International Business Machines Corporation

Anirban Laha

Parag Jain

Karthik Sankaranarayanan

Abhijit Mishra

Vijay Ekambaram

Saravanan Krishnan

Disha Shrivastava

Shivkumar Kalyanaraman

Pranay Kumar Lohia

Priyanka Agrawal

Saneem Ahmed Chemmengath

Anush Sankaran

Methods, systems, and computer program products related to a cognitive assistant for co-generating creative content are provided herein. A computer-implemented method includes obtaining semantic-level inputs from at least one user, wherein the semantic-level inputs pertain to multiple aspects of a desired content narrative; generating textual content based at least in part on the semantic-level inputs, wherein said generating the textual content comprises applying one or more deep learning algorithms to the semantic-level inputs; generating image content based at least in part on the generated textual content; creating the desired content narrative by integrating (i) the generated textual content and (ii) the generated image content; and outputting the desired content narrative to the at least one user.

Cognitive assistant for co-generating creative content

Text suggestions are generated. A document is received, and a portion score for at least one portion of the document is generated. A global assessment score for at least two portions of the document is also generated. A variation between the portion score and the global assessment score is calculated. It is determined that the variation is above a threshold variation, and at least one text change suggestion is generated.

Real-time assessment of text consistency

One embodiment provides a method, including: receiving, from a user, input for generating an article, wherein the input comprises (i) an indication of topic-specific requirements for the article that are dependent upon a topic of the article and (ii) an indication of non-topic-specific requirements for the article that are independent of the topic of the article; creating at least one query from the input; retrieving, from secondary sources by performing a search utilizing the query, structured information contextually relevant to the topic; and from the structured information, generating the article, wherein the article comprises a coherent and grammatically fluid structured article generated in view of the topic-specific requirements and the non-topic-specific requirements.

Structured article generation

Techniques for script modification are provided including receiving a script and parsing the script to identify at least one attribute of the script. The identified at least one attribute is presented to a user in a graphical user interface via a display device and an adjustment of at least one element in the graphical user interface that corresponds to the at least one attribute is received from the user via an input device. Modification data corresponding to the at least one attribute are received from a data repository and at least one attribute of the script is modified based on the received adjustment and the obtained modification data corresponding to the at least one attribute. A modified script is generated based on the modified at least one attribute.

Script modification

Techniques for the generation of variable natural language descriptions from structured data are disclosed including receiving input data and generating a first plurality of tuples based on the received input data. A first plurality of sentences and a corresponding second plurality of tuples are obtained from a data repository based on the first plurality of tuples. A second plurality of sentences is generated based on the second plurality of tuples, the first plurality of sentences, and the first plurality of tuples. A sentence is selected from the first plurality of sentences and the second plurality of sentences for each of the first plurality of tuples. At least one paragraph variation is generated where each paragraph variation is generated based on two or more of the selected sentences. The at least one paragraph variation is presented as a natural language description of the input data.

Generation of variable natural language descriptions from structured data

One embodiment provides a method, including: capturing at least one image of an object that is of interest to a user; identifying and capturing an environmental context of the object, wherein the environmental context (i) identifies a plurality of features of the environment surrounding the object, and (ii) comprises context captured from different modalities; storing the at least one image and the environmental context of the object, wherein the storing comprises indexing the object within the remote storage location using the identified features of the environment; receiving a request for the at least one image of the object; accessing the remote storage location and retrieving the at least one image of the object, wherein the retrieving comprises (i) searching for the at least one of the plurality of features and (ii) retrieving the at least one image of an object; and displaying the at least one image.

Object storage and retrieval based upon context

Aspects of the present disclosure relate to techniques for presenting content on a plurality of devices. The techniques including determining a first configuration for displaying first content on a plurality of devices, where the first configuration is based on a collective viewing size, an aspect ratio, a resolution shift, an internal border area, and a tactile quality gradient. The techniques including displaying, on a first device of the plurality of devices, a first device identifier, an orientation indicator, and an adjacent device identifier.

Growing community of inventors

Chinsurah, India

Anirban Laha