公开(公告)号：US20250156680A1

公开(公告)日：2025-05-15

申请号：US18507605

申请日：2023-11-13

Applicant: International Business Machines Corporation

Inventor： Maxwell Crouse ,  Ramon Fernandez Astudillo ,  Tahira Naseem ,  Subhajit Chaudhury ,  Pavan Kapanipathi Bangalore ,  Alexander Gray

IPC: G06N3/0455 ,  G06N3/0895

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to scalable learning of latent language structure with logical offline cycle consistency. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that can train a semantic parser to predict one or more parses for an input text using offline reinforcement learning based on parallelizable offline sampling.

公开(公告)号：US20230060589A1

公开(公告)日：2023-03-02

申请号：US17462327

申请日：2021-08-31

Applicant: International Business Machines Corporation

Inventor： Srinivas Ravishankar ,  Pavan Kapanipathi Bangalore ,  IBRAHIM ABDELAZIZ ,  NANDANA MIHINDUKULASOORIYA ,  Dinesh Garg ,  Salim Roukos ,  Alexander Gray

IPC: G06F40/20 ,  G06F16/2452 ,  G06F16/901 ,  G06N3/08 ,  G06N3/04

Abstract: One or more computer processors parse a received natural language question into an abstract meaning representation (AMR) graph. The one or more computer processors enrich the AMR graph into an extended AMR graph. The one or more computer processors transform the extended AMR graph into a query graph utilizing a path-based approach, wherein the query graph is a directed edge-labeled graph. The one or more computer processors generate one or more answers to the natural language question through one or more queries created utilizing the query graph.

公开(公告)号：US20220076144A1

公开(公告)日：2022-03-10

申请号：US17015243

申请日：2020-09-09

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Parikshit Ram ,  Dakuo Wang ,  Deepak Vijaykeerthy ,  Vaibhav Saxena ,  Sijia Liu ,  Arunima Chaudhary ,  Gregory Bramble ,  Horst Cornelius Samulowitz ,  Alexander Gray

IPC: G06N5/04 ,  G06K9/62 ,  G06F9/38

Abstract: The exemplary embodiments disclose a method, a computer program product, and a computer system for determining that one or more model pipelines satisfy one or more constraints. The exemplary embodiments may include detecting a user uploading data, one or more constraints, and one or more model pipelines, collecting the data, the one or more constraints, and the one or more model pipelines, and determining that one or more of the model pipelines satisfies all of the one or more constraints based on applying one or more algorithms to the collected data, constraints, and model pipelines.

公开(公告)号：US20250111206A1

公开(公告)日：2025-04-03

申请号：US18477575

申请日：2023-09-29

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Naweed Aghmad Khan ,  Jonathan Lenchner ,  Ismail Yunus Akhalwaya ,  Ryan Nelson Riegel ,  Alexander Gray

IPC: G06N3/047 ,  G06N3/048 ,  G06N3/082 ,  G06N3/084

Abstract: A method, computer system, and a computer program product are provided. Inferencing is performed with a probabilistic logical neural network. The probabilistic logical neural network includes a probabilistic graphical model that includes propositional nodes, logical operational nodes, and directed edges. The directed edges indicate a direction of upward inference. The downward inference is in an opposite direction from that of the directed edges. The probabilistic logical neural network implements upward and downward inference. The propositional and logical operational nodes are coupled with respective belief bounds. Each of the logical operational nodes includes a respective activation function set to a probability-respecting generalization of the Fréchet inequalities.

公开(公告)号：US20250021836A1

公开(公告)日：2025-01-16

申请号：US18351667

申请日：2023-07-13

Applicant: International Business Machines Corporation

Inventor： Shajith Ikbal Mohamed ,  Hima Prasad Karana ,  Udit Sharma ,  Sumit Neelam ,  Pavan Kapanipathi Bangalore ,  Ronny Luss ,  Maxwell Crouse ,  SUBHAJIT CHAUDHURY ,  Achille Belly Fokoue-Nkoutche ,  Alexander Gray

IPC: G06N5/025

Abstract: A system can comprise a memory that stores computer executable components, and a processor, operably coupled to the memory, that executes the computer executable components comprising: a linking component that associates one or more unmasked elements of the logical form with one or more corresponding structured knowledge elements of a knowledge base and a prediction component that predicts the one or more masked elements based on extended context of the corresponding structured knowledge elements of the knowledge base to generate one or more predicted elements. In an embodiment, the prediction component predicts the one or more masked elements based on scores of one or more candidate elements. In an embodiment, the system can determine one or more rules that describe the natural language text segment in terms of the structured knowledge elements and associated weights of the knowledge base paths.

