Abstract: A computer-implemented method includes obtaining, from text corpus including article-summary pairs in a plurality of languages, a plurality of article-summary pairs in a target language among the plurality of languages, to form an article-summary pairs dataset in which each article corresponds to a summary; inputting articles from the article-summary pairs to a machine learning model; generating, by the machine learning model, embeddings for sentences of the articles; extracting, by the machine learning model, keywords from the articles with a probability that varies based on lengths of the sentences, respectively; outputting, by the machine learning model, the keywords; applying a maximal marginal relevance algorithm to the extracted keywords, to select relevant keywords; and generating a keyword-text pairs dataset that includes the relevant keywords and text from the articles, the text corresponding to the relevant keywords in each of keyword-text pairs of the keyword-text pairs dataset.

Abstract: A computer-implemented method includes obtaining, from text corpus including article-summary pairs in a plurality of languages, a plurality of article-summary pairs in a target language among the plurality of languages, to form an article-summary pairs dataset in which each article corresponds to a summary; inputting articles from the article-summary pairs to a machine learning model; generating, by the machine learning model, embeddings for sentences of the articles; extracting, by the machine learning model, keywords from the articles with a probability that varies based on lengths of the sentences, respectively; outputting, by the machine learning model, the keywords; applying a maximal marginal relevance algorithm to the extracted keywords, to select relevant keywords; and generating a keyword-text pairs dataset that includes the relevant keywords and text from the articles, the text corresponding to the relevant keywords in each of keyword-text pairs of the keyword-text pairs dataset.

Abstract: A method includes preparing a base model using an input model pretrained on at least three languages different from each other and a base vocabulary including words corresponding to two languages among the at least three languages, where the preparing the base model includes constraining the input model to the words included in the base vocabulary; training the base model using a first enhanced training dataset generated from public data, to generate a text summarization model; training the base model using a second enhanced training dataset generated from the first enhanced training dataset, to generate a text generation model; and training the base model using a third enhanced training dataset that is generated using the second enhanced training dataset and the text summarization model, to generate a next sentence generation model.

Abstract: A method for generating multilingual aspect-based sentiment annotations in different languages includes, by a computing system, receiving first content in a first language and performing an inference of the first content for presence of a plurality of aspects, including identifying aspects within the first content, annotating the first content in accordance with the identified aspects within the first content, and generating an annotated first content. The method further includes receiving second content in a second language, including a translation of the first content, performing the inference of the second content for presence of the aspects to generate an annotated second content and producing a training set in the second language from the annotated second content. The training set is suitable for use, in the second language, in refining the inference in classifying portions of the second content into one of a plurality of polarities associated with the plurality of aspects.

Abstract: The system generates templates to be used for use in synthetic document generation. Generating a template includes selecting entities to be included in the template and/or selecting characteristics of entities in the template. The system may execute randomization functions to determine which entities, of a candidate set of entities, are to be included in a template. The randomization functions may accept, as input, probabilities associated with the entities to compute the inclusion or exclusion of entities in the template. Different entities may be associated with different corresponding probabilities. The system may execute randomization functions to determine characteristics of entities that are included in a template. The characteristics may be selected from a specific candidate set of characteristics or a range of characteristic values.

Abstract: Knowledge graph guide and entity controlled techniques for generating synthetic doctor-patient conversations.

Abstract: The system generates templates to be used for use in synthetic document generation. Generating a template includes selecting entities to be included in the template and/or selecting characteristics of entities in the template. The system may execute randomization functions to determine which entities, of a candidate set of entities, are to be included in a template. The randomization functions may accept, as input, probabilities associated with the entities to compute the inclusion or exclusion of entities in the template. Different entities may be associated with different corresponding probabilities. The system may execute randomization functions to determine characteristics of entities that are included in a template. The characteristics may be selected from a specific candidate set of characteristics or a range of characteristic values.

Abstract: A computer-implemented method includes obtaining, from text corpus including article-summary pairs in a plurality of languages, a plurality of article-summary pairs in a target language among the plurality of languages, to form an article-summary pairs dataset in which each article corresponds to a summary; inputting articles from the article-summary pairs to a machine learning model; generating, by the machine learning model, embeddings for sentences of the articles; extracting, by the machine learning model, keywords from the articles with a probability that varies based on lengths of the sentences, respectively; outputting, by the machine learning model, the keywords; applying a maximal marginal relevance algorithm to the extracted keywords, to select relevant keywords; and generating a keyword-text pairs dataset that includes the relevant keywords and text from the articles, the text corresponding to the relevant keywords in each of keyword-text pairs of the keyword-text pairs dataset.

Abstract: A method includes preparing a base model using an input model pretrained on at least three languages different from each other and a base vocabulary including words corresponding to two languages among the at least three languages, where the preparing the base model includes constraining the input model to the words included in the base vocabulary; training the base model using a first enhanced training dataset generated from public data, to generate a text summarization model; training the base model using a second enhanced training dataset generated from the first enhanced training dataset, to generate a text generation model; and training the base model using a third enhanced training dataset that is generated using the second enhanced training dataset and the text summarization model, to generate a next sentence generation model.

Abstract: A turn signal switch assembly is constructed having a switch stalk and junction box rotatably coupled using a shoulder bolt. The shoulder bolt has a shoulder area useful for allowing the switch stalk to rotate freely relative to the junction box. The threaded end of the shoulder bolt is turned and tightened into at least one corresponding threaded aperture in the junction box, thereby mechanically coupling the switch stalk to the junction box. The threaded end of the shoulder bolt also extends past a surface of the junction box so that the threaded end is exposed. The threaded end is mechanically transformed by an orbital riveting device so as to act as a positive locking feature. The shoulder bolt thereafter secures the switch stalk to the junction box using the mechanical advantages of a threaded connection in combination with the positive locking feature of a riveted connection.

Abstract: A turn signal switch assembly is constructed having a switch stalk and junction box rotatably coupled using a shoulder bolt. The shoulder bolt has a shoulder area useful for allowing the switch stalk to rotate freely relative to the junction box. The threaded end of the shoulder bolt is turned and tightened into at least one corresponding threaded aperture in the junction box, thereby mechanically coupling the switch stalk to the junction box. The threaded end of the shoulder bolt also extends past a surface of the junction box so that the threaded end is exposed. The threaded end is mechanically transformed by an orbital riveting device so as to act as a positive locking feature. The shoulder bolt thereafter secures the switch stalk to the junction box using the mechanical advantages of a threaded connection in combination with the positive locking feature of a riveted connection.

Abstract: Apparatus, methods and devices for electrically coupling wires in a turn signal switch assembly that prevents the entangling of wires with the different components of the turn signal switch assembly.

Abstract: An adjustable lamp mounting system consisting of a lamp housing, a mounting bracket and a mounting stud having an enlarged head and a guiding portion adjacent the enlarged head. The enlarged head of the mounting stud is configured to substantially correspond to the height of the interior chamber created between the mounting bracket and lamp housing, thereby maintaining the mounting stud guiding portion within a mounting bracket slot.