Enhancing reading accuracy, efficiency and retention

• US 10,515,138 B2
• Filed: 04/17/2015
• Issued: 12/24/2019
• Est. Priority Date: 04/25/2014
• Status: Active Grant

• Current Assignee: Mayo Foundation For Medical Education And Research (Mayo Clinic)
• Original Assignee: Mayo Foundation For Medical Education And Research (Mayo Clinic)
• Inventors: Walker, Randall C.
• Primary Examiner(s): Cortes, Howard
• Application Number:
  US15/306,190
• Publication Number:
  US 20170046311A1
• Time in Patent Office: 1,712 Days
• Field of Search: None
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/117 Tagging; Marking up details of markup languages G06F40/143; Designating a block; Setting of attributes style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records

Abstract

This document provides systems and methods for altering text presentation to increase reading accuracy, efficiency, and retention. This can include identification text specific attributes from machine readable text (through parsing of the text), varying the text presentation in accordance with the attributes, and creating an enhanced visual product for enhancing the reading experience. For example, a computer system can extract attributes such as parts of speech from an input sentence and display that sentence in cascading text segments down and across a display screen. The system can further use domain-specific dictionaries derived from domain-specific texts to identify domain-specific compound noun phrases and verb phrases that require specific linguistic tagging to be usable in other linguistic analysis steps.

Claims

1. A computer-implemented method for extracting, from a machine-readable natural language text, nested structures of sentences with embedded clauses, the method comprising:

accessing, by a computing system, computer readable memory storing one or more files containing machine-readable natural language text;

enriching, by the computing system, the machine-readable natural language text by adding word-specific attribute tags to the text, wherein each word-specific attribute tag comprises a computer readable code associated with a particular location within the machine-readable natural language text;

accessing, by the computing system, one or more databases containing domain-specific multi-word terms developed through a process of statistical frequency analysis of a plurality of texts in the domain;

identifying, by the computing system and within the one or more databases, a plurality of domain-specific multi-word binding tags that are applicable to the machine-readable natural language text;

adding the identified of domain-specific multi-word binding tags to the machine-readable natural language text;

adding, to the machine readable natural language text, clustering tags that identify groups of individual words as discrete multi-word clusters,

adding, to the machine readable natural language text, phrase-bracketing tags, using recursive, context-specific rules that assemble words and multi-word clusters into phrases, based on the attribute tags and the multi-word binding tags;

adding, to the machine readable natural language text, clause-encapsulating tags, using context-specific rules that examine the phrase-bracketing tags for specific patterns of phrase-segments that meet clause pattern criteria;

adding, to the machine readable natural language text, envelope tags that denote open and closed states of phrases that contain other phrases and clauses, using context-specific rules that examine attributes of phrases, including open, closed and inter-phrase touching states of adjacent phrases, to allow or disallow absorption of phrases by other phrases and absorption of closed clauses by phrases, and to determine the closure of phrases when criteria for sets of inter-phrase attributes and sentence-concluding punctuation boundaries are met;

storing, by the computing system and on one or more computer readable memory devices, the machine-readable natural language text along with the word-specific attribute tags, the domain-specific multi-word binding tags, the clustering tags, the phrase-bracketing tags, the clause-encapsulating tags, and the envelope tags such that each of the word-specific attribute tags, the domain-specific multi-word binding tags, the clustering tags, the phrase-bracketing tags, the clause-encapsulating tags, and the envelope tags is associated with a particular portion of the machine-readable natural language text within the one or more computer readable memory devices; and

displaying, on a display screen of the computing system, the machine readable natural language text with indications of at least some of the word-specific attribute tags, domain-specific multi-word binding tags, clustering tags, phrase-bracketing tags, clause-encapsulating tags, or envelope tags.

2. The method of claim 1, wherein the domain-specific multi-word terms have removable binding tags for provisional part-of-speech use of the multi-word term, which are removed in response to an inter-cycle state comparison that indicates that no net state change between cycles without full-sentence clause structure extraction has occurred, with repeat interrogation of the machine readable text with the individual words in the multi-word term being re-tagged as separate words, each separate word having its own set of part-of-speech attributes.

3. The method of claim 1, wherein at least some of the word-specific attribute tags, domain-specific multi-word binding tags, clustering tags, phrase-bracketing tags, clause-encapsulating tags, or envelope tags are used to assign multi-dimensional display properties of the presented text to improve reading comprehension.

4. The method of claim 1, the method further comprising:

identifying domain-specific compound noun phrases and verb phrases based on domain-specific dictionaries derived from domain-specific texts.

5. The method of claim 4, wherein the domain-specific texts include medical texts such as electronic medical records, medical dictionaries, medical text books, medical trade publications, legal texts, scientific texts, accounting texts, and engineering texts.

6. The method of claim 1, wherein the context-specific rules are based, at least in part, on an attribute of whether a phrase-envelope is open, closed, or closed-with-inter-phrase-touching.

7. The method of claim 1, wherein the context-specific rules are based, at least in part, on the person and case of a noun phrase.

8. The method of claim 1, wherein the context-specific rules are based, at least in part, on the person, case, tense, and transitivity of a verb phrase.

9. The method of claim 1, wherein the context-specific rules are based, at least in part, on attributes for noun-less verb phrases and pairs of verb phrases in compound verb phrases.

10. The method of claim 1, wherein the context-specific rules are based, at least in part, on the presence of coordinating conjunctions at the head of verb phrases.

11. The method of claim 1, wherein the context-specific rules are based, at least in part, on the presence, at the end of each of a plurality of phrases, of a sentence-concluding punctuation mark.

12. The method of claim 1, wherein the context-specific rules specify that a phrase is not joined with an immediately distal phrase until after the distal phrase is closed.

13. The method of claim 1, wherein the context-specific rules specify that an encounter between a noun phrase and an immediately distal verb phrase that have incompatible case agreement properties results in the noun-phrase becoming closed without a touched-verb-mate marker.

14. The method of claim 1, wherein the context-specific rules specify that verb-phrases that are not potential noun-less verb phrases are not gathered into other phrases but only join, with a case-agreement compatible closed noun-phrase, to form a clause.

15. The method of claim 1, wherein the context-specific rules specify that if the gathering process for a proximal verb phrase envelope encounters, while assessing whether to gather the next phrase, the proximal boundary of another verb phrase that is not a potential noun-less verb phrase, then the envelope of the proximal verb phrase closes.