Patents by Inventor Lingfei Wu
Lingfei Wu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11615152Abstract: Systems, devices, computer-implemented methods, and/or computer program products that facilitate event schema induction from unstructured or semi-structured data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a schema component and a retrieval component. The schema component can derive an event schema for a document corpus using parsing results obtained from the document corpus. The retrieval component can populate a response to a query with a document of the document corpus using events extracted from the query and the document using the event schema.Type: GrantFiled: April 6, 2021Date of Patent: March 28, 2023Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOISInventors: Rajarshi Haldar, Yu Deng, Lingfei Wu, Ruchi Mahindru, Julia Constanze Hockenmaier, Sinem Guven Kaya
-
Patent number: 11593672Abstract: Aspects described herein include a method of conversational machine reading comprehension, as well as an associated system and computer program product. The method comprises receiving a plurality of questions relating to a context, and generating a sequence of context graphs. Each of the context graphs includes encoded representations of: (i) the context, (ii) a respective question of the plurality of questions, and (iii) a respective conversation history reflecting: (a) one or more previous questions relative to the respective question, and (b) one or more previous answers to the one or more previous questions. The method further comprises identifying, using at least one graph neural network, one or more temporal dependencies between adjacent context graphs of the sequence. The method further comprises predicting, based at least on the one or more temporal dependencies, an answer for a first question of the plurality of questions.Type: GrantFiled: August 22, 2019Date of Patent: February 28, 2023Assignee: International Business Machines CorporationInventors: Lingfei Wu, Mohammed J Zaki, Yu Chen
-
Publication number: 20230055666Abstract: For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignment on the contextualized passage embeddings and the contextualized answer embeddings to obtain a passage embedding matrix. Construct a passage graph of the passage text based on the passage embedding matrix, and apply a bidirectional gated graph neural network to the passage graph until a final state embedding is determined, during which intermediate node embeddings are fused from both incoming and outgoing edges. Obtain a graph-level embedding from the final state embedding, and decode the final state embedding to generate an output sequence word-by-word. Train a machine learning model to generate at least one question corresponding to the passage text and the answer text, by evaluating the output sequence with a hybrid evaluator combining cross-entropy evaluation and reinforcement learning evaluation.Type: ApplicationFiled: October 23, 2022Publication date: February 23, 2023Inventors: Lingfei Wu, Yu Chen, Mohammed J. Zaki
-
Patent number: 11580322Abstract: A computer-implemented method for calculating Scalable Attributed Graph Embedding for Large-Scale Graph Analytics that includes computing a node embedding for a first node-attributed graph in a node embedded space. One or more random attributed graphs is generated in the node embedded space. A graph embedding operation is performed using a dissimilarity measure between one or more raw graphs and the one or more generated random graphs, and an edge-attributed graph into a second node-attributed graph using an adjoint graph.Type: GrantFiled: May 15, 2020Date of Patent: February 14, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventor: Lingfei Wu
-
Publication number: 20230012063Abstract: An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.Type: ApplicationFiled: July 7, 2021Publication date: January 12, 2023Inventors: Wenhao Yu, LINGFEI WU, Yu Deng, Qingkai Zeng, Ruchi Mahindru, Sinem Guven Kaya, Meng Jiang
-
Patent number: 11481418Abstract: For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignment on the contextualized passage embeddings and the contextualized answer embeddings to obtain a passage embedding matrix. Construct a passage graph of the passage text based on the passage embedding matrix, and apply a bidirectional gated graph neural network to the passage graph until a final state embedding is determined, during which intermediate node embeddings are fused from both incoming and outgoing edges. Obtain a graph-level embedding from the final state embedding, and decode the final state embedding to generate an output sequence word-by-word. Train a machine learning model to generate at least one question corresponding to the passage text and the answer text, by evaluating the output sequence with a hybrid evaluator combining cross-entropy evaluation and reinforcement learning evaluation.Type: GrantFiled: April 9, 2020Date of Patent: October 25, 2022Assignees: International Business Machines Corporation, RENSSELAER POLYTECHNIC INSTITUTEInventors: Lingfei Wu, Yu Chen, Mohammed J. Zaki
-
Publication number: 20220335270Abstract: Aspects of the present disclosure relate to knowledge graph compression. An input knowledge graph (KG) can be received. The input KG can be encoded to receive a first set of node embeddings. The input KG can be compressed into an output KG. The output KG can be encoded to receive a second set of node embeddings. A model for KG compression can be trained using optimal transport based on a distance matrix between the first set of node embeddings and the second set of node embeddings.Type: ApplicationFiled: April 15, 2021Publication date: October 20, 2022Inventors: Tengfei Ma, Manling Li, Mo Yu, Tian GAO, LINGFEI WU
