total overnegation score exceeding a pre-determined level, one or more actions are executed.

Claims

1. A method of detecting overnegation in text, the method comprising:

compiling, by one or more processors, a plurality of word lists, wherein the plurality of word lists includes;

a first list including one or more negative verbs and adjectives, a second list including one or more measurement verbs, and a third list including one or more negation and mitigation words;

receiving, by one or more processors, an input text;

determining, by one or more processors, one or more combined weightings, wherein each combined weighting is based, at least in part, on a portion of the input text and the plurality of word lists;

generating, by one or more processors, a total overnegation score of the input text based, at least in part, on a statistical aggregation of the one or more combined weightings;

determining, by one or more processors, that the total overnegation score exceeds a pre-determined threshold and, in response, determining that the input text contains a logical error wherein the logical error is an overnegation; and

responsive to the total overnegation score exceeding one or more pre-determined levels, executing, by one or more processors, one or more actions.

2. The method of claim 1, wherein determining a first combined weighting is based, at least in part, on a number of occurrences of a first portion of the input text for each of the plurality of word lists and a weight corresponding to each of the plurality of word lists.

3. The method of claim 1, wherein the statistical aggregation includes a logistic regression classification technique.

4. The method of claim 1, wherein the statistical aggregation includes a Bayesian technique.

5. The method of claim 1, wherein one of the one or more actions comprises correction of the logical error.

6. The method of claim 1, wherein one of the one or more actions comprises flagging the logical error to a user.

7. The method of claim 1, further comprising:

determining, by one or more processors, that the total overnegation score exceeds a first pre-determined level and, in response, flagging the logical error to a user; and

determining, by one or more processors, that the total overnegation score exceeds a second pre-determined level and, in response, correcting the logical error.