WO2021223882A1 - Explication de prédiction dans des classificateurs d'apprentissage automatique - Google Patents

Explication de prédiction dans des classificateurs d'apprentissage automatique Download PDF

Info

Publication number
WO2021223882A1
WO2021223882A1 PCT/EP2020/062888 EP2020062888W WO2021223882A1 WO 2021223882 A1 WO2021223882 A1 WO 2021223882A1 EP 2020062888 W EP2020062888 W EP 2020062888W WO 2021223882 A1 WO2021223882 A1 WO 2021223882A1
Authority
WO
WIPO (PCT)
Prior art keywords
textual
knowledge graph
text data
features
input text
Prior art date
Application number
PCT/EP2020/062888
Other languages
English (en)
Inventor
Suleiman Ali KHAN
Simone ROMANO
Mark VAN HEESWIJK
Muhammad AMMAD-UD-DIN
Jonathan Paul FERNANDEZ STRAHL
Adrian Flanagan
Kuan Eeik TAN
Original Assignee
Huawei Technologies Co., Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co., Ltd. filed Critical Huawei Technologies Co., Ltd.
Priority to PCT/EP2020/062888 priority Critical patent/WO2021223882A1/fr
Publication of WO2021223882A1 publication Critical patent/WO2021223882A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Definitions

