An entity resolution system performs a method of resolving one or more candidate entities based on a data set. The entity resolution system has a rules-based module, a machine learning module, a narrative module, and an evaluation module. The rules-based module compares the first entity features to the second entity features and determines whether a rule identifies a relationship between the first entity and the second entity. The machine learning module rates a similarity of the first entity features and the second entity features. The narrative module generates a narrative output based on one or more of the rules-based module and the machine learning module, the narrative output stating an identified relationship between the first entity and the second entity. The evaluation module determines one or more metrics to apply feedback to the system.

A client computing device receives a behavior model corresponding to a user group associated with a user. The behavior model has been trained with monitored user interactions of one or more files associated with the user group. The client computing device further mounts a snapshot of a file and determines, based on the behavior model, which files of the mounted snapshot to transfer to a locally accessible cache. During use of the client computing device, the client computing device may determine whether the mounted snapshot is accessible. If the mounted snapshot is not accessible, the client computing device may selectively delete, based on the behavior model, one or more of the files stored in the locally accessible cache. If the mounted snapshot is accessible, the client computing device may update the one or more files of the locally accessible cache with monitored user interactions with the mounted snapshot.

A system may determine information in relation to a link in an interlinked set of information content items. A memory may store a set of machine-readable instructions operable, when executed by a processor, to receive a link context associated with a link in an information content item of the interlinked set. The link context may include information from the information content item providing context for the link. Instructions may also be operable to identify one or more additional links present in the link context and determine a link density as the proportion of the link context which includes the or each additional link relative to the size of the link context, and/or determine a text density as the proportion of the link context which does not include the or each additional link relative to the size of the link context and/or count the or each additional link.

The present teaching relates to methods, systems, and programming for information retrieval. A search result associated with a search query is obtained and provided to a user. Upon receiving a filtering request from the user, the search result is filtered based on the filtering request to generate an updated search result. The updated search result is provided to the user in response to the filtering request.

In response to running at least one testing phrase on a previously trained text classifier and identifying a separate predicted classification label based on a score calculated for each respective at least one testing phrase, a text classifier decomposes extracted features summed in the score into word-level scores for each word in the at least one testing phrase. The text classifier assigns a separate heatmap value to each of the word-level scores, each respective separate heatmap value reflecting a weight of each word-level score. The text classifier outputs the separate predicted classification label and each separate heatmap value reflecting the weight of each word-level score for defining a heatmap identifying the contribution of each word in the at least one testing phrase to the separate predicted classification label for facilitating client evaluation of text classification anomalies.

Aspects of the disclosure relate to using a machine learning system to process a corpus of documents associated with a user to determine a user-specific consequence index. A computing platform may load a corpus of documents associated with a user. Subsequently, the computing platform may create a first plurality of smart groups based on the corpus of documents, and then may generate a first user interface comprising a representation of the first plurality of smart groups. Next, the computing platform may receive user input applying one or more labels to a plurality of documents associated with at least one smart group. Subsequently, the computing platform may create a second plurality of smart groups based on the corpus of documents and the received user input. Then, the computing platform may generate a second user interface comprising a representation of the second plurality of smart groups.

A system for classifying a language sample intent by receiving a language sample including a set of features, identifying language sample features, determining a tokenization score for the language sample according to the language sample features, eliminating duplicate features according to the tokenization score, determining a term frequency (tf) according to the identified features and the tokenization score, determining an inverse document frequency (idf) according to the identified features and the tokenization score, and generating a term frequency-inverse document frequency (tf-idf) matrix for the identified features.

Categorical data transformation and clustering techniques and systems are described for machine learning using natural language processing. These techniques and systems are configured to improve operation of a computing device to support efficient and accurate use of categorical data, which is not possible using conventional techniques. In an example, categorical data is received by a computing device that includes a categorical variable having a non-numerical data type for a number of classes. The categorical data is then converted into numerical data using natural language processing. Data is then generated by the computing device that includes a plurality of latent classes. This is performed by clustering the numerical data into a number of clusters that is smaller than the number of classes in the categorical data.

Methods and systems are disclosed herein for using artificial intelligence to determine which standardized text description an adverse event reported by a patient may match with. Artificial intelligence/machine learning may be used to determine matches between standardized text descriptions of adverse events and other text descriptions of adverse events (e.g., text descriptions input by patients that have taken a drug). Techniques described herein may improve the functioning of a computing system by allowing it to perform an action that it otherwise could not perform (e.g., determining a standardized text description for an adverse event experienced by a patient).

At least one social media channel includes a plurality of user messages, which are accessible via a communication network. At least some of the stored messages are retrieved from the at least one social media channel via the communication network, and a collection of frequently asked questions (FAQ) is generated or updated by analyzing the retrieved messages to form a plurality of topical issue clusters. Each topical issue cluster is associated with at least one topic parameter from among a plurality of topic parameters, each topic parameter relates to at least one of use, installation or maintenance of a product or service, and each topical issue cluster includes at least one issue identified by a community of users and at least one resolution of the issue identified by the community of users. The generated or updated FAQ is uploaded to a storage location accessible to the community of users.