Amazon Technologies, Inc.

Janna Hamaker

Tom Killalea

Eugene Kalenkovich

Adam J Iser

Abhishek Patnia

Joshua M Goodspeed

Alla Taborisskaya

Peter Thomas Killalea

Christopher F Weight

Daniel Benjamin Rausch

Bruno A Posokhow

Preetha Chatterjee

Michel Leonard Goldstein

Sravan Babu Bodapati

Walter Manching Tseng

Andrew Douglas Birkett

Thomas F Dimson

Jeffrey L Belle

Sriraghavendra Ramaswamy

Gururaj Narayanan

Ankur Jain

Zaur Kambarov

Alexander William Robb Nelson

John Hambacher

Ravi Shankar Thangavel

Gregory Gridin

Vaibhav Shankar

Techniques for use with electronic book readers include coordinating or translating position information between different versions of an electronic book. Positions within different versions can be translated for various purposes, such as transferring annotations between versions or synchronizing positions within different versions.

Book version mapping

In some implementations, a device displays a user interface that provides supplemental information in connection with a digital work. For example, the supplemental information may include a listing of objects identified in the digital work. Further, a visual representation may be displayed with each listed object. The visual representation for each listed object may provide a representation of at least one location of at least one occurrence of the object in the digital work. The objects may be displayed according to a supplemental information view, a page view, a chapter view, a book view, a series view, a library view, or the like. Additionally, one or more object buttons may be displayed concurrently with the listing of objects. The object buttons may correspond to the types of objects displayed, and may be selected to limit the displayed objects to a particular type.

Providing supplemental information for a digital work in a user interface

Highlights from a community of users highlighting portions of an electronic digital content are analyzed and popular highlights determined. The popular highlights are then distributed to the users.

Selection of popular portions of content

In some implementations, a device displays supplemental information in connection with a digital work. The supplemental information may include a visual representation that represents one or more occurrences of an object in the digital work. The visual representation may include an area representative of an expanse of the digital work. At least one marking is located in the area in correlation to a location of an occurrence of the object in the digital work. In some examples, the visual representation may include a plurality of markings representing multiple occurrences of the object in the digital work, with a first or leftmost marking positioned in the area in proportion to a first occurrence of the object in the digital work. A second or rightmost marking may be positioned in the area in proportion to a final occurrence of the object in the digital work.

Visual representation of supplemental information for a digital work

Techniques are described for identifying book title sets. The techniques may include a first-pass comparison with other books to identify other candidate title sets. A second-pass comparison may then be performed with respect to the candidate title sets. The first-pass comparison may be based on book metadata such as titles and authorship. The second-pass comparison may include a more comprehensive content comparison, such as comparing the body text of the books.

Identifying book title sets

A machine learning engine may correlate contextual information associated with a misspelling in a publication with a likelihood that the misspelling is intentional in nature. Training data may be generated by analyzing one or more past publication to identify misspellings and labeling the misspellings as intentional. A contextual indicators application may analyze the context in which intentional misspellings have been previously included within publication to identify indicators of future misspellings being intentional. A machine learning engine may use the training data and indicators to generate an intentional linguistic deviation (ILD) prediction model to determine whether a new misspelling is an intentional misspelling. The machine learning engine may also determine weights for individual indicators that may calibrate the influence of the respective individual indicators. The ILD prediction model may be deployed to analyze a new publication to identify a likelihood of the new misspelling being intentional.

Distinguishing intentional linguistic deviations from unintentional linguistic deviations

In some examples, an electronic device may present a portion of a content item in a first language contemporaneously with a corresponding portion in a second language. Thus, a user may view the portion of content in the first language and the same portion of content in the second language. Further, the electronic device may dynamically adjust an area allotted to displaying each language version, such as in the case that a portion of content in one language takes up more space than a matching portion of content in the other language. In some examples, metadata for multiple language versions of a content item may include mapping information for correlating a portion of the first language version of the content item with a matching or corresponding portion of the second language version of the content item based, at least in part, on location information.

Presenting content in multiple languages

In some implementations, text is extracted from a digital work and proper nouns are identified in the text to generate a list of names. The list of names may be sorted so that names containing more information are positioned toward the beginning of the list. The list may be traversed to cluster names and alternate names into name sets that correspond to particular entities in the digital work. Non-unique names that appear in more than one name set may be disambiguated based on proximity to unique names in the same name sets to determine which occurrences of the non-unique names belong with which name sets. Furthermore, a representative name may be selected from among multiple names in a name set for use in representing an entity or object corresponding to the name set. In some examples, the representative name may be selected based on a fullness of the name.

Identifying entities in a digital work

In some implementations, text is extracted from a digital work and a plurality of noun phrases are identified. The noun phrases are checked against a network accessible resource, such as an online encyclopedia, that includes a plurality of interlinked article entries. The noun phrases that have corresponding entries in the network accessible resource are included in a set of candidate topics. The candidate topics are ranked based, at least in part, on the links to and from each of the entries corresponding to the candidate topics. Candidate topics below a ranking threshold are removed from the set of candidate topics. Further, term frequency information for each candidate topic in relation to the digital work is compared against term frequency information for the candidate topic in a large corpus of textual works to remove candidate topics within a frequency difference threshold.

Identifying topics in a digital work

Digital content such as eBook may have several sections such as front matter, body matter, back matter, and so forth. To aid in the use of the content, it is worthwhile to find an end-of-body matter or other section breaks. As described herein, these sections may be determined by looking for keywords, specific formatting, manual intervention, last position read, and so forth. Once determined, tags may be generated which designate boundaries of these sections. These tags may then be used during consumption of the content.

Finding an end-of-body within content

Character identity recognition is applied to identify text strings corresponding to character identities in a written work. The textual strings are grouped according to character identity and, from each group, a primary name is selected. A significance value may be calculated for each of the character identities. The character identities including the primary names are presented in a catalog based on the calculated significance values.

Recognition of characters and their significance within written works

In some implementations, a digital work may include a plurality of objects that may be selected to view supplemental information. A supplemental information user interface may include a listing of objects from the digital work. For instance, the listing may include a selected object appearing at an identified location in the digital work. The user interface may further present a visual representation displayed with each object that provides an indication of at least one location of at least one occurrence of the corresponding object in the digital work. In some examples, a user may navigate between a supplemental information view user interface, a page view user interface, a chapter view user interface, a book view user interface, a series view user interface, and/or a library view user interface to view occurrences of a particular object in the digital work or other digital works.

Navigating supplemental information for a digital work

In some implementations, one or more words from a digital work are used to generate a game to be displayed on an electronic device. For example, the electronic device may include a library of one or more digital works. A word or knowledge game may be dynamically generated based on objects, such as characters, topics, places, organizations, things, etc., identified in at least one digital work in the library. As one example, a crossword puzzle may be created to include words and clues based at least in part on the objects identified in at least one digital work and supplemental information associated with the objects. The clues for the crossword puzzle may be generated automatically based, at least in part, on a desired level of difficulty. Further, in some cases, the game may be generated from words drawn from multiple digital works in the library.

Generating a game related to a digital work

A method is provided for presenting a written work. A character identity is recognized within a written work. Presentation information for the written work, such as a graphical scheme or an electronic voice, is determined based on the character identity. The presentation information is provided to a user computing device. The user computing device renders the written work or a portion thereof using the presentation information.

Growing community of inventors

Issaquah, WA, United States of America

Janna Hamaker