A system and methods are disclosed for enabling users to attach a tag and highlight in a single action or activity to a select piece or portion of text in digital content (e.g., in a digital book or other content provided for viewing on an electronic device). In some implementations, the teacher may associate a tag with a particular text in the assignment, push the assignment embedding the tag to one or more students, and the tag becomes automatically visible to the one or more students through their highlight menu when they open up the assignment for completion. In some implementations, with this single activity, users may easily share tasks, comments etc., with ease. One or more other activities are also used among teachers and students to create and execute assignments with efficiency.

Systems and methods are disclosed herein for processing one or more document and/or hierarchal project. For example, a system is disclosed having memory storing the document as a data file comprising content data. The system also includes at least one processor coupled to the at least one memory and configured to designate a portion of the content data as micro content; receive user input providing a phrase; and generate a phrase map configured to associate the phrase with the designated micro content and store the phrase map as phrase map data, the phrase map data comprising at least the phrase associated with a reference indicative of the associated micro content.

Systems and methods are disclosed herein for processing one or more document and/or hierarchal project. For example, a system is disclosed having memory storing the document as a data file comprising content data. The system also includes at least one processor coupled to the at least one memory and configured to designate a portion of the content data as micro content; receive user input providing a phrase; and generate a phrase map configured to associate the phrase with the designated micro content and store the phrase map as phrase map data, the phrase map data comprising at least the phrase associated with a reference indicative of the associated micro content.

Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products that enable performing format-dynamic string processing in a group-based communication system.

Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products that enable performing format-dynamic string processing in a group-based communication system.

The disclosure herein describes determining topics of communication transcripts using trained summarization models. A first communication transcript associated with a first communication is obtained and divided into a first set of communication segments. A first set of topic descriptions is generated based on the first set of communication segments by analyzing each communication segment of the first set of communication segments with a generative language model. A summarization model is trained using the first set of communication segments and associated first set of topic descriptions as training data. The trained summarization model is then applied to a second communication transcript and, based on applying the trained summarization model to the second communication transcript, a second set of topic descriptions of the second communication transcript is generated. By training the summarization model based on output of the generative language model, it enables efficient, accurate generation of topic descriptions from communication transcripts.

The disclosure herein describes determining topics of communication transcripts using trained summarization models. A first communication transcript associated with a first communication is obtained and divided into a first set of communication segments. A first set of topic descriptions is generated based on the first set of communication segments by analyzing each communication segment of the first set of communication segments with a generative language model. A summarization model is trained using the first set of communication segments and associated first set of topic descriptions as training data. The trained summarization model is then applied to a second communication transcript and, based on applying the trained summarization model to the second communication transcript, a second set of topic descriptions of the second communication transcript is generated. By training the summarization model based on output of the generative language model, it enables efficient, accurate generation of topic descriptions from communication transcripts.

Apparatus and methods for using artificial intelligence to process and remediate test failures are provided. The methods may include monitoring an execution of an automated test on a software application. The automated test may include a plurality of steps. The methods may include receiving a first error message and a second error message during the execution of a step included in the plurality of steps. The methods may include processing each of the first and second error messages individually and, after completion of the step, again as a group. The processing may include determining if the error messages were generated by a defect in the software application.

Apparatus and methods for using artificial intelligence to process and remediate test failures are provided. The methods may include monitoring an execution of an automated test on a software application. The automated test may include a plurality of steps. The methods may include receiving a first error message and a second error message during the execution of a step included in the plurality of steps. The methods may include processing each of the first and second error messages individually and, after completion of the step, again as a group. The processing may include determining if the error messages were generated by a defect in the software application.

Methods and systems for performing named entity recognition are disclosed. One method includes using a multi-task approach to fine-tune a neural network to perform named entity recognition. A multi-task objective function can include a combination of a triplet loss and a named entity recognition loss. The triplet loss can include the use of supplementary texts. The method further includes using the fine-tuned neural network to identify one or more named entities in a text. Aspects of the disclosure also include integrating named entity recognition with one or more other natural language processing tasks.