-
公开(公告)号：US20230419045A1
公开(公告)日：2023-12-28
申请号：US17808628
申请日：2022-06-24
Applicant: International Business Machines Corporation
Inventor： Song Feng , Chulaka Gunasekara , Hui Wan , Jatin Ganhotra , Siva Sankalp Patel , Sachindra Joshi
Abstract: Provided is a computer-implemented method, system, and computer program product for generating a goal-oriented dialogue from a grounding document. A processor may analyze a corpus of text. The processor may identify, based on the analyzing, one or more semantic structures that can be used to simulate a dialogue. The processor may generate, based on the identifying, a simulated dialogue, the simulated dialogue including one or more utterances from a simulated agent and one or more utterances from a simulated user to form a dialogue flow.
-
公开(公告)号：US11062726B2
公开(公告)日：2021-07-13
申请号：US16773335
申请日：2020-01-27
Applicant: International Business Machines Corporation
Inventor： Sasha P. Caskey , Jian Ni , Andrzej Sakrajda , Hui Wan , Cheng Wu
Abstract: A method of providing real-time speech analysis to a user includes capturing a speech input, performing a real-time recognition of the speech input including converting the speech input to a text, analyzing the recognized speech input to identify an error in a voice of the user, the analyzing including comparing a voice of a correct text generated by an automated speech generation system with the captured speed input, and processing the text to extract a context dialog prompt.
-
公开(公告)号：US20240202189A1
公开(公告)日：2024-06-20
申请号：US18081107
申请日：2022-12-14
Applicant: International Business Machines Corporation
Inventor： Hui Wan , Sachindra Joshi , Boaz Carmeli , Marina Danilevsky Hailpern
IPC: G06F16/2452
CPC classification number: G06F16/24526 , G06F16/24522
Abstract: Techniques for generating a clarification to distinguish among retrieved content in interactive systems are provided. In one aspect, a method for generating a clarification prompt in an interactive system includes: obtaining a training dataset for generating the clarification prompt from existing question-answering datasets by modifying original queries in the existing question-answering datasets to obtain training examples of under-specified queries; and training a machine learning model using the training dataset how to select latent differentiating factors in content candidates obtained from an under-specified query from a user and, based on the latent differentiating factors, generate the clarification prompt to clarify an intent of the user.
-
公开(公告)号：US11934922B2
公开(公告)日：2024-03-19
申请号：US17066685
申请日：2020-10-09
Applicant: International Business Machines Corporation
Inventor： Parul Awasthy , Bishwaranjan Bhattacharjee , John Ronald Kender , Radu Florian , Hui Wan
CPC classification number: G06N20/00 , G06F16/285
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.
-
公开(公告)号：US10586556B2
公开(公告)日：2020-03-10
申请号：US13930546
申请日：2013-06-28
Applicant: International Business Machines Corporation
Inventor： Sasha P. Caskey , Jian Ni , Andrzej Sakrajda , Hui Wan , Cheng Wu
Abstract: A method of providing real-time speech analysis for a user includes capturing a speech input, performing a real-time recognition of the speech input including converting the speech input to a text using an automatic speech recognition component, analyzing the recognized speech input, by a processing unit of a computer in a speech recognition and analyzing system, to identify an error in the user's speech, and by comparing a voice of a correct text generated by a speech generation and analyzing system with the captured speech input, and providing a real-time correction to the user based on a result of the comparing the voice of the correct text with the captured speech input. The comparing the voice of the correct text with the captured speech input includes comparing a standard pronunciation of the correct text with a pronunciation of the user in the captured speech input to identify the error.
-
Patent Agency Ranking
公开(公告)号：US09946800B2
公开(公告)日：2018-04-17
申请号：US14791789
申请日：2015-07-06
Applicant: International Business Machines Corporation
Inventor： Haifeng Qian , Hui Wan
CPC classification number: G06F17/30867 , G06F17/30958 , G06Q50/01
Abstract: Mechanisms are provided for performing a cognitive operation. An input graph is received having a plurality of first nodes, where subsets of first nodes are coupled to one another via first edges and each first edge has an associated weight. A blinking graph model is generated based on the graph, where blink rates are associated with second edges and are calculated based on weights of corresponding first edges in the input graph. The blink rate specifies a fraction of time a corresponding second edge is determined to be present in the blinking graph model. A relatedness metric is calculated for a target node relative to a node of interest based on the blink rates of the second edges. The relatedness metric indicates a degree of relatedness of the target node to the node of interest. A cognitive operation is then performed based on the relatedness metric.