公开(公告)号：US20230229859A1

公开(公告)日：2023-07-20

申请号：US17575951

申请日：2022-01-14

Applicant: International Business Machines Corporation

Inventor： Dinesh Khandelwal ,  G P Shrivatsa Bhargav ,  Saswati Dana ,  Dinesh Garg ,  Pavan Kapanipathi Bangalore ,  Salim Roukos ,  Alexander Gray ,  L. Venkata Subramaniam

IPC: G06F40/279 ,  G06N5/02

CPC classification number: G06F40/279 ,  G06N5/027

Abstract: Methods, systems, and computer program products for zero-shot entity linking based on symbolic information are provided herein. A computer-implemented method includes obtaining a knowledge graph comprising a set of entities and a training dataset comprising text samples for at least a subset of the entities in the knowledge graph; training a machine learning model to map an entity mention substring of a given sample of text to one corresponding entity in the set of entities, wherein the machine learning model is trained using a multi-task machine learning framework using symbolic information extracted from the knowledge graph; and mapping an entity mention substring of a new sample of text to one of the entities in the set using the trained machine learning model.

公开(公告)号：US20220300799A1

公开(公告)日：2022-09-22

申请号：US17202406

申请日：2021-03-16

Applicant: International Business Machines Corporation

Inventor： Hang Jiang ,  Sairam Gurajada ,  Lucian Popa ,  Prithviraj Sen ,  Alexander Gray ,  Yunyao Li

IPC: G06N3/08 ,  G06N3/04

Abstract: A system, computer program product, and method are provided for entity linking in a logical neural network (LNN). A set of features are generated for one or more entity-mention pairs in an annotated dataset. The generated set of features is evaluated against an entity linking LNN rule template having one or more logically connected rules and corresponding connective weights organized in a tree structure. An artificial neural network is leveraged along with a corresponding machine learning algorithm to learn the connective weights. The connective weights associated with the logically connected rules are selectively updated and a learned model is generated with learned thresholds and the learned weights for the logically connected rules.

公开(公告)号：US20210342732A1

公开(公告)日：2021-11-04

申请号：US16861671

申请日：2020-04-29

Applicant: International Business Machines Corporation

Inventor： Lior Horesh ,  Giacomo Nannicini ,  Oktay Gunluk ,  Sanjeeb Dash ,  Parikshit Ram ,  Alexander Gray

IPC: G06N20/00 ,  G06F17/10

Abstract: A processor may include a set of primitive operators, receive a set of data-driven operators, at least one of the set of data-driven operators including a machine learning model, and receive an input-output data pair set. Based on a grammar specifying rules for linking the set of primitive operators and the set of data-driven operators, the processor may search among the set of primitive operators and the set of data-driven operators to find a symbolic model that fits the input-output data set.

公开(公告)号：US12248521B1

公开(公告)日：2025-03-11

申请号：US18456999

申请日：2023-08-28

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Rosario Uceda-Sosa ,  Guilherme Augusto Ferreira Lima ,  Achille Belly Fokoue-Nkoutche ,  Alexander Gray ,  Maria Chang ,  Marcelo Machado

IPC: G06F16/90 ,  G06F16/903 ,  G06F16/9038

Abstract: Provided are techniques for a search using an overlay graph mapping to source knowledge graphs. A plurality of overlay graphs are generated, where each overlay graph comprises entities represented by nodes and relations represented by edges, and where the entities and the relations map to a subset of entities and relations in a plurality of source knowledge graphs. A search request comprising an entity and a relation is received. An overlay graph is selected from the plurality of overlay graphs based on the entity and the relation. The search request is issued against the overlay graph, where the search request is translated to knowledge graph specific queries, and where the knowledge graph specific queries are issued against the plurality of source knowledge graphs. Search results are received from the plurality of source knowledge graphs. The search results are used to respond to the search request.

公开(公告)号：US12242980B2

公开(公告)日：2025-03-04

申请号：US17015243

申请日：2020-09-09

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Parikshit Ram ,  Dakuo Wang ,  Deepak Vijaykeerthy ,  Vaibhav Saxena ,  Sijia Liu ,  Arunima Chaudhary ,  Gregory Bramble ,  Horst Cornelius Samulowitz ,  Alexander Gray

IPC: G06N5/04 ,  G06F9/38 ,  G06F18/243

Abstract: The exemplary embodiments disclose a method, a computer program product, and a computer system for determining that one or more model pipelines satisfy one or more constraints. The exemplary embodiments may include detecting a user uploading data, one or more constraints, and one or more model pipelines, collecting the data, the one or more constraints, and the one or more model pipelines, and determining that one or more of the model pipelines satisfies all of the one or more constraints based on applying one or more algorithms to the collected data, constraints, and model pipelines.