International Business Machines Corporation

Nuance Communications, Inc.

Radu Florian

Vittorio R Castelli

Avirup Sil

Taesun Moon

Gourab Kundu

Georgiana Dinu

Mihaela Ancuta Bornea

Sara Rosenthal

Martin Franz

Robert T Ward

Xiaoqiang Luo

Hema Raghavan

Robert G Farrell

Bishwaranjan Bhattacharjee

Alfio Massimiliano Gliozzo

Abraham P Ittycheriah

Girija Yegnanarayanan

Jeffrey Scott Sorensen

John Ronald Kender

Salim Estephan Roukos

Laura Chiticariu

Hiroshi Kanayama

Gaetano Rossiello

Sameer Maskey

Sarthak Dash

Jeffrey Scott McCarley

Kishore A Papineni

Hui Wan

John Ferdinand Pitrelli

Jian Ni

Salim E Roukos

Brian William Delaney

Imed Zitouni

Bassem Makni

Lin Pan

Neal Snider

Yaser Al-Onaizan

Takuya Ohko

Efsun Kayi

Yousef El-Kurdi

Parul Awasthy

Scott McCarley

A computer system, product, and method are provided. The computer system includes an artificial intelligence (AI) platform operatively coupled to a processor. The AI platform includes tools in the form of a machine learning model (MLM) manager, a metric manager, and a training manager. The MLM manager accesses a plurality of pre-trained source MLMs, and inputs a plurality of data objects of a test dataset into each of the source MLMs. The test dataset includes the plurality of data objects associated with respective labels. For each source MLM, associated labels are generated from the inputted data objects and a similarity metric is calculated. The MLM manager selects a base MLM to be used for transfer learning from the plurality of source MLMs based upon the calculated similarity metric. The training manager trains the selected base MLM with a target dataset for the target domain.

Predictive data and model selection for transfer learning in natural language processing

An approach for generating synthetic treebanks to be used in training a parser in a production system is provided. A processor receives a request to generate one or more synthetic treebanks from a production system, wherein the request indicates a language for the one or more synthetic treebanks. A processor retrieves at least one corpus of text in which the requested language is present. A processor provides the at least one corpus to a transformer enhanced parser neural network model. A processor generates at least one synthetic treebank associated with a string of text from the at least one corpus of text in which the requested language is present. A processor sends the at least one synthetic treebank to the production system, wherein the production system trains a parser utilized by the production system with the at least one synthetic treebank.

Treebank synthesis for training production parsers

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 processor may receive a text segment. The processor may analyze the text segment at a plurality of granularity levels wherein each of the plurality of granularity levels has a comparative selection value for identifying one or more objects of interest within the text segment. The processor may select an optimized granularity level with an optimum comparative selection value. The processor may identify the one or more objects of interest within the text segment. The processor may display the one or more objects of interest to a user.

Text classification using models with complementary granularity and accuracy

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 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

A method for automatically extracting and organizing information by a processing device from a plurality of data sources is provided. A natural language processing information extraction pipeline that includes an automatic detection of entities is applied to the data sources. Information about detected entities is identified by analyzing products of the natural language processing pipeline. Identified information is grouped into equivalence classes containing equivalent information. At least one displayable representation of the equivalence classes is created. An order in which the at least one displayable representation is displayed is computed. A combined representation of the equivalence classes that respects the order in which the displayable representation is displayed is produced.

System and method for automatically detecting and interactively displaying information about entities, activities, and events from multiple-modality natural language sources

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

Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.

Growing community of inventors

Danbury, CT, United States of America

Radu Florian