International Business Machines Corporation

Avirup Sil

Radu Florian

Vittorio R Castelli

Taesun Moon

Gourab Kundu

Georgiana Dinu

Mihaela Ancuta Bornea

Sara Rosenthal

Robert G Farrell

Bishwaranjan Bhattacharjee

Alfio Massimiliano Gliozzo

Martin Franz

Gaetano Rossiello

Michele Merler

Sarthak Dash

Rameswar Panda

Bassem Makni

Lin Pan

Aashka Trivedi

A neural architecture search method, system, and computer program product that determines, by a computing device, a best fit language model of a plurality of language models that is a best fit for interpretation of a corpus of natural language and interprets, by the computing device, the corpus of natural language using the best fit language model.

Neural architecture search of language models using knowledge distillation

A method, computer program product, and/or computer system generate a first adversarial statement via: (1) receiving a question and an original context for the question; (2) converting the question into a statement with a placeholder answer; (3) picking randomly an answer entity from a training text corpus; (4) replacing the placeholder answer with the randomly picked answer entity; and (5) leaving a correct question entity in the statement. The first adversarial statement is inserted into the original context to form a first adversarial context. The question and the first adversarial context as a first pair and the question and the original context as a second pair are input into a question-answer dialog system to train the question-answer dialog system.

Training a question-answer dialog system to avoid adversarial attacks

A method and system are provided for combining models. The method includes forming, by a computer having a processor and a memory, model pairs from a model ensemble that includes a plurality of models. The method further includes comparing the model pairs based on sets of output results produced by the model pairs to provide comparison results. The method also includes constructing, by the computer, a combination model from at least one of the model pairs based on the comparison results. The comparing step is performed using user-generated set-based feedback.

Search, question answering, and classifier construction

A method includes receiving, by a question-answer system, a question in a first language and the question in a second language and predicting, by the question-answer system, a first answer to the question in the first language and a second answer to the question in the second language. The method also includes generating, by the question-answer system, a first vector representing the question in the first language and a second vector representing the question in the second language and adjusting the question-answer system based on the first and second answers and the first and second vectors such that when the question-answer system subsequently generates a third vector representing the question in the first language and a fourth vector representing the question in the second language, a distance between the third and fourth vectors is less than a distance between the first and second vectors.

Enhancing multi-lingual embeddings for cross-lingual question-answer system

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

A method, computer program product, and/or computer system protects a question-answer dialog system from being attacked by adversarial statements that incorrectly answer a question. A computing device accesses a plurality of adversarial statements that are capable of making an adversarial attack on a question-answer dialog system, which is trained to provide a correct answer to a specific type of question. The computing device utilizes the plurality of adversarial statements to train a machine learning model for the question-answer dialog system. The computing device then reinforces the trained machine learning model by bootstrapping adversarial policies that identify multiple types of adversarial statements onto the trained machine learning model. The computing device then utilizes the trained and bootstrapped machine learning model to avoid adversarial attacks when responding to questions submitted to the question-answer dialog system.

Training a question-answer dialog sytem to avoid adversarial attacks

A personalized scheduling and networking method, system, and non-transitory computer readable medium include creating a user persona profile based on user information, extracting scheduling and networking information based on event information, matching a user with events during a conference based on the extracted scheduling and networking information and the user persona profile, and creating a schedule and a route for maximizing a number of the events and networking opportunities based on matches of the matching.

Personalized scheduling and networking system, method, and recording medium

A roadway condition predictive model that can recommend ameliorative roadway action(s) is disclosed. A roadway controller computer acquires sensor and location information, which describe physical driving surface conditions on the roadway, from a plurality of vehicles that travel on the roadway. The roadway controller computer also acquires environmental and traffic conditions for the roadway. The roadway controller computer creates a predictive model that describes a deterioration rate and future physical condition of the roadway, based on the acquired sensor, location information, environmental and traffic conditions for the roadway. The roadway controller computer then implements an action to ameliorate deterioration of the roadway that is predicted by the predictive model.

Roadway condition predictive models

A computer-implemented computer documentation validation method, the method comprising: manipulating a user interface of an operating system by taking control of a user input device to execute a command of a computer software documentation on behalf of the user; and outputting an error code when a failure is a result of the executed command.

Validating computer documentation via error detection in a natural language of the computer documentation

A query expansion method, system, and computer program product, include establishing a context of a query to execute the query within a search index by labeling phrases of interest of the query, expanding of the phrases of interest based on a language model and a topic model, and identifying and incorporating an available historical query into the context according to a historical phrase of interest and an expansion of one or more historical phrases of interest, and retrieving and displaying one or more search results based on the query and the context of the query as a first visual mark indicating a linkage between one or more terms of the query and the one or more search results and a second visual mark indicating an alignment between the available historical query and a match to the terms of the query and the search result.

Query expansion

An analytics engine operates on data associated with users and opportunities. A broker system provides the opportunity data to the analytics engine, but the analytics engine does not provide user data to the broker system. The analytics engine notifies users of results of analytics operations.

Contextualized analytics platform

A power tool accident prevention system receiving images from a static camera of a setup of a power tool, the system comprising: a processor; and a memory, the memory storing instructions to cause the processor to: analyze the images to identify inherent dangers in the setup of the power tool; identify at least one potential cause of an accident based on the identified inherent dangers; and activate an emergency safety measure of the power tool to avoid the at least one potential cause of the accident.

Power tool accident prevention

A computer-implemented computer documentation validation method, system, and computer program product for discovering problems and errors in an entire set of program/software documentation written by humans and flagging the documentation errors to suggest corrections to humans.

System, method, and recording medium for validating computer documentation

A power tool accident prevention method, system, and non-transitory computer readable medium receiving images from a static camera of a setup or operation of a power tool, include a danger identification circuit configured to: analyze the images to identify inherent dangers in the setup or the operation of the power tool, and identify at least one potential cause of an accident based on the identified inherent dangers, and a power tool disabling circuit configured to activate an emergency safety measure of the power tool to avoid the at least one potential cause of the accident.

System, method, and recording medium for power tool accident prevention

Techniques for drone device control are provided. In one example, a computer-implemented method comprises: meeting, by a drone device operatively coupled to a processor, an aircraft at a first location; and guiding, by the drone device, the aircraft to a second location along a ground movement path selected from a plurality of ground movement paths associated with an airport. The guiding can comprise providing a direction indication to the aircraft; and monitoring a defined region around the aircraft for one or more hazards. The guiding can also comprise, in response to identifying a hazard from the one or more hazards related to the defined region around the aircraft, providing a hazard indication to the aircraft.

Growing community of inventors

Ossining, NY, United States of America

Avirup Sil