ONLINE QUESTION ANSWERING, USING READING COMPREHENSION WITH AN ENSEMBLE OF MODELS

    公开(公告)号:US20230023958A1

    公开(公告)日:2023-01-26

    申请号:US17384690

    申请日:2021-07-23

    摘要: 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.

    Training a question-answer dialog sytem to avoid adversarial attacks

    公开(公告)号:US11520829B2

    公开(公告)日:2022-12-06

    申请号:US17076031

    申请日:2020-10-21

    摘要: 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.

    Entity Metadata Attached to Multi-Media Surface Forms
    6.
    发明申请
    Entity Metadata Attached to Multi-Media Surface Forms 有权
    实体元数据附加到多媒体表面形式

    公开(公告)号:US20160267071A1

    公开(公告)日:2016-09-15

    申请号:US14645935

    申请日:2015-03-12

    IPC分类号: G06F17/27 H04L12/58 H04L29/08

    摘要: A method, system, and/or computer program product displays related content on a user interface. An initial electronic document is analyzed to identify a mention in the initial electronic document. A mention descriptor of the mention in the initial electronic document is generated according to a context of the initial electronic document. The mention descriptor is mapped to a disambiguation identifier from a knowledge base that contains an entity related to the mention, where the disambiguation identifier identifies the entity within the knowledge base. The disambiguation identifier is associated with the initial electronic document, and is also associated with an entity metadata visualization panel. The disambiguation identifier is associated with the entity metadata visualization panel by mapping the entity metadata visualization panel to the disambiguation identifier. The entity metadata visualization panel is retrieved and displayed, on the user interface, as content related to the mention in the initial electronic document.

    摘要翻译: 方法,系统和/或计算机程序产品在用户界面上显示相关内容。 分析初始电子文档以识别初始电子文档中的提及。 根据初始电子文档的上下文产生在初始电子文档中提及的描述符。 提及描述符被映射到知识库中的消歧识别符,该知识库包含与提及相关的实体,其中消歧标识符标识知识库中的实体。 消歧识别符与初始电子文档相关联,并且还与实体元数据可视化面板相关联。 通过将实体元数据可视化面板映射到消歧识别符,消歧识别符与实体元数据可视化面板相关联。 实体元数据可视化面板在用户界面上被检索和显示为与初始电子文档中提及的内容相关的内容。

    Roadway condition predictive models

    公开(公告)号:US10916129B2

    公开(公告)日:2021-02-09

    申请号:US15418839

    申请日:2017-01-30

    摘要: 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.