-
7.发明申请Ranking Related Objects Using Blink Model Based Relation Strength Determinations 有权使用基于眨眼模型的关系强度确定来排列相关对象公开(公告)号：US20170011037A1
公开(公告)日：2017-01-12
申请号：US14791789
申请日：2015-07-06
Applicant: International Business Machines Corporation
Inventor： Haifeng Qian , Hui Wan
IPC: G06F17/30
CPC classification number: G06F17/30867 , G06F17/30958 , G06Q50/01
Abstract: Mechanisms are provided for performing a cognitive operation. An input graph is received having a plurality of first nodes, where subsets of first nodes are coupled to one another via first edges and each first edge has an associated weight. A blinking graph model is generated based on the graph, where blink rates are associated with second edges and are calculated based on weights of corresponding first edges in the input graph. The blink rate specifies a fraction of time a corresponding second edge is determined to be present in the blinking graph model. A relatedness metric is calculated for a target node relative to a node of interest based on the blink rates of the second edges. The relatedness metric indicates a degree of relatedness of the target node to the node of interest. A cognitive operation is then performed based on the relatedness metric.
Abstract translation: 提供了进行认知手术的机制。 接收具有多个第一节点的输入图，其中第一节点的子集经由第一边缘彼此耦合，并且每个第一边缘具有相关联的权重。 基于图形生成闪烁图形模型，其中闪烁速率与第二边缘相关联，并且基于输入图中对应的第一边缘的权重来计算。 闪烁速率指定相应的第二个边沿被确定为存在于闪烁图形模型中的一小段时间。 基于第二边缘的闪烁速率，针对目标节点相对于感兴趣的节点计算相关性度量。 相关性度量指示目标节点与感兴趣的节点的相关程度。 然后基于相关性度量执行认知操作。
-
公开(公告)号：US20220358288A1
公开(公告)日：2022-11-10
申请号：US17308575
申请日：2021-05-05
Applicant: International Business Machines Corporation
Inventor： Hui Wan , Xiaodong Cui , Luis A. Lastras-Montano
IPC: G06F40/284 , G06F40/205 , G06F40/237 , G06F40/30 , G06F40/42 , G06K9/66
Abstract: From metadata of a corpus of natural language text documents, a relativity matrix is constructed, a row-column intersection in the relativity matrix corresponding to a relationship between two instances of a type of metadata. An encoder model is trained, generating a trained encoder model, to compute an embedding corresponding to a token of a natural language text document within the corpus and the relativity matrix, the encoder model comprising a first encoder layer, the first encoder layer comprising a token embedding portion, a relativity embedding portion, a token self-attention portion, a metadata self-attention portion, and a fusion portion, the training comprising adjusting a set of parameters of the encoder model.
-
公开(公告)号：US20220229995A1
公开(公告)日：2022-07-21
申请号：US17154640
申请日：2021-01-21
Applicant: International Business Machines Corporation
Inventor： Song Feng , Hui Wan , Chulaka Gunasekara , Jatin Ganhotra , Sachindra Joshi , Luis A. Lastras-Montano
IPC: G06F40/35 , G06F40/44 , G06F40/284 , G06N5/04
Abstract: Techniques facilitating interpretation of deep neural model based dialogue agents are provided. In one example, a computer-implemented method comprises extracting, by a device operatively coupled to a processor, features from a dialogue model independently from the dialogue model, the features comprising input features provided to the dialogue model and output features produced via the dialogue model in response to the input features, resulting in extracted features; and analyzing, by the device, a dialogue context associated with the extracted features by identifying pairwise interactions between respective ones of the extracted features.
-
10.发明申请公开(公告)号：US20220114473A1
公开(公告)日：2022-04-14
申请号：US17066685
申请日：2020-10-09
Applicant: International Business Machines Corporation
Inventor： Parul Awasthy , Bishwaranjan Bhattacharjee , John Ronald Kender , Radu Florian , Hui Wan
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.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.021 seconds)
