US 12,086,172 B2
Determining named entities associated with aspect terms extracted from documents having unstructured text data
Ramakanth Kanagovi, Bengaluru (IN); Shrikrishna K. Joisa, Bengaluru (IN); Sandeep Ratnakar, Bengaluru (IN); Arun Swamy, Bengaluru (IN); Sumant Sahoo, Bengaluru (IN); Prakash Sridharan, Bengaluru (IN); and Ravi Shukla, Bengaluru (IN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Oct. 13, 2021, as Appl. No. 17/500,044.
Prior Publication US 2023/0116515 A1, Apr. 13, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/00 (2019.01); G06F 16/34 (2019.01); G06F 16/35 (2019.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01); G06N 3/045 (2023.01)
CPC G06F 16/345 (2019.01) [G06F 16/353 (2019.01); G06F 40/284 (2020.01); G06F 40/295 (2020.01); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to perform steps of:
receiving a query to determine associations between named entities and aspect terms for a document, the document comprising unstructured text data;
generating, utilizing a first machine learning model, a first set of encodings of the unstructured text data of the document, the first set of encodings classifying each word of the unstructured text data of the document as being an aspect term or a non-aspect term;
generating, utilizing a second machine learning model, a second set of encodings of the unstructured text data of the document, the second set of encodings classifying associations of each word of the unstructured text data of the document;
determining, for a given aspect term corresponding to a given sequence of one or more of the words of the unstructured text data of the document classified as an aspect term in the first set of encodings, attention weights for a given subset of words in the unstructured text data surrounding the given sequence of the one or more words;
generating, utilizing a third machine learning model, predictions of association between the given aspect term and one or more named entities recognized in the given subset of the words in the unstructured text data surrounding the given sequence of the one or more words, the third machine learning model generating the predictions based at least in part on (i) the attention weights for the given subset of the words in the unstructured text data surrounding the given sequence of the one or more words and (ii) a given portion of the second set of encodings classifying the associations of the given subset of the words in the unstructured text data surrounding the given sequence of the one or more words; and
providing a response to the query, the response to the query comprising at least one of the predicted associations between the given aspect term and the one or more named entities;
wherein the third machine learning model comprises a multi-level feed forward neural network classifier.