Detecting and executing data re-ingestion to improve accuracy in a NLP system

摘要

In some NLP systems, queries are compared to different data sources stored in a corpus to provide an answer to the query. However, the best data sources for answering the query may not currently be contained within the corpus or the data sources in the corpus may contain stale data that provides an inaccurate answer. When receiving a query, the NLP system may evaluate the query to identify a data source that is likely to contain an answer to the query. If the data source is not currently contained within the corpus, the NLP system may ingest the data source. If the data source is already within the corpus, however, the NLP may determine a time-sensitivity value associated with at least some portion of the query. This value may then be used to determine whether the data source should be re-ingested—e.g., the information contained in the corpus is stale.

主权项

1. A system, comprising:
a computer processor; and a memory containing a program that, when executed on the computer processor, performs an operation comprising:
receiving first and second queries for processing by a natural language processing (NLP) system;identifying first and second data sources related to the first and second queries, respectively, by associating one or more elements of the first and second queries to the first and second data sources; andupon determining that the first related data source is not in a corpus of the NLP system, ingesting the first related data source into the corpus, wherein the corpus includes a data store comprising information from one or more data sources formatted and stored into one or more objects; andupon determining that the second related data source is in the corpus of the NLP system:
before searching the second related data source for at least one answer to the second query, determining a time-sensitivity value associated with the second query indicating a degree to which an accurate answer to the second query is dependent on a staleness of the second related data source, andupon determining that the time-sensitivity value satisfies a staleness threshold, re-ingesting the second related data source into the corpus.