Abstract: Described herein are techniques for automatically updating (e.g., augmenting) the content of documents with additional content. Such documents may be generated automatically using a natural language generation (NLG) engine. In some embodiments, the techniques developed by the inventors are configured to update a document with text explaining what caused a certain event or set of events described in the document. The techniques developed by the inventors involve multiple acts. For example, the techniques may identify content of relevance to a document, may identify whether the content includes a text segments having a causal structure, and may separate the cause sub-segment from the cause-segment. The cause sub-segment, and optionally the effect sub-segment, may be used to update the document.

Abstract: Techniques for determining a degree to which a document can be generated using a natural language generation (NLG) system, the NLG system being configured to generate natural language text. The techniques include using at least one computer hardware processor to perform: obtaining a document including text segments; determining a degree to which at least some of the text segments can be generated using the NLG system; generating a report indicating the degree to which the at least some of the text segments can be generated using the NLG system; and outputting the report.

Abstract: Described herein are techniques for generating natural language text customized to linguistic preferences of a user. Customizing the generation of natural language text to the linguistic preference of a user can significantly improve the overall user experience. Some embodiments relate to techniques for learning the linguistic preferences of a user, and for assisting NLG systems to generate natural text that reflects more closely the linguistic preferences of the user. A linguistic preference learner can present different natural language options to a user, and can ask the user to select the option that or appears to reflect more closely the user's personal linguistic preferences. The Linguistic preference learner may determine, based on the user selection, information relating to what linguistic characteristics the user appears to prefer.

Abstract: Techniques for identifying vocabulary associated with semantic objects used for generating natural language text with a natural language generation (NLG) system, the semantic objects including a first semantic object having a first set of ordered attributes. The techniques include: obtaining text segments; identifying, from among the text segments and using at least one first machine learning classifier, groups of text segments corresponding to respective semantic objects in the plurality of semantic objects; identifying, from the groups of text segments and using at least one second machine learning classifier, a plurality of vocabularies for the plurality of semantic objects; and generating natural language text using the NLG system, the plurality of vocabularies, and the plurality of semantic objects; and outputting the generated natural language text.

Abstract: Methods and apparatus for summarizing a chatbot interaction with a user are provided. The method comprises using at least one computer hardware processor to perform generating an initial summary based, at least in part, on user data, receiving first input from the user during the chatbot interaction, processing the first input with a natural language processing engine, updating the initial summary based, at least in part, on an output of the processing by the natural language processing engine to generate an updated summary, wherein the updating is performed prior to completion of the chatbot interaction, and outputting a final summary of the chatbot interaction, wherein the final summary of the chatbot interaction is based, at least in part, on the updated summary.