Receive a question via a graphical user interface (GUI), obtain a passage of text potentially relevant to the question, and receive, via the GUI, a selection of a number of question-answering models to be ensembled. Produce a plurality of answers to the question by running a plurality of question-answering models, consistent with the selection of the number of question-answering models to be ensembled, on the passage of text. Produce an ensembled answer by ensembling the plurality of answers according to their respective confidence scores. Display, via the GUI, the ensembled answer in context of the passage of text, with the ensembled answer visually marked in the passage of text. Optionally, repeat these steps for a second passage of text.

A computing system accesses an image-based document and a text document having text extracted from the image-based document and provides a user interface displaying at least a portion of the image-based document. In response to selection of a text portion of the image-based document, the system determines an occurrence of the text portion within at least a portion of the image-based document and then applies a search model on the text document to identify the same occurrence of the text portion. Once matched, alignment data indicating a relationship between a selected tag and both the text portion of the image-based document and the text portion of the text document is stored.

A computing system accesses an image-based document and a text document having text extracted from the image-based document and provides a user interface displaying at least a portion of the image-based document. In response to selection of a text portion of the image-based document, the system determines an occurrence of the text portion within at least a portion of the image-based document and then applies a search model on the text document to identify the same occurrence of the text portion. Once matched, alignment data indicating a relationship between a selected tag and both the text portion of the image-based document and the text portion of the text document is stored.

A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.

A method for estimating text heights of text line images includes estimating a text height with a sequence recognizer. The method further includes normalizing a vertical dimension and/or position of text within a text line image based on the text height. The method may also further include calculating a feature of the text line image. In some examples, the sequence recognizer estimates the text height with a machine learning model.

Embodiments are disclosed for text-aware application of a color gradient to text characters. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a set of text characters in a first layout, determining a first text path of the set of text characters in the first layout, mapping the set of text characters from the first layout to a second layout, wherein the set of text characters in the second text path are aligned along a coordinate axis, applying a linear color gradient across the mapped set of text characters in the second layout, reverse mapping the set of text characters with the applied linear color gradient from the second layout to the first layout, and outputting the set of text characters in the first layout with the applied linear color gradient from the second layout based on the reverse mapping.

Embodiments are disclosed for text-aware application of a color gradient to text characters. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input including a set of text characters in a first layout, determining a first text path of the set of text characters in the first layout, mapping the set of text characters from the first layout to a second layout, wherein the set of text characters in the second text path are aligned along a coordinate axis, applying a linear color gradient across the mapped set of text characters in the second layout, reverse mapping the set of text characters with the applied linear color gradient from the second layout to the first layout, and outputting the set of text characters in the first layout with the applied linear color gradient from the second layout based on the reverse mapping.

Systems and methods for document processing that can process and understand the layout, text size, text style, and multimedia of a document can generate more accurate and informed document representations. The layout of a document paired with text size and style can indicate what portions of a document are possibly more important, and the understanding of that importance can help with understanding of the document. Systems and methods utilizing a hierarchical framework that processes the block-level and the document-level of a document can capitalize on these indicators to generate a better document representation.

Systems and methods for document processing that can process and understand the layout, text size, text style, and multimedia of a document can generate more accurate and informed document representations. The layout of a document paired with text size and style can indicate what portions of a document are possibly more important, and the understanding of that importance can help with understanding of the document. Systems and methods utilizing a hierarchical framework that processes the block-level and the document-level of a document can capitalize on these indicators to generate a better document representation.

Provided is a method for automatically generating a banner image for a promotion, performed by a computing device comprising a processor and a memory. The method comprises the steps of: acquiring information about any concept classification to which a product or service to be promoted corresponds from among a plurality of predefined concept classifications; determining a setting value for a foundation that is a minimum unit constituting the design of a banner image, on the basis of the concept classification to which the product or service to be promoted belongs; determining at least one component included in the banner image, on the basis of the setting value for the foundation; and generating at least one banner template including component arrangement information that is information about the location and size of which of the at least one component.