  • the present disclosure relates to explanation of reasons for classification predictions of machine learning based text classifiers.
  • Machine learning (ML) text classifiers such as neural network text classifier models, employ successive layers of operations to progressively extract features from input text data to generate a classification prediction for the input text data.
  • ML text classifiers One application of ML text classifiers is automated moderation of user-generated text content in online discussion forums, for deciding whether to display or hide a content item, such as a user post, from forum users.
  • classification predictions of ML text classifiers may appear relatively arbitrary and difficult to understand. This may undesirably result in a lack of users’ trust in classification predictions and decisions based thereon. It is therefore desirable to provide an explanation of the reasons for classification predictions of ML text classifiers.
  • An objective of the present disclosure is to provide a method for explaining reasons for classification predictions of ML text classifiers. From a user’s perspective, by providing reasons for classification predictions, a user may better comprehend the prediction and decisions based thereon. Consequently, users’ trust in classification predictions of ML text classifiers and decisions based thereon may advantageously be increased.
  • An aspect of the present disclosure provides a method of classifying input text data using a machine-learning classifier, the method comprising: receiving input text data, performing text classification operations using the machine-learning classifier on the input text data and predicting a classification for the input text data, identifying a textual feature of the input text data relevant to the classification prediction, comparing the identified textual feature of the input text data to a knowledge graph representation of textual features wherein one or more textual features of the knowledge graph are labelled with a natural-language descriptor of the respective textual feature.
  • the method could, for example, be used for moderating user-generated content in an online discussion forum to remove offensive posts.
  • the step of receiving input text data could comprise selecting a user-generated post for review.
  • the textual features could, for example, be words or phrases.
  • the method firstly involves generating a classification for input text data, e.g. whether the input text is ‘offensive’ or ‘not-offensive’.
  • a classification for input text data e.g. whether the input text is ‘offensive’ or ‘not-offensive’.
  • the method of the disclosure thus further facilitates generating an explanation of the reason for the classification prediction in a human-understandable natural-language, for example, English-language.
  • the explanation of the reason for the classification prediction involves identifying textual features, e.g. word, of the input text data that are relevant to the classification prediction are identified.
  • the identified textual features are then compared to a knowledge graph representation of textual features, wherein one or more textual features of the knowledge graph are labelled with natural-language descriptors.
  • the natural-language descriptors are human generated pre-defmed label describing the semantic meaning of the textual features in a natural language, e.g. “this word/phrase is derogatory.”.
  • Such a natural-language descriptor may desirably be capable of explaining succinctly and understandably to a human user why a classification prediction and associated decision was made, e.g. that a comment was removed because the comment was classified as “offensive” because “word X is derogatory”.
  • each textual feature had its own natural-language descriptor label
  • the reference would need to contain a very large number of textual features, e.g. words, and it may be prohibitively time-consuming for a human to generate a unique natural-language descriptor label for each word in the reference, and may additionally be very computationally expensive to store such as large number of natural-language descriptor labels.
  • the method further comprises identifying one or more textual features of the knowledge graph corresponding to the identified textual feature of the input text data.
  • the method further comprises identifying natural-language descriptor labels of the one or more textual features of the knowledge graph corresponding to the identified textual feature of the input text data, inputting vector representations of the identified natural language descriptor labels into a graph convolutional network, and predicting a natural- language descriptor using the graph convolutional network for the identified textual feature of the input text data based on the natural-language descriptor labels of the one or more textual features of the knowledge graph corresponding to the identified textual feature of the input text data.
  • the method comprises training the graph convolutional neural network to predict one or more natural-language descriptor labels for textual features of the knowledge graph based on natural language descriptor labels of one or more other textual features of the knowledge graph.
  • the method comprises training the graph convolutional neural network to predict one or more natural-language descriptor labels for any unlabelled textual feature of the knowledge graph based on the natural language descriptor labels of the one or more other textual features of the knowledge graph.
  • the method may involve predicting natural-language descriptor labels for all unlabelled textual features of the knowledge graph, to thereby generate a fully-labelled knowledge graph based on the human-generated sparse- labels.
  • the graph convolutional neural network is trained by stochastic gradient descent.
  • the method further comprises outputting the predicted classification for the input text data and the predicted natural-language descriptor for the identified textual feature of the input text data.
  • the predicted classification and the predicted natural-language descriptor could be output via an electronic display device for display to a user.
  • the method further comprises outputting the predicted classification for the input text data and the predicted natural-language descriptor for the identified textual feature of the input text data comprises outputting the predicted classification together with the predicted natural-language descriptor.
  • comparing the identified textual feature of the input text data to a knowledge graph representation of textual features wherein one or more textual features of the knowledge graph are labelled with a natural-language descriptor of the respective textual feature comprises obtaining a knowledge graph representation of textual features, obtaining natural-language descriptors of one or more of the textural features of the knowledge graph, and storing the knowledge graph of textual features and the natural-language descriptors in a machine-readable memory wherein the natural-language descriptors are linked to a respective textual feature of the knowledge graph.
  • the method may comprise obtaining a pre-built knowledge graph representation of textual features and adding sparse natural- language descriptor labels.
  • identifying one or more textual features of the knowledge graph corresponding to the identified textual feature of the input text data comprises identifying one or more textual features of the knowledge graph corresponding to the identified textual feature of the input text data, determining a semantic relationship between the one or more corresponding textual features of the knowledge graph and one or more other textural features of the knowledge graph, and identifying one or more other textual features of the knowledge graph which correspond to the one or more corresponding textual features of the knowledge graph.
  • This may allow for identification of a plurality of textual features of the knowledge graph which correspond to the identified textual features of the input text data.
  • this facilitates identification of natural-language descriptor labels of the corresponding textual features.
  • determining a semantic relationship between the one or more corresponding textual features of the knowledge graph and the one or more other textural features of the knowledge graph comprises, generating for each of the textual features a numerical vector representing a semantic of the textual feature, and computing a similarity between the numerical vectors.
  • Computing similarities between numerical vector representations advantageously allows for similarities between textual features of the knowledge graph to be inferred.
  • generating for each of the textual features a numerical vector representing a semantic of the textual feature comprises generating a numerical vector representing a context in which the textual feature is used in a text.
  • the text could comprise a plurality of sources of text, to increase the accuracy and/or precision of the encoded semantic.