-
Publication number: 20220318316Abstract: Systems, devices, computer-implemented methods, and/or computer program products that facilitate event schema induction from unstructured or semi-structured data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a schema component and a retrieval component. The schema component can derive an event schema for a document corpus using parsing results obtained from the document corpus. The retrieval component can populate a response to a query with a document of the document corpus using events extracted from the query and the document using the event schema.Type: ApplicationFiled: April 6, 2021Publication date: October 6, 2022Inventors: Rajarshi Haldar, Yu Deng, Lingfei Wu, Ruchi Mahindru, Julia Constanze Hockenmaier, Sinem Guven Kaya
-
Publication number: 20220245838Abstract: A computer-implemented method for visual question generation includes training an alignment module to analyze an image, an answer hint, and a visual hint with respect to the image. A k-nearest neighbors (KNN) graph is constructed by performing an aligned embedding for each region of the image. A node embedding component is generated by using a graph embedding component of the KNN graph. A visual question is generated by sequence decoding each image and graph of the image.Type: ApplicationFiled: January 29, 2021Publication date: August 4, 2022Inventors: Lingfei Wu, Lei Yu, Chen Wang, Dakuo Wang
-
Publication number: 20220245337Abstract: A set of sentences within a natural language text document are parsed, generating a word-level graph corresponding to a sentence in the set of sentences. Within the word-level graph using a trained entity identification model, a set of entity candidates are identified. From a set of graphs modelling relationships between portions of the set of sentences, a set of embeddings is generated. From a set of pairs of embeddings in the set of embeddings using a set of deconvolution layers, a set of links between entity candidates within the set of entity candidates is extracted. From the set of links and the set of entity candidates, an output graph modelling linkages between portions of the set of sentences within the natural language text document is generated.Type: ApplicationFiled: February 2, 2021Publication date: August 4, 2022Applicant: International Business Machines CorporationInventors: LINGFEI WU, Tengfei Ma, Tian GAO, Xiaojie Guo
-
Publication number: 20220245460Abstract: A graph neural network (GNN) training method, system, and computer program product in a graph, include generating, by the computing device, one or more one or more hypothetical edges between two or more nodes of a plurality of nodes of a graph neural network, testing, by the computing device, to determine whether the one or more generated hypothetical edges should be connected by using negative sampling, and permanently connecting, by the computing device, the one or more tested hypothetical edges if the negative sampling indicates the connectivity.Type: ApplicationFiled: January 29, 2021Publication date: August 4, 2022Inventors: Xiao Qin, Nasrullah Sheikh, Berthold Reinwald, Lingfei Wu
-
Patent number: 11366990Abstract: Embodiments of the present invention provide a computer-implemented method for performing unsupervised time-series feature learning. The method generates a set of reference time-series of random lengths, in which each length is uniformly sampled from a predetermined minimum length to a predetermined maximum length, and in which values of each reference time-series in the set are drawn from a distribution. The method generates a feature matrix for raw time-series data based on a set of computed distances between the generated set of reference time-series and the raw time-series data. The method provides the feature matrix as an input to one or more machine learning models.Type: GrantFiled: May 15, 2017Date of Patent: June 21, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Michael J. Witbrock, Lingfei Wu, Cao Xiao, Jinfeng Yi
-
Patent number: 11360763Abstract: One embodiment of the invention provides a method for automated code annotation in machine learning (ML) and data science. The method comprises receiving, as input, a section of executable code. The method further comprises classifying, via a ML model, the section of executable code with a stage classification label indicative of a stage within a workflow for automated ML that the executable code applies to. The method further comprises categorizing, based on the stage classification label, the section of executable code with a category of annotation that is most appropriate for the section of executable code. The method further comprises generating a suggested annotation for the section of executable code based on the category of annotation. The method further comprises providing, as output, the suggested annotation to a display of an electronic device for user review. The suggested annotation is user interactable via the electronic device.Type: GrantFiled: October 13, 2020Date of Patent: June 14, 2022Assignee: International Business Machines CorporationInventors: Dakuo Wang, Lingfei Wu, Yi Wang, Xuye Liu, Chuang Gan, Si Er Han, Bei Chen, Ji Hui Yang
-
