International Business Machines Corporation

Bassem Makni

Bishwaranjan Bhattacharjee

Yuan-Chi Chang

Achille Belly Fokoue-Nkoutche

Mustafa Canim

Mohammad Sadoghi Hamedani

Kenneth Andrew Ross

Ibrahim Abdelaziz

Veronika Thost

Vittorio R Castelli

Robert G Farrell

Alfio Massimiliano Gliozzo

Kavitha Srinivas

Lingfei Wu

Radu Florian

Avirup Sil

Maria Chang

Gaetano Rossiello

Chulaka Gunasekara

Sarthak Dash

Kartik Talamadupula

Kshitij P Fadnis

Pavan Kapanipathi Bangalore

Cristina Cornelio

Nicholas Mattei

Avinash Balakrishnan

Maxwell Crouse

Siva Sankalp Patel

Generate, from a logical formula, a directed acyclic graph having a plurality of nodes and a plurality of edges. Assign an initial embedding to each mode and edge, to one of a plurality of layers. Compute a plurality of initial node states by using feed-forward networks, and construct cross-dependent embeddings between conjecture node embeddings and premise node embeddings. Topologically sort the DAG with the initial embeddings and node states. Beginning from a lowest rank, compute layer-by-layer embedding updates for each of the plurality of layers until a root is reached. Assign the embedding update for the root node as a final embedding for the DAG. Provide the final embedding for the DAG as input to a machine learning system, and carry out the automatic theorem proving with same.

Capturing the global structure of logical formulae with graph long short-term memory

A computer-implemented method according to one embodiment includes converting an input question into a vector form using trained word embeddings; constructing a type similarity matrix using a predetermined ontology; and determining a score for all possible types for the input question, based on the input question in vector form and the type similarity matrix.

Performing fine-grained question type classification

One embodiment of the invention provides a method for natural language processing (NLP). The method comprises extracting knowledge outside of text content of a NLP instance by extracting a set of subgraphs from a knowledge graph associated with the text content. The set of subgraphs comprises the knowledge. The method further comprises encoding the knowledge with the text content into a fixed size graph representation by filtering and encoding the set of subgraphs. The method further comprises applying a text embedding algorithm to the text content to generate a fixed size text representation, and classifying the text content based on the fixed size graph representation and the fixed size text representation.

Infusing knowledge into natural language processing tasks using graph structures

A method includes the following steps. Runtime statistics related to data transaction processing in a concurrent system are collected. A given request to access shared data in the concurrent system is receive. Based on the collected runtime statistics, the number of reattempts the given request can make to access the shared data prior to access control being switched from a hardware transactional memory to a locking mechanism is adaptively determined.

Adaptive concurrency control using hardware transactional memory and locking mechanism

Growing community of inventors

Troy, NY, United States of America

Bassem Makni