  • generating a numerical vector representing a context in which the textual feature is used in a text comprises, generating a numerical vector for the textual feature and generating numerical vectors for one or more other textual features accompanying the textual feature in the text, computing a numerical vector representing an average of numerical vectors of the one or more other textual features accompanying the textual feature in the text, and computing a concatenation numerical vector representing a concatenation of the numerical vector of the textual feature and the average of numerical vectors of the one or more other textual features accompanying the textual feature in the text.
  • the method further comprises storing the concatenation numerical vector in the machine-readable memory linked to the respective textual feature of the knowledge graph.
  • the concatenation numerical vector representing the semantic of the textual feature, is pre-computed and stored in the knowledge graph. This may advantageously reduce latency during execution of the reason prediction task and reduce the computational resource required for execution of the reason prediction task.
  • the method further comprises computing a concatenation numerical vector representing a concatenation of a textual feature of the knowledge graph and an average of numerical vectors of textual features accompanying the textual feature in text for each textual feature in the knowledge graph.
  • the method may comprise generating an embedding for every textual feature of the knowledge graph. This may advantageously enable a full network of the textual features to be created.
  • the numerical vectors are generated using a transformer neural network architecture.
  • a further aspect of the present disclosure provides a computer program comprising instructions which, when executed by a computer, cause the computer to carry out the method of any one of the preceding statements.
  • a further aspect of the present disclosure provides a computer-readable data carrier having stored thereon the computer program of the immediately preceding statement.
  • a further aspect of the present disclosure provides a computer system configured to perform the method of any one of the preceding statements.
  • Figure 1 shows schematically an example of a computer embodying an aspect of the invention
  • Figures 2 and 3 show an overview of processes of a method of classifying input text data using a machine-learning classifier model run on the computer identified with reference to Figure 1 to generate one or more classification predictions for the input text data using a convolutional neural network and predict one or more reasons for the classification prediction using a graph convolutional neural network;
  • Figure 4 shows an overview of processes involved in predicting one or more reasons for the classification prediction using the graph convolutional neural network
  • FIG 5 shows an overview of processes involved in training the convolutional neural network identified previously with reference to Figures 2 and 3 for the classification task;
  • Figure 6 shows an overview of processes involved in generating a sparsely-labelled knowledge graph representation of textual features
  • Figure 7 shows schematically an overview of processes involved in generating embeddings for textural features of the knowledge graph
  • Figure 8 shows schematically a sparsely-labelled knowledge graph obtained by the processes identified previously with reference to Figure 6;
  • FIG 9 shows an overview of processes involved in training the graph convolutional neural network previously identified with reference to Figure 4.
  • Figure 10 shows an overview of processes involved in generating a classification prediction for input text data
  • Figure 11 shows an overview of processes involved in predicting one or more reasons for the classification prediction obtained in the processes identified previously with reference to Figure 10 using a graph convolutional neural network, which includes a step of predicting reasons for unlabelled textual features of the knowledge graph using the graph convolutional neural network; and
  • Figure 12 shows schematically an overview of process involved in predicting reasons for unlabelled textual features of the knowledge graph using the graph convolutional neural network.
  • a computer 101 embodying an aspect of the invention comprises central processing unit 102, flash memory 103, random-access memory 104, input/output interface 105, and system bus 106.
  • the computer 101 is configured to run a machine-learning text classification model, specifically, a neural network, for classification of input text data.
  • Central processing unit 102 is configured for execution of instructions of a computer program.
  • Flash memory 103 is configured for non-volatile storage of computer programs for execution by the central processing unit 102.
  • Random-access memory 104 is configured as read/write memory for storage of operational data associated with computer programs executed by the central processing unit 102.
  • Input/output interface 105 is provided for connection of external computing devices and/or other peripheral hardware to computer 101, to facilitate control of the computer 101 and inputting of input data.
  • the components 102 to 105 of the computer 101 are in communication via system bus 106.
  • the flash memory 103 has a computer program for classifying input text data stored thereon.
  • the computer program is operable on input text data to generate one or more classification predictions for characteristics of the input text data using a convolutional neural network model, and further to predict one or more reasons for the classification prediction(s) using a graph convolutional neural network model.
  • the computer program is configured for classification of input text data with respect to “offensive” and “not- offensive” classifications.
  • the computer 101 is then configured to output the classification prediction(s) and the reason prediction(s), for example, for display to a user of the computer via a display device connected to the input/output interface 105.
  • the method for classifying input text data performed by the computer program stored on flash memory 103 comprises seven stages.
  • the computer program causes the central processing unit 102 to perform initialisation and training processes.
  • the processes comprise: training a ‘text classification’ convolutional neural network model for the classification task of classifying input text data into the classifications of “offensive” and “not-offensive”; constructing a sparsely-labelled knowledge graph representation of a vocabulary of words in which a subset of words of the knowledge graph are labelled with natural-language descriptor labels defining a semantic meaning of the respective word; and training a ‘reason prediction’ graph convolutional neural network for predicting natural language descriptor labels for unlabelled words of the sparsely- labelled knowledge graph.
  • Stage 201 further comprises storing the trained neural network models and knowledge graph in the flash memory 103 of computer 101.
  • the computer program causes the central processing unit 102 to locate and load from the flash memory 103 the text classification convolutional neural network model trained at stage 201.
  • the computer program causes the central processing unit 102 to locate input text data for classification by the text classification convolutional neural network model. For example, this stage could involve the central processing unit 102 outputting, via a display device connected to input/output interface 105, a message to prompt a user to input text data for classification via the input/output interface 105.
  • stage 202 could involve the central processing unit 102 itself directly selecting and importing textual content for classification, for example, text posted by a user in an online discussion forum accessible by the central processing unit 102.
  • the computer program causes the central processing unit 102 to execute the text classification convolutional neural network model on the input text data received at stage 203, and generate one or more classification predictions for the input text data, e.g. that the input text data is ‘offensive’ or ‘not-offensive’.
  • the output of stage 203 could be probabilities of the input text data falling into each of the offensive/not-offensive classifications.
  • the computer program causes the central processing unit 102 to locate and load from flash memory 103 the reason prediction graph convolutional neural network model trained at stage 201.
  • the graph convolutional neural network model is trained for predicting reasons for classification predictions of the convolutional neural network model, i.e. for predicting reasons why input text data has been classified as offensive/not- offensive.
