International Business Machines Corporation

Ibrahim Abdelaziz

Kavitha Srinivas

Julian Timothy Dolby

Achille Belly Fokoue-Nkoutche

Pavan Kapanipathi Bangalore

Cristina Cornelio

Bassem Makni

Veronika Thost

Mohammad Sadoghi Hamedani

Lingfei Wu

Dinesh Garg

Maria Chang

Chulaka Gunasekara

Kartik Talamadupula

Kshitij P Fadnis

Nandana Sampath Mihindukulasooriya

Michael John Witbrock

Alexander Gray

Meinolf Sellmann

Salim E Roukos

Avinash Balakrishnan

Maxwell Crouse

Aldo Pareja

Nicholas Mattei

Siva Sankalp Patel

Srinivas Ravishankar

Wenting Zhao

A corpus of source code from a code database is accessed and a language prediction model is trained based on the corpus of source code. A given program is accessed and a completion of a given line of the given program is predicted by performing inferencing using the language prediction model and at least a portion of the given program. The given line is completed based upon the prediction.

Performing code completion using data flow

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.

Knowledge base question answering

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

To improve the technological process of programming a computer using a dynamic programming language, generate a first portion of training data which maps types in the dynamic programming language to corresponding functions and methods by performing information retrieval on documentation libraries in the dynamic programming language and/or generate a second portion of training data which maps program variables to the corresponding functions and methods by performing data flow analysis on a plurality of pre-existing programs written in the dynamic programming language. Train a neural network on the first and/or second portions of training data to infer unknown types in the dynamic programming language. Carry out inference with the trained neural network to infer the unknown types. Facilitate programming in the dynamic programming language based on the inferred unknown types. Optionally, execute a resulting program.

Type inference in dynamic languages

A method of improving computing efficiency of a computing device for language-independent problem solving and reasoning includes receiving a query from a user, which is decomposed into one or more sub-queries arranged according to a tree structure. The one or more sub-queries are executed in a knowledge base. The results of the executed one or more sub-queries are received and composed into a query response. The query response is transmitted to the user.

Problem manipulators for language-independent computerized reasoning

Systems and methods for indexing and accessing code snippets in repositories. A program graph index is maintained for code snippets within a repository with documents that have at least one code snippet. The program graph index includes a program graph indicating a relationship between program elements within each source code snippet within the documents. A user provided code snippet is received and a target program graph indicating a relationship between program elements within the user provided code snippet is determined and compared to each respective program graph. Based on the comparison, an identified set of documents within the repository of documents is determined that have code snippets with respective program graphs that are also at least a sub-tree of the target program graph. At least one document in the identified set of documents is presented to a user.

Indexing and accessing source code snippets contained in documents

A processor may analyze one or more sections of code within a program. The processor may compute a context for each of the one or more sections of code. The processor may generate one or more search terms that are respectively associated with each of the one or more sections of code. The processor may automatically display reference data to a user.

Automatic identification of reference data

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 knowledge graph is traversed by receiving a knowledge graph at a deep neural network, the knowledge graph including a plurality of nodes connected by a plurality of edges, each respective edge of the plurality of edges being associated with a corresponding distance representing embedded semantic information. The deep neural network is trained to capture the embedded semantic information. A path query is received at the deep neural network. A context is determined for the received path query at the deep neural network. The deep neural network performs the traversing of the knowledge graph in response to the received path query, based upon the determined context and the embedded semantic information.

Determining context-aware distances using deep neural networks

Growing community of inventors

Tarrytown, NY, United States of America

Ibrahim Abdelaziz