Adobe, Inc.

Milan Aggarwal

Balaji Krishnamurthy

Mausoom Sarkar

Nikaash Puri

Pinkesh Badjatiya

Shripad Vilasrao Deshmukh

Sumit Bhatia

Arneh Jain

Surgan Jandial

Simra Shahid

Rachit Bansal

Abhinav Java

Sharat Chandra Racha

S Sejal Naidu

Jivat Neet Kaur

Mihir Naware

Shagun Sodhani

Hyman Chung

Matthew William Rozen

Hiresh Gupta

Puneet Mangla

Tanay Anand

Somesh Singh

Pranjal Prasoon

Ganesh Karbhari Palwe

Nikitha Srikanth

Sumegh Roychowdhury

Sumedh A Sontakke

Nisarg Shailesh Joshi

Seoyoung Park

Nithyakala Sainath

Silky Singh

Shashank Shailabh

Madhur Panwar

Aarushi Arora

In implementations of systems for digital content analysis, a computing device implements an analysis system to extract a first content component and a second content component from digital content to be analyzed based on content metrics. The analysis system generates first embeddings using a first machine learning model and second embedding using a second machine learning model. The first embeddings and the second embeddings are combined as concatenated embeddings. The analysis system generates an indication of a content metric for display in a user interface using a third machine learning model based on the concatenated embeddings.

Digital content analysis

A corrective noise system receives an electronic version of a fillable form generated by a segmentation network and receives a correction to a segmentation error in the electronic version of the fillable form. The corrective noise system is trained to generate noise that represents the correction and superimpose the noise on the fillable form. The corrective noise system is further trained to identify regions in a corpus of forms that are semantically similar to a region that was subject to the correction. The generated noise is propagated to the semantically similar regions in the corpus of forms and the noisy corpus of forms is provided as input to the segmentation network. The noise causes the segmentation network to accurately identify fillable regions in the corpus of forms and output a segmented version of the corpus of forms having improved fidelity without retraining or otherwise modifying the segmentation network.

Personalized form error correction propagation

Various embodiments classify one or more portions of an image based on deriving an 'intrinsic' modality. Such intrinsic modality acts as a substitute to a “text” modality in a multi-modal network. A text modality in image processing is typically a natural language text that describes one or more portions of an image. However, explicit natural language text may not be available across one or more domains for training a multi-modal network. Accordingly, various embodiments described herein generate an intrinsic modality, which is also a description of one or more portions of an image, except that such description is not an explicit natural language description, but rather a machine learning model representation. Some embodiments additionally leverage a visual modality obtained from a vision-only model or branch, which may learn domain characteristics that are not present in the multi-modal network. Some embodiments additionally fuse or integrate the intrinsic modality with the visual modality for better generalization.

Using intrinsic multimodal features of image for domain generalized

Methods and systems are provided for facilitating generation and utilization of a commonsense contextualizing machine learning (ML) model, in accordance with embodiments described herein. In embodiments, a commonsense contextual ML model is trained by fine-tuning a pre-trained language model using a set of training path-sentence pairs. Each training path-sentence pair includes a commonsense path, identified via a commonsense knowledge graph, and a natural language sentence identified as contextually related to the commonsense path. The trained commonsense contextualizing ML model can then be used to generate a commonsense inference path for a text input. Such a commonsense inference path can include a sequence of entities and relations that provide commonsense context to the text input. Thereafter, the commonsense inference path can be provided to a natural language processing system for use in performing a natural language processing task.

Generating commonsense context for text using knowledge graphs

A method of finding online relevant conversing posts, comprises receiving, by a web server serving an online forum, a query post from an inquirer using the online forum, computing a contextual similarity score between each conversing post of a set of conversing posts with a query post, wherein the contextual similarity score is computed between the body of each of conversing posts and of the query post, wherein N1 conversing posts with a highest contextual similarity score are selected; computing a fine grained similarity score between the subject of the query post and of each of the Nconversing posts, wherein N2 conversing posts with a highest fine grained similarity score are selected; and boosting the fine grained similarity score of the N2 conversing posts based on relevance metrics, wherein N3 highest ranked conversing posts are selected as a list of conversing posts most relevant to the query post.

Semantics-aware hybrid encoder for improved related conversations

Systems and methods for topic modeling are described. The systems and methods include encoding words of a document using an embedding matrix to obtain word embeddings for the document. The words of the document comprise a subset of words in a vocabulary, and the embedding matrix is trained as part of a topic attention network based on a plurality of topics. The systems and methods further include encoding a topic-word distribution matrix using the embedding matrix to obtain a topic embedding matrix. The topic-word distribution matrix represents relationships between the plurality of topics and the words of the vocabulary. The systems and methods further include computing a topic context matrix based on the topic embedding matrix and the word embeddings and identifying a topic for the document based on the topic context matrix.