  • the computer program causes the central processing unit 102 to execute the graph convolutional neural network model on words of the input text data that are identified as important to the classification prediction(s) of the convolutional neural network model generated at stage 204, to generate predictions for the reason(s) for the classification prediction(s) of the first neural network model, e.g. “because word X is derogatory”, and/or “because word Y is an expletive”.
  • the computer program causes the central-processing unit 102 to output the classification prediction(s) obtained at stage 203 and the reason prediction obtained at stage 205.
  • this stage may involve the computer 101 outputting the classification prediction(s) and the reason prediction(s) via a display device connected to the input/output interface 105.
  • the initialisation and training processes of stage 201 are conducted immediately prior to the text classification processes of stages 202 to 204 and reason prediction processes of stages 205 to 207.
  • one or more of the initialization and training processes of stage 201 could be performed ahead of time.
  • the text classifier convolutional neural network model and reason prediction graph convolutional neural network could be trained, and the knowledge graph constructed, ahead of time, using computing devices external to the computer 101, and the pre-trained neural network models and the pre constructed knowledge graph could be uploaded onto flash memory 103 of computer 101 via input/output interface 105.
  • stage 201 for initialization and training comprises four stages.
  • the text classification convolutional neural network model is trained for the task of classifying input text data of classifying input text data into the classifications of “offensive” and “not-offensive”.
  • the sparsely-labelled knowledge graph representation of a vocabulary of words is constructed, to include a subset of words labelled with natural-language descriptor labels defining a semantic meaning of the respective word.
  • the reason prediction graph convolutional neural network is trained for the task of predicting natural language descriptor labels for unlabelled words of the sparsely-labelled knowledge graph.
  • the text classification convolutional neural network and graph convolutional neural network models trained at stages 401 and 403 respectively, parameters associated with the trained neural network models, and the knowledge graph constructed at stage 402, are stored in the flash memory 103 of computer 101.
  • stage 401 for training the text classification convolutional neural network model for the task of classifying input text data into the classifications of “offensive” and “not-offensive” comprises four stages.
  • a plurality of items of training text data labelled with respect to the offensive/not- offensive classification of interest is input into the computer 101 via the input/output interface 105.
  • a convolutional neural network model comprising plural successive feature extraction and classification layers, is executed by the central-processing unit 102 on each item of the training text data input at stage 501, and a classification prediction for the offensive/not- offensive classification of interest is generated for each item of training data.
  • the classification prediction generated at stage 502 for each item of the training text data is compared to the respective label of the item of training text data, and a loss function representative of an error in the classification prediction is computed.
  • the loss function obtained at stage 503 is back-propagated through the text classification convolutional neural network model, and the parameters of the model, such as the weights of the feature extraction and classification layers, are updated.
  • stage 402 for constructing the sparsely-labelled knowledge graph representation of a vocabulary of words comprises four stages.
  • a vocabulary of words is obtained.
  • an embedding e i.e. a low-dimensional vector encoding a semantic of the word.
  • the embedding e ( for each word W j is computed using Transformer architectures by crawling textual corpora containing the word, for example, Wikipedia (trade mark) and news articles.
  • the final embedding e ( stored is the concatenation of e w and e c ; where e w is the embedding for the word w ; , and e c is the average embedding of the context words around the word W j in the textual corpora.
  • the final embedding e thus defines a semantic meaning of the respective word.
  • the embeddings generated at stage 602 are used to determine semantic relationships, i.e. links between words of the vocabulary, to define a graph structure in which words of the vocabulary are represented by nodes of the graph, and semantic relationships between words by edges of the graph.
  • nodes (representing words) in the graph may be linked by semantic relationships such as “synonym”, “antonym”, “hypernym” and “hyponym”.
  • the knowledge graph thus defines semantic relationships between words of the vocabulary.
  • a subset of words of the vocabulary are labelled with natural-language descriptor labels o
  • the natural-language descriptor labels are human-generated descriptions of the semantic sentiment of the word, e.g. “this word is derogatory”.
  • a human-generated natural- language descriptor label may be particularly efficient in explaining clearly and succinctly to a human user why a classification prediction has been made, e.g. that a post has been classified as ‘offensive’ because “word X is derogatory”.
  • stage 403 for training the reason prediction graph convolutional neural network for predicting reason labels for unlabelled words of the knowledge graph comprises two stages.
  • the graph convolutional neural network comprises a plurality of successive convolutional layers.
  • the word embeddings for each node of the knowledge graph summarised as a n x s matrix W, where ‘n’ is the number of nodes in the knowledge graph and ‘s’ is the size of the word embeddings
  • the links in the graph structure summarised as an n x n adjacency matrix A, wherein ‘n’ is again the number of nodes in the knowledge graph
  • a matrix representation of O’ of reason labels o are input into the graph convolutional neural network model. Labels in O’ are available for the rows that have a correspondingly labelled node in the knowledge graph. If labels are missing for a node in the knowledge graph, the corresponding row in O’ has a correspondingly missing value.
  • the parameters of the graph convolutional neural network are updated using a stochastic gradient descent technique.
  • stage 204 for generating a classification prediction for the input text data comprises three stages.
  • encoding operations are applied to the input text data to generate a numerical vector representation of the text data for processing.
  • the numerical vector representations obtained at stage 1001 are passed through layers of convolutional feature extraction and classification operations to generate a classification prediction for the input text data with respect to the offensive/not-offensive classification of interest.
  • the classification prediction for the input text data obtained at stage 1002 is stored in random-access memory 104 of computer 101.
  • stage 206 for predicting reasons for the classification predictions of the text classification convolutional neural network model comprises six stages.
  • stage 1101 textual features, e.g. words, of the input text data that are relevant to the classification prediction generated at stage 204 are identified.
  • the identified textual features are compared to the sparsely-labelled knowledge graph obtained at stage 402 and corresponding, features of the knowledge graph are identified.
  • respective embeddings, e for the corresponding features of the knowledge graph obtained at stage 402 are identified and summarised as an n x s embedding matrix W, where ‘n’ is again the number of nodes in the graph and s is again the size of the word embeddings.
  • the graph convolutional neural network model takes as an input the n x s embedding matrix W along with the weighted n x n adjacency matrix A.
  • the GCN comprises multiple convolutional layers:
  • the function / is defined as: where: s is the RELU (Rectified Linear Unit) activation, introducing a non-linearity.
  • A A + 1, where I is the identity matrix added to ensure nodes own embeddings are also used, D is the diagonal node-degree matrix of A , to normalize the model from variance in node-connections.
  • V (/) is the weight of the I th layer of neural network.
  • the ‘r’ possible reasons may then be output to the user at stage 207, alongside the classification prediction for the input text data obtained at stage 204.
  • the user may thus be presented not only with a classification prediction for the input text data, e.g. a post in an online discussion forum, but also a list of possible reasons for the classification prediction, e.g. “because word X is derogatory”, and/or “because word Y is an expletive”.
  • the user may thus be assisted in better understanding and appreciating the classification prediction. Consequently, a user’s trust in the classification prediction, and decisions based thereon, may desirably be improved.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

