Jpmorgan Chase Bank, N.a.

Refinitiv US Organization LLC

Financial & Risk Organisation Limited

Natraj Raman

Sameena Shah

Armineh Nourbakhsh

Manuela Veloso

Salwa Husam Alamir

Jochen Lothar Leidner

John F Duprey

Tim Nugent

Daniel Borrajo

Zhen Zeng

Naftali Y Cohen

Simerjot Kaur

Vali Tawosi

Mathieu Sibue

Fabio Petroni

Lucas Carstens

Alec Louis Clemente Candidato

Yulong Pei

Petr Babkin

Dongsheng Wang

Zarko Panic

Zhiqiang Ma

John Duprey

Jochen Leidner

Various methods and processes, apparatuses/systems, and media for performing spatial-aware reading for visual documents are disclosed. A processor implements a language model; modifies existing parameters and architecture of the language model to incorporate new parameters in its architecture by integrating a disentangled spatial attention process to the language model; pretrains the modified model by performing an autoregressive block infilling process on a plurality of document pages thereby training the new parameters and further adjusting the existing parameters; instruction-tunes the pretrained model on data derived from a plurality of visually rich document understanding datasets to teach the pretrained model to follow document-oriented instructions or answer questions about documents by leveraging their content and their spatial layout and outputting a trained model; and performs spatial-aware reading for visual documents by utilizing the trained model.

System and method for layout-aware generative pretraining for visually rich document understanding

A method and system for providing a video query are disclosed. The method includes acquiring context information, training a first machine learning (ML) model using historical data of the software life cycle tool, and removing, by the first ML model, noise from the context information for generating a query including at least one keyword. Once the query is generated, executing, by a second ML model, the query to retrieve at least one video segment from a learning repository. Scoring and ranking is then performed on the at least one video segment. The ranked video segment is then transmitted, to the user interface of the software life cycle tool, and displayed in an ad-hoc manner.

System and method for providing video query

A method and a system for providing a visual representation of textual information is provided. The method includes: receiving a corpus that includes documents containing textual information; analyzing the textual information by applying a text analytics algorithm thereto; generating a visual representation of the textual information based on a result of the analysis; and displaying the visual representation on a graphical user interface (GUI) that includes mechanisms for facilitating user interaction therewith. The visual representation be any one of a hypergraph that encodes a distributional similarity between words included in the textual information, a multi-level radial layout that captures distinguishing terms included in the textual information, a clutter-free parallel coordinate plot of topic relations with respect to the textual information, a nested topology of hierarchical relations with respect to the textual information, and a tessellated plane that highlights boundary points with respect to the textual information.

Method and system for providing visual text analytics

A method and system for detecting, segmenting, and extracting salient regions in documents by using attention tracking sensors is provided. The method includes: receiving an image that corresponds to a document; receiving, from a sensor, a sequence of measurements that correspond to a human reading of the document; determining, based on the sequence of measurements, at least one region of the document as being a salient document region; demarcating the salient document region in an electronically displayable manner; and outputting a file that includes a displayable version of the document with the demarcated document region. The salient document region may include a title, a section header, and/or a table. The sensor may be an eye-tracking sensor that detects a sequence of eye-gaze positions on the document as a function of time.

Method of detecting, segmenting and extracting salient regions in documents using attention tracking sensors

A solution to identify the layout elements in a document is provided. The documents are formulated in an integrated visual space, where they are treated uniformly as a rasterized image. The transformation to image space facilitates exploitation of a spectrum of stylistic cues, such as spacing between the lines and paragraphs. Effective recognition of layout elements is provided by applying a synthetic generator model that creates artificial documents with the required labels and bounding boxes. The generator model is based on a Bayesian Network, offers full flexibility in controlling the document types and labels, and can introduce artificial defects to synthesize low-quality documents. An artificial intelligence model for detecting layouts is trained based on these synthetic documents and the resultant model is used to identify the layout elements in real-world documents. The resulting layout elements, when augmented with the text content, greatly aids in effective information retrieval.

Method and system for generating synthetic documents for layout recognition and information retrieval

A method of providing cross-media event linking may include: receiving, at a first input of an event coreferencing system, a stream of social media postings, and at a second input, a stream of news articles; generating, by the event coreferencing system, a first set of event representations representing events referenced by the social media postings, and a second set of event representations representing events referenced by the news articles; determining, by the event coreferencing system, that at least one of the social media postings references a same event referenced by at least one of the news articles, the determining including determining at least one similarity using data of at least one of the first set of event representations corresponding to the at least one of the social media postings and data of at least one of the second set of event representations corresponding to the at least one of the news articles; and transmitting, by an output of the event resolution system to the user system, an alert including at least one coreferenced event representation representing the event referenced by the at least one of the social media postings and the at least one of the news articles.

Systems and methods for cross-media event detection and coreferencing

Growing community of inventors

London, United Kingdom

Natraj Raman