IP Library › Granted Patent US 12,406,136
Granted Patent B2
US 12,406,136 · App. 18/052,697 · Granted Sep 2, 2025

Method and system for determining relationships between linguistic entities

Inventors: Bharathwaj Raghunathan (Mississauga, CA); Vishal Jain (Toronto, CA); Tyler Wagner (Boston, MA); Tyler Feener (Toronto, CA); Shimeng Chen (Toronto, CA); Eric Brine (Toronto, CA); Lorenzo Kogler Anele (Toronto, CA); Danylo Oliynyk (Toronto, CA); Rashik Shahjahan (Toronto, CA)
Assignee: nference, Inc.
G06F40/205G06F40/289G06F40/30
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,406,136
App. No.
18/052,697
Granted
Sep 2, 2025
Kind
B2
Abstract

Disclosed herein are methods for identifying and classifying relationships between entities. A method of identifying relationships includes receiving a first entity and a second entity; accessing a corpus; retrieving a plurality of sentences containing the first entity and the second entity from the corpus; identifying a plurality of relational phrases by extracting a relational phrase from each of the plurality of sentences; and identifying one or more relationships between the first entity and the second entity. A method of classifying relationships includes using a classification model.

Claims (187)

1. A method comprising

receiving, by a computing device, a first entity and a second entity;

accessing a corpus;

preprocessing, by the computing device, the corpus by:

grouping the corpus into a plurality of chunks at a head node;

distributing the plurality of chunks to a plurality of