Est ici divulgué un procédé de classification de données de texte d'entrée mettant en œuvre un classificateur d'apprentissage automatique. Le procédé comprend la réception de données de texte d'entrée, la réalisation d'opérations de classification de texte à l'aide du classificateur d'apprentissage automatique sur les données de texte d'entrée et la prédiction d'une classification pour les données de texte d'entrée, l'identification d'une caractéristique textuelle des données de texte d'entrée pertinente pour la prédiction de classification, la comparaison de la caractéristique textuelle identifiée des données de texte d'entrée à une représentation par graphe de connaissances de caractéristiques textuelles, une ou plusieurs caractéristiques textuelles du graphe de connaissances étant marquées par un descripteur de langage naturel de la caractéristique textuelle respective. Le procédé pourrait, par exemple, être utilisé pour modérer un contenu généré par l'utilisateur dans un forum de discussion en ligne pour éliminer les publications désagréables. L'utilisation d'une représentation par graphe de connaissances de caractéristiques textuelles, tels que des mots, permet avantageusement de définir les significations sémantiques respectives d'un grand ensemble de caractéristiques textuelles en utilisant uniquement des étiquettes sporadiques de descripteur de langage naturel par la définition de relations sémantiques entre caractéristiques textuelles dans le graphe de connaissances. L'étiquetage sporadique de caractéristiques textuelles dans une référence présente avantageusement un coût humain/de calcul moindre pour sa génération qu'un ensemble complet d'étiquettes, tout en facilitant de manière souhaitable l'explication des raisons pour une prédiction de classification, même si une raison pour la prédiction de classification concerne des caractéristiques textuelles non étiquetées du graphe de connaissances.
PCT/EP2020/062888 2020-05-08 2020-05-08 Explication de prédiction dans des classificateurs d'apprentissage automatique WO2021223882A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2020/062888 WO2021223882A1 (fr) 2020-05-08 2020-05-08 Explication de prédiction dans des classificateurs d'apprentissage automatique