System and methods for neural topic modeling using topic attention networks

Form structure similarity detection techniques are described. A content processing system, for instance, receives a query snippet that depicts a query form structure. The content processing system generates a query layout string that includes semantic indicators to represent the query form structure and generates candidate layout strings that represent form structures from a target document. The content processing system calculates similarity scores between the query layout string and the candidate layout strings. Based on the similarity scores, the content processing system generates a target snippet for display that depicts a form structure that is structurally similar to the query form structure. The content processing system is further operable to generate a training dataset that includes image pairs of snippets depicting form structures that are structurally similar. The content processing system utilizes the training dataset to train a machine learning model to perform form structure similarity matching.

Form structure similarity detection

The technology described herein receives a natural-language sequence of words comprising multiple entities. The technology then identifies a plurality of entities in the natural-language sequence. The technology generates a masked natural-language sequence by masking a first entity in the natural-language sequence. The technology retrieves, from a knowledge base, information related to a second entity in the plurality of entities. The technology then trains a natural-language model to respond to a query. The training uses a first representation of the masked natural-language sequence, a second representation of the information, and the first entity.

Language model with external knowledge base

In implementations of refining element associations for form structure extraction, a computing device implements a structure system to receive estimate data describing estimated associations of elements included in a form and a digital image depicting the form. An image patch is extracted from the digital image, and the image patch depicts a pair of elements of the elements included in the form. The structure system encodes an indication of whether the pair of elements have an association of the estimated associations. An indication is generated that the pair of elements have a particular association based at least partially on the encoded indication, bounding boxes of the pair of elements, and text depicted in the image patch.

Refining element associations for form structure extraction

An interactive search session is implemented using an artificial intelligence model. For example, when the artificial intelligence model receives a search query from a user, the model selects an action from a plurality of actions based on the search query. The selected action queries the user for more contextual cues about the search query (e.g., may enquire about use of the search results, may request to refine the search query, or otherwise engage the user in conversation to better understand the intent of the search). The interactive search session may be in the form, for example, of a chat session between the user and the system, and the chat session may be displayed along with the search results (e.g., in a separate section of display). The interactive search session may enable the system to better understand the user's search needs, and accordingly may help provide more focused search results.

Interactive search experience using machine learning

Systems and methods for video processing are described. Embodiments of the present disclosure generate a plurality of image feature vectors corresponding to a plurality of frames of a video; generate a plurality of low-level event representation vectors based on the plurality of image feature vectors, wherein a number of the low-level event representation vectors is less than a number of the image feature vectors; generate a plurality of high-level event representation vectors based on the plurality of low-level event representation vectors, wherein a number of the high-level event representation vectors is less than the number of the low-level event representation vectors; and identify a plurality of high-level events occurring in the video based on the plurality of high-level event representation vectors.

Self-supervised hierarchical event representation learning

Techniques described herein extract form structures from a static form to facilitate making that static form reflowable. A method described herein includes accessing low-level form elements extracted from a static form. The method includes determining, using a first set of prediction models, second-level form elements based on the low-level form elements. Each second-level form element includes a respective one or more low-level form elements. The method further includes determining, using a second set of prediction models, high-level form elements based on the second-level form elements and the low-level form elements. Each high-level form element includes a respective one or more second-level form elements or low-level form elements. The method further includes generating a reflowable form based on the static form by, for each high-level form element, linking together the respective one or more second-level form elements or low-level form elements.

Form structure extraction by predicting associations

Techniques are disclosed for providing an interactive search session. The interactive search session is implemented using an artificial intelligence model. For example, when the artificial intelligence model receives a search query from a user, the model selects an action from a plurality of actions based on the search query. The selected action queries the user for more contextual cues about the search query (e.g., may enquire about use of the search results, may request to refine the search query, or otherwise engage the user in conversation to better understand the intent of the search). The interactive search session may be in the form, for example, of a chat session between the user and the system, and the chat session may be displayed along with the search results (e.g., in a separate section of display). The interactive search session may enable the system to better understand the user's search needs, and accordingly may help provide more focused search results.

Classifying structural features of a digital document by feature type using machine learning is leveraged in a digital medium environment. A document analysis system is leveraged to extract structural features from digital documents, and to classifying the structural features by respective feature types. To do this, the document analysis system employs a character analysis model and a classification model. The character analysis model takes text content from a digital document and generates text vectors that represent the text content. A vector sequence is generated based on the text vectors and position information for structural features of the digital document, and the classification model processes the vector sequence to classify the structural features into different feature types. The document analysis system can generate a modifiable version of the digital document that enables its structural features to be modified based on their respective feature types.

Classifying structural features of a digital document by feature type using machine learning

A conversational agent facilitates conversational searches for users. The conversational agent is a reinforcement learning (RL) agent trained using a user model generated from existing session logs from a search engine. The user model is generated from the session logs by mapping entries from the session logs to user actions understandable by the RL agent and computing conditional probabilities of user actions occurring given previous user actions in the session logs. The RL agent is trained by conducting conversations with the user model in which the RL agent selects agent actions in response to user actions sampled using the conditional probabilities from the user model.

Growing community of inventors

Pitam Pura, India

Milan Aggarwal