Event clustering and classification with document embedding

A computer readable storage medium storing a program of instructions executable by a machine to perform a method of training a machine to learn to predict a label for data, the method performed by at least one hardware processor, the method comprising:

• receiving a document;
• creating clusters of words in the document based on cosine similarity of word embeddings of words in the document;
• responsive to determining that the document has a title, determining a cosine similarity between word embeddings of words in a cluster and word embeddings of words in the title and based on the determined cosine similarity, ranking the clusters;
• responsive to determining that the document has no title, ranking the clusters based on compactness of a cluster indicating how closely related the words in the cluster are and a semantic distance of the cluster from other clusters;
• selecting a top-k number of the ranked clusters;
• determining a document embedding as a weighted sum of word embeddings of words in the top-k number of ranked clusters,
• wherein the receiving, the creating, the ranking, the selecting, and the determining of the document embedding are performed for multiple documents;
• labeling each of the multiple documents;
• and
• training a machine learning algorithm based on the multiple documents that are labeled, wherein the training comprises separating the multiple documents as a training set and a test set, and generating a machine learning model that predicts a label for a given document based on the training set and the test set.

A system of training a machine to learn to predict a label for data, comprising:

• a storage device;
• and
• a hardware processor coupled to the storage device,
• the hardware processor operable to receive a document;
• the hardware processor further operable to create clusters of words in the document based on cosine similarity of word embeddings of words in the document;
• the hardware processor further operable to, responsive to determining that the document has a title, determine a cosine similarity between word embeddings of words in a cluster and word embeddings of words in the title and based on the determined cosine similarity, rank the clusters;
• the hardware processor further operable to, responsive to determining that the document has no title, rank the clusters based on compactness of a cluster indicating how closely related the words in the cluster are and a semantic distance of the cluster from other clusters;
• the hardware processor further operable to select a top-k number of the ranked clusters;
• the hardware processor further operable to determine a document embedding as a weighted sum of word embeddings of words in the top-k number of ranked clusters, wherein the hardware processor determines document embeddings for multiple documents and stores the multiple documents with document embeddings in the storage device;
• the hardware processor further operable to label each of the multiple documents;
• and
• the hardware processor further operable to generate a machine learning model that predicts a label for a given document by training the machine learning model based on the multiple documents separated into the training set and the test set.