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2020/062888 WO2021223882A1 (fr) 2020-05-08 2020-05-08 Explication de prédiction dans des classificateurs d'apprentissage automatique

Publications (1)

Publication Number Publication Date
WO2021223882A1 true WO2021223882A1 (fr) 2021-11-11

Family

ID=70681825

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2020/062888 WO2021223882A1 (fr) 2020-05-08 2020-05-08 Explication de prédiction dans des classificateurs d'apprentissage automatique

Country Status (1)

Country Link
WO (1) WO2021223882A1 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114036298A (zh) * 2021-11-17 2022-02-11 西安理工大学 一种基于图卷积神经网络与词向量的节点分类方法
CN115712734A (zh) * 2022-11-21 2023-02-24 之江实验室 一种基于元学习的稀疏知识图谱嵌入方法和装置
CN116339799A (zh) * 2023-04-06 2023-06-27 山景智能(北京)科技有限公司 一种智能化数据接口管理的方法、系统、终端设备及存储介质
CN117473431A (zh) * 2023-12-22 2024-01-30 青岛民航凯亚系统集成有限公司 一种基于知识图谱的机场数据分类分级方法及系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3462385A1 (fr) * 2017-09-28 2019-04-03 Siemens Aktiengesellschaft Sgcnn : réseau neuronal convolutionnel à graphe structural

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3462385A1 (fr) * 2017-09-28 2019-04-03 Siemens Aktiengesellschaft Sgcnn : réseau neuronal convolutionnel à graphe structural

