Disambiguation of term meaning

• US 8,972,393 B1
• Filed: 07/19/2012
• Issued: 03/03/2015
• Est. Priority Date: 06/30/2010
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Killalea, Tom, Hamaker, Janna S.
• Primary Examiner(s): LE, DEBBIE M
• Application Number:
  US13/553,172
• Time in Patent Office: 957 Days
• Field of Search: 707/728, 707/726, 707/730, 707/749
• US Class Current: 707/728
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A meaning of a term is determined using the contents of a corpus of books through use of metadata about the books within the corpus, terms in the same work which provide context, and so forth. Users may query to determine the meaning of a term. Users may also build vocabulary skills by testing as well. A changing meaning of a term over time may be determined and utilized as well. Searches are facilitated by the enhanced ability to determine meaning of the terms, particularly in context. Feedback from the searches may also be used to refine future searches.

Claims

1. A computer-implemented method, comprising:

under control of one or more computers configured with specific executable instructions,

accepting a query for a term in a target passage within an electronic book;

accessing the electronic book;

associating the term with the electronic book;

accessing possible meanings of the term; and

determining a top ranking meaning of the term from the possible meanings, the top ranking meaning based at least in part upon metadata associated with contents of the associated electronic book and metadata associated with the term.

2. The computer-implemented method of claim 1, further comprising determining one or more related portions of one or more other electronic books, the one or more related portions using the term consistent with the top ranking meaning in the target passage within the electronic book.

3. The computer-implemented method of claim 1, further comprising presenting the determined term meaning.

4. The computer-implemented method of claim 1, the determining the top ranking meaning of the term further comprising:

ranking the possible meanings according to correspondence of the metadata associated with the term and the metadata associated with the contents of the associated electronic book; and

selecting the meaning of the term with a highest ranking.

5. The computer-implemented method of claim 1, further comprising presenting a confounder passage in which the term is used with a meaning other than the top ranking meaning of the target passage, and presenting a question to a user, the question being associated with.

6. The computer-implemented method of claim 1, further comprising presenting a report displaying variation of meaning of the term within a pre-determined set of parameters.

7. The computer-implemented method of claim 6, wherein the pre-determined set of parameters comprise:

a range of dates;

a user demographic;

genre;

or

a combination thereof.

8. The computer-implemented method of claim 2, further comprising presenting the one or more related portions.

9. A computer-implemented method, comprising:

under control of one or more computers configured with specific executable instructions,

receiving a query for a term from a user accessing a content item on an electronic book reader device;

accessing metadata associated with the user, the term, and the content item;

ranking the possible meanings according to correspondence of metadata associated with the term and metadata associated with the content item;

determining a top ranking meaning of the term from possible meanings based at least in part upon the metadata associated with the term and the metadata associated with the content item; and

selecting the meaning of the term with a top ranking.

10. The computer-implemented method of claim 9, further comprising presenting one or more sample passages containing the top ranking meaning of the term from one or more content items in a corpus.

11. The computer-implemented method of claim 10, wherein the corpus of content items comprises electronic books.

12. The computer-implemented method of claim 9, further comprising presenting one or more sample passages containing non-top ranking meanings of the term from one or more content items in a corpus.

13. The computer-implemented method of claim 9, further comprising receiving a selection from the user to confine the query to a specified metadata attributed.

14. The computer-implemented method of claim 9, wherein the query is received from a dedicated electronic book reader.

15. A computer-implemented method, comprising:

under control of one or more computers configured with specific executable instructions,

determining a meaning of a term within the context of a passage in a target content item;

presenting the term and an associated definition appropriate to the context;

receiving an input containing the term as used in an incorrect fashion as a confounder;

storing the confounder;

causing a presentation of the confounder to a user as part of a vocabulary question; and

ranking the confounder based at least in part on a frequency with which the confounder is selected when the confounder is part of the vocabulary question.

16. A computer-implemented method, comprising:

receiving, from an electronic device, a term in a target passage for which a reader has initiated a query while reading an electronic book on the electronic device;

determining a top ranked meaning of the term based at least in part upon the context of the target passage and metadata associated with the electronic book;

generating a vocabulary question for the term with the meaning as used in the target passage; and

serving the vocabulary question for presentation to the reader.

17. The computer-implemented method of claim 16, wherein the electronic device comprises an electronic book reader device.

18. The computer-implemented method of claim 16, wherein generating a vocabulary question comprises determining one or more excerpts of another electronic book using a same term with one or more non-top ranked meanings, and crafting a vocabulary question that includes at least a portion of the excerpt.

19. The computer-implemented method of claim 16, wherein generating a vocabulary question comprises enabling the reader to create the vocabulary question.

20. The computer-implemented method of claim 16, wherein serving the vocabulary question comprises serving the vocabulary question to the electronic device for display on the electronic device.

21. The computer-implemented method of claim 16, further comprising prompting the reader for feedback as to quality of the vocabulary question.

22. The computer-implemented method of claim 18, further comprising creating an audible version of the vocabulary question.

23. A device, comprising:

a processor;

a vocabulary service module stored in a memory coupled to the processor, the vocabulary service module configured to;

receive a query from a querying entity about a term in a target passage of a content item within an electronic book;

access metadata associated with the querying entity, the term, and the content item containing the target passage;

determine a most likely meaning of the term as attributed to the querying entity based, at least in part, upon analysis of the metadata and a rank of possible meanings by a ranking module;

search a corpus based at least in part upon the most likely meaning, and

generate a vocabulary question based at least in part upon the determined most likely meaning.

24. The electronic device of claim 23, wherein the ranking module is configured to:

access possible meanings of the term;

rank the possible meanings according to correspondence of the metadata; and

select the possible meaning of the term with a highest rank.

25. The electronic device of claim 23, wherein the corpus comprises a plurality of content items.

26. The electronic device of claim 23, the vocabulary service module further configured to present the determined most likely meaning.

27. The electronic device of claim 23, the vocabulary service module further configured to generate a vocabulary question based at least in part upon the determined most likely meaning.