Patent number: 11354904Abstract: Techniques for generating a grounded video description for a video input are provided. Hierarchical Attention based Spatial-Temporal Graph-to-Sequence Learning framework for producing a GVD is provided by generating an initial graph representing a plurality of object features in a plurality of frames of a received video input and generating an implicit graph for the plurality of object features in the plurality of frames using a similarity function. The initial graph and the implicit graph are combined to form a refined graph and the refined graph is processed using attention processes, to generate an attended hierarchical graph of the plurality of object features for the plurality of frames. The grounded video description is generated for the received video input using at least the hierarchical graph of the plurality of features.Type: GrantFiled: July 10, 2020Date of Patent: June 7, 2022Assignee: International Business Machines CorporationInventors: Lingfei Wu, Liana Fong
-
Publication number: 20220171923Abstract: A computer-implemented method for generating an abstract meaning representation (“AMR”) of a sentence, comprising receiving, by a computing device, an input sentence and parsing the input sentence into one or more syntactic and/or semantic graphs. An input graph including a node set and an edge set is formed from the one or more syntactic and/or semantic graphs. Node representations are generated by natural language processing. The input graph is provided to a first neural network to provide an output graph having learned node representations aligned with the node representations in the input graph. The method further includes predicting via a second neural network, node label and predicting, via a third neural network, edge labels in the output graph. The AMR is generated based on the predicted node labels and predicted edge labels. A system and a non-transitory computer readable storage medium are also disclosed.Type: ApplicationFiled: December 1, 2020Publication date: June 2, 2022Inventors: Lingfei Wu, Jinjun Xiong, Hongyu Gong, Suma Bhat, Wen-Mei Hwu
-
Publication number: 20220138266Abstract: Obtain, at a computing device, a segment of computer code. With a classification module of a machine learning system executing on the computing device, determine a required annotation category for the segment of computer code. With an annotation generation module of the machine learning system executing on the computing device, generate a natural language annotation of the segment of computer code based on the segment of computer code and the required annotation category. Provide the natural language annotation to a user interface for display adjacent the segment of computer code.Type: ApplicationFiled: November 3, 2020Publication date: May 5, 2022Inventors: Dakuo Wang, Lingfei Wu, Xuye Liu, Yi Wang, Chuang Gan, Jing Xu, Xue Ying Zhang, Jun Wang
-
Patent number: 11321541Abstract: Technology for using a bi-directed graph convolutional neural network (“BGCNN”) to convert RDF data into natural language text. Some embodiments perform RDF-to-Text generation by learning graph-augmented structural neural encoders, consisting of: (a) bidirected graph-based meta-paths encoder; (b) bidirected graph convolutional networks encoder, and (c) separated attention mechanism for combining encoders and decoder to translate RDF triplets to natural language description.Type: GrantFiled: July 2, 2020Date of Patent: May 3, 2022Assignee: International Business Machines CorporationInventors: Lingfei Wu, Chen Wang
-
Patent number: 11314950Abstract: A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.Type: GrantFiled: March 25, 2020Date of Patent: April 26, 2022Assignees: INTERNATIONAL BUSINESS MACHINES CORPORATION, THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOISInventors: Lingfei Wu, Jinjun Xiong, Hongyu Gong, Suma Bhat, Wen-Mei Hwu
-
Publication number: 20220113964Abstract: One embodiment of the invention provides a method for automated code annotation in machine learning (ML) and data science. The method comprises receiving, as input, a section of executable code. The method further comprises classifying, via a ML model, the section of executable code with a stage classification label indicative of a stage within a workflow for automated ML that the executable code applies to. The method further comprises categorizing, based on the stage classification label, the section of executable code with a category of annotation that is most appropriate for the section of executable code. The method further comprises generating a suggested annotation for the section of executable code based on the category of annotation. The method further comprises providing, as output, the suggested annotation to a display of an electronic device for user review. The suggested annotation is user interactable via the electronic device.Type: ApplicationFiled: October 13, 2020Publication date: April 14, 2022Inventors: Dakuo Wang, Lingfei Wu, Yi Wang, Xuye Liu, Chuang Gan, Si Er Han, Bei Chen, Ji Hui Yang
-
Publication number: 20220107799Abstract: Techniques regarding code retrieval tasks are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a code retrieval component that can execute a code retrieval machine learning task by computing an amount of similarity between neural network embeddings of graph representations of a query text and at least a portion of a computer program code.Type: ApplicationFiled: October 2, 2020Publication date: April 7, 2022Inventors: Lingfei Wu, Liana Fong