Machine learning recollection as part of question answering using a corpus
AssigneeAdobe Inc.
InventorsJoseph D. Barrow, Darrell Jan Dykstra, Varun Manjunatha, Nedim Lipka
Life of this patent
Estimating the term…
Abstract
Machine learning recollection techniques are described as part of question answering using a corpus. Inputs are received identifying a search query and a corpus of search data that is to be searched based on the search query. The search query is decomposed to form a plurality of decomposed queries and retrieval search results are generated by searching the corpus of search data using one or more additional terms based on the decomposed queries. A search result is synthesized based on the retrieval search results using a text generation machine-learning model. The search result is presented for display in a user interface.
Claims20
A method comprising:
- receiving, by a processing device, inputs identifying a search query and a corpus of search data that is to be searched based on the search query;
- decomposing, by the processing device, the search query using a generative machine-learning model trained to form first generated text including a plurality of decomposed queries;
- synthesizing, by the processing device, a search result using the generative machine-learning model further trained to form second generated text based on a plurality of search results obtained from a search of the corpus of search data using a plurality of terms of the plurality of decomposed queries and one or more additional terms from a reformulation of the plurality of terms, the second generated text including readable text describing the search result and supported by citations to portions of the corpus of search data used as sources for the readable text;
- and
- presenting, by the processing device, the readable text describing the search result for display in a user interface including the citations to the portions of the corpus of search data used as the sources.
A system comprising:
- a search input module implemented by a processing device to receive inputs identifying a search query and a corpus of search data that is to be searched based on the search query;
- a query decomposition module implemented by the processing device to decompose the search query to form a plurality of decomposed queries into first generated text using a generative machine-learning model;
- a hypothesis search module implemented by the processing device to generate hypothesis results specifying one or more additional terms to be searched based on a reformulation that reorders a plurality of terms of the plurality of decomposed queries;
- a retrieval module implemented by the processing device to generate retrieval search results by searching the corpus of search data using the plurality of terms and the one or more additional terms based on the plurality of decomposed queries;
- a synthesis module implemented by the processing device to synthesize a search result into second generated text using the generative machine-learning model based on the retrieval search results, the second generated text including readable text supported by citations to portions of the corpus of search data used as sources for the readable text, and
- the search input module is further implemented by the processing device to present the readable text of the search result in a user interface that displays a portion of the corpus of search data used as a source for a portion of the readable text identified from a user selection in the user interface.
One-or-more computer-readable storage media storing instructions that, responsive to execution by a processing device, causes the processing device to perform operations including:
- receiving inputs defining a search query using text and one or more digital documents for inclusion as part of a corpus of search data;
- decomposing the search query to form a plurality of decomposed queries into first generated text using a generative machine-learning model;
- generating hypothesis results specifying one or more additional terms to be searched based on a reformulation that reorders a plurality of terms of the plurality of decomposed queries;
- generating retrieval search results by searching the corpus of search data using the plurality of terms and the one or more additional terms based on the plurality of decomposed queries;
- synthesizing a search result into second generated text using the generative machine-learning model based on the retrieval search results, the second generated text including readable text supported by citations to portions of the corpus of search data used as sources for the readable text;
- and
- presenting the readable text of the search result in a user interface that displays a portion of the corpus of search data used as a source for a portion of the readable text identified from a user selection in the user interface.
Dependencies are inferred from the claim text.