Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method, apparatus and computer program products are provided for generating routes for vehicles participating in a platooning plan, where the routes are influenced by one another. Methods may include receiving a first trip request including a first vehicle identification, a first trip origin, and a first trip destination; receiving a second trip request including a second vehicle identification, a second trip origin, and a second trip destination, where the first trip origin, second trip origin, first trip destination, and second trip destination are all different; generating a platooning plan that includes a first route and a second route, where the first route and the second route overlap for at least a portion of the respective route, where at least one of the first route and the second route are generated with an influence from the other of the first route and the second route.

Abstract: 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.

Abstract: Receive a question via a graphical user interface (GUI), obtain a passage of text potentially relevant to the question, and receive, via the GUI, a selection of a number of question-answering models to be ensembled. Produce a plurality of answers to the question by running a plurality of question-answering models, consistent with the selection of the number of question-answering models to be ensembled, on the passage of text. Produce an ensembled answer by ensembling the plurality of answers according to their respective confidence scores. Display, via the GUI, the ensembled answer in context of the passage of text, with the ensembled answer visually marked in the passage of text. Optionally, repeat these steps for a second passage of text.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A system, computer program product, and method are provided for extraction of factual data from unstructured natural language (NL) text. A detection model is applied to convert unstructured NL text in a first language to annotated NL text. The detection model identifies two or more mentions from the unstructured NL text and a logical position of the mentions. The detection model further identifies a sequential position for each of the mentions and attaches a sequential position identifier. A pattern of rules corresponding with the annotated NL text is identified and applied to the annotated NL text, and one or more facts embedded within the annotated NL text are extracted and converted into structured data.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: A method, apparatus and computer program products are provided for generating platooning plans for a plurality of vehicles and segmenting the routes of each of the vehicles into route segments based on how each segment is to be traversed. Methods may include: receiving a first trip request associated with a first vehicle including a first trip origin and destination; receiving a second trip request associated with a second vehicle including a second trip origin and destination; generating a platooning plan that includes a first route associated with the first vehicle and a second route associated with the second vehicle, where the first route and the second route overlap for at least a portion of the route; and segmenting the first route and the second route into a plurality of segments, where a platooning segment includes an overlap between the first route and the second route.

Abstract: A method, apparatus and computer program products are provided for identifying platooning restrictions and assessing dynamic factors associated with a road segment relating to platooning, and providing platooning information relating these restrictions and dynamic factors to a vehicle for platooning along the road segment. Methods may include: receiving an indication of a platooning request along a road segment from a vehicle; retrieving, from a database, restrictions relating to platooning along the road segment; analyzing information relating to dynamic factors associated with the road segment; generating platooning information based on a combination of restrictions relating to platooning along the road segment and the dynamic factors associated with the road segment; and providing route guidance to the vehicle, where the route guidance incorporates the platooning information.