公开(公告)号：US20210026922A1

公开(公告)日：2021-01-28

申请号：US16518120

申请日：2019-07-22

Applicant: International Business Machines Corporation

Inventor： LINGFEI WU ,  Wei Zhang

IPC: G06F17/27

Abstract: Aspects described herein include a method of semantic parsing, and related system and computer program product. The method comprises receiving an input comprising a plurality of words, generating a structured representation of the plurality of words, encoding the structured representation into a latent embedding space, and decoding the encoded structured representation from the latent embedding space into a logical representation of the plurality of words.

公开(公告)号：US20220245337A1

公开(公告)日：2022-08-04

申请号：US17165440

申请日：2021-02-02

Applicant: International Business Machines Corporation

Inventor： LINGFEI WU ,  Tengfei Ma ,  Tian GAO ,  Xiaojie Guo

IPC: G06F40/205 ,  G06F16/28 ,  G06N3/04 ,  G06N3/08 ,  G06F40/279

Abstract: 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.

公开(公告)号：US20230012063A1

公开(公告)日：2023-01-12

申请号：US17369040

申请日：2021-07-07

Applicant: International Business Machines Corporation ,  University of Notre Dame

Inventor： Wenhao Yu ,  LINGFEI WU ,  Yu Deng ,  Qingkai Zeng ,  Ruchi Mahindru ,  Sinem Guven Kaya ,  Meng Jiang

IPC: G06F16/9032 ,  G06N20/00 ,  G06K9/00 ,  G06K9/62

Abstract: 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.

公开(公告)号：US20220335270A1

公开(公告)日：2022-10-20

申请号：US17231289

申请日：2021-04-15

Applicant: International Business Machines Corporation

Inventor： Tengfei Ma ,  Manling Li ,  Mo Yu ,  Tian GAO ,  LINGFEI WU

IPC: G06N3/04

Abstract: 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.

公开(公告)号：US20210056445A1

公开(公告)日：2021-02-25

申请号：US16547862

申请日：2019-08-22

Applicant: International Business Machines Corporation

Inventor： LINGFEI WU ,  MOHAMMED J. ZAKI ,  YU CHEN

IPC: G06N5/04 ,  G06F17/16 ,  G06F17/27 ,  G06N3/04 ,  G06K9/62

Abstract: 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.

公开(公告)号：US20190340542A1

公开(公告)日：2019-11-07

申请号：US15972108

申请日：2018-05-04

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： LINGFEI WU ,  Kun Xu ,  Pin-Yu Chen ,  Chia-Yu Chen

IPC: G06N99/00 ,  G06F17/30

Abstract: A method and system of analyzing a symbolic sequence is provided. Metadata of a symbolic sequence is received from a computing device of an owner. A set of R random sequences are generated based on the received metadata and sent to the computing device of the owner of the symbolic sequence for computation of a feature matrix based on the set of R random sequences and the symbolic sequence. The feature matrix is received from the computing device of the owner. Upon determining that an inner product of the feature matrix is below a threshold accuracy, the iterative process returns to generating R random sequences. Upon determining that the inner product of the feature matrix is at or above the threshold accuracy, the feature matrix is categorized based on machine learning. The categorized global feature matrix is sent to be displayed on a user interface of the computing device of the owner.