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
GONG JIBING ET AL: "Hierarchical Graph Transformer-Based Deep Learning Model for Large-Scale Multi-Label Text Classification", IEEE ACCESS, IEEE, USA, vol. 8, 10 February 2020 (2020-02-10), pages 30885 - 30896, XP011772649, DOI: 10.1109/ACCESS.2020.2972751 *
JIE ZHOU ET AL: "Graph Neural Networks: A Review of Methods and Applications", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 20 December 2018 (2018-12-20), XP080994868 *
LU ZHIBIN ET AL: "VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification", 8 April 2020, LECTURE NOTES IN COMPUTER SCIENCE; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER BERLIN HEIDELBERG, BERLIN GERMANY, PAGE(S) 369 - 382, ISBN: 978-3-030-67069-6, ISSN: 0302-9743, XP047547106 *
MARCOS ZAMPIERI ET AL: "SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 19 March 2019 (2019-03-19), XP081162731 *
SEONGJUN YUN ET AL: "Graph Transformer Networks", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 November 2019 (2019-11-06), XP081592564 *
YAO LIANG ET AL: "Graph Convolutional Networks for Text Classification", 13 November 2018 (2018-11-13), XP055775123, Retrieved from the Internet <URL:https://arxiv.org/pdf/1809.05679.pdf> [retrieved on 20210211], DOI: 10.1609/aaai.v33i01.33017370 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114036298A (zh) * 2021-11-17 2022-02-11 西安理工大学 一种基于图卷积神经网络与词向量的节点分类方法
CN114036298B (zh) * 2021-11-17 2024-02-02 西安理工大学 一种基于图卷积神经网络与词向量的节点分类方法
CN115712734A (zh) * 2022-11-21 2023-02-24 之江实验室 一种基于元学习的稀疏知识图谱嵌入方法和装置
CN115712734B (zh) * 2022-11-21 2023-10-03 之江实验室 一种基于元学习的稀疏知识图谱嵌入方法和装置
CN116339799A (zh) * 2023-04-06 2023-06-27 山景智能(北京)科技有限公司 一种智能化数据接口管理的方法、系统、终端设备及存储介质
CN116339799B (zh) * 2023-04-06 2023-11-28 山景智能(北京)科技有限公司 一种智能化数据接口管理的方法、系统、终端设备及存储介质
CN117473431A (zh) * 2023-12-22 2024-01-30 青岛民航凯亚系统集成有限公司 一种基于知识图谱的机场数据分类分级方法及系统

Similar Documents

Publication Publication Date Title
CN110347835B (zh) 文本聚类方法、电子装置及存储介质
CN110162749B (zh) 信息提取方法、装置、计算机设备及计算机可读存储介质
CN108363790B (zh) 用于对评论进行评估的方法、装置、设备和存储介质
CN111241304B (zh) 基于深度学习的答案生成方法、电子装置及可读存储介质
WO2021223882A1 (fr) Explication de prédiction dans des classificateurs d&#39;apprentissage automatique
JP2020520492A (ja) 文書要約自動抽出方法、装置、コンピュータ機器及び記憶媒体
US20210035556A1 (en) Fine-tuning language models for supervised learning tasks via dataset preprocessing
US11727211B2 (en) Systems and methods for colearning custom syntactic expression types for suggesting next best correspondence in a communication environment
US10678769B2 (en) Artificial intelligence system and method for auto-naming customer tree nodes in a data structure
CN112667782A (zh) 一种文本分类方法、装置、设备及存储介质
Rathee et al. Sentiment analysis using machine learning techniques on Python
Ali et al. Genetic approach for Arabic part of speech tagging
CN112686049A (zh) 文本审核方法、装置、设备及存储介质
WO2014073206A1 (fr) Dispositif de traitement de données, et procédé pour le traitement de données
CN114385806A (zh) 一种基于深度学习的文本摘要方法及系统
CN111985243A (zh) 情感模型的训练方法、情感分析方法、装置及存储介质
Hossain et al. Text classification using convolution neural networks with fasttext embedding
CN113886601A (zh) 电子文本事件抽取方法、装置、设备及存储介质
CN116304748A (zh) 一种文本相似度计算方法、系统、设备及介质
CN113360654B (zh) 文本分类方法、装置、电子设备及可读存储介质
CN108875024B (zh) 文本分类方法、系统、可读存储介质及电子设备
Rizou et al. Multilingual name entity recognition and intent classification employing deep learning architectures
Lindén et al. Evaluating combinations of classification algorithms and paragraph vectors for news article classification
Acharya et al. Question Answering System using NLP and BERT
CN112036189A (zh) 一种金文语义识别方法和系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20725490

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20725490

Country of ref document: EP

Kind code of ref document: A1