Embodiments herein describe creating a searchable catalog of composite actions for embroidery designs. The catalog can also store a design intent and the embroidery technique for each of the composite actions. The design intents and the embroidery techniques for the composite actions can be stored in a design intent hierarchy and an embroidery technique hierarchy which can then be compared to text in a search query to identify matches. These matches can then be used to identify composite actions that match the search query.

Systems, devices, media, and methods are presented for assembling a database for query generation. The database is assembled by receiving a query history log, the query history log including target queries and a mapping between each of the target queries and associated subqueries for each of the target queries, selecting one or more of the associated subqueries for a first target query based on a conditional probability exceeding a threshold for the associated subqueries of the first target query compared to the matching associated subqueries of the other target queries, and including the first target query and the selected one or more associated subqueries for the first target query in the in-memory data structure store for query generation.

Disclosed are various embodiments for navigating a taxonomy using search queries. An unstructured search query is parsed in order to identify one or more categories of a taxonomy of a collection of items. Each one of the one or more categories is associated with a confidence score. When the confidence score meets a threshold, a pool of items is selected from a respective one of the one or more categories. When no confidence score meets the threshold, the pool of items is selected from the collection of items.

Systems and methods of natural language processing in an environment with no existing corpus are disclosed. The method includes defining an input grammar specific to a chosen domain, the input grammar having a domain specific knowledge and general grammatical knowledge. Groups of tokens are identified within the input grammar having syntactic and semantic equivalence. The identified groups are assembled into hypernyms, wherein the hypernyms include a semantic output for each token in the hypernyms. A list of fields is then combined with the hypernyms for combination with the hypernyms. A corpus of possible combinations of hypernyms and fields is created. A data structure mapping each possible combination to a partial semantic output is generated and the data structure is saved for use in later processing.

A structured dictionary in a database is populated from unstructured text stored in a data repository. Dictionary text is retrieved from the data repository and a dictionary term and an associated dictionary definition are identified from the dictionary text. A database category is determined for the dictionary term from the associated dictionary definition. An indication of the dictionary term is stored in the structured dictionary in association with the database category.

A computer-implemented method, a computer system and a computer program product enhance user input to a conversational agent. The method includes identifying a word using a natural language processing algorithm. The word is in a query from a user to the conversational agent. The method also includes determining a set of keywords related to each of a plurality of intents associated with the conversational agent within a database. In addition, the method includes calculating a semantic similarity score between each determined set of keywords and the identified word. Lastly, the method includes displaying the identified word on a screen to the user when the identified word is not found in each determined set of keywords and when the semantic similarity score is above a threshold. The display includes a distinct indication of the identified word.

In general, in one aspect, the invention relates to a method for servicing requests. The method includes receiving, from a client system, a request comprising a query, where the query includes a first plurality of terms. The method further includes generating, using a thesaurus library, a related query including a second plurality of terms, where at least one term in the second plurality of terms is present in the first plurality of terms. The method further includes issuing the query to a content repository to obtain a first result, issuing the related query to the content repository to obtain a second result, processing the first result and the second result to generate a final result, and providing the final result to the client system.

A text containing a word is received by a computing device. The word is compared to inventory words in a sense inventory. The sense inventory comprises at least one inventory word and at least one concept corresponding to the at least one inventory word. Upon matching the word to an inventory word in the sense inventory, a concept for the word is identified by comparing each concept related to the inventory word to the word. The concept is assigned the word.

Technologies related to personal assistant context building are generally described. In some examples, network service communications, such as network traffic resulting from the use of mobile applications or “apps” on a mobile device, may be captured, parsed, and included in personal assistant context databases for use in configuring automated personal assistant user interaction operations. In some examples, parsing services may be provided to parse forwarded network service communications and generate converted data for inclusion in personal assistant context databases.

Embodiments provide a computer implemented method for generating a domain-specific thesaurus on a cognitive system, comprising: receiving data of the domain-specific corpus and a plurality of terms of interest from a user; splitting the data of the domain-specific corpus into a plurality of sentences using natural language processing techniques; for each term in the plurality of terms of interest, retrieving a plurality of candidate sentences containing a corresponding term, from the plurality of sentences; for each candidate sentence, providing a list of synonyms of the corresponding term, wherein the synonyms are contextual alternatives in the corresponding candidate sentence; for each term in the plurality of terms of interest, tracking a frequency of each synonym, and forming a frequency map including all the synonyms of a corresponding term and the frequency of each synonym; and generating a domain-specific thesaurus based on a combination of all the synonyms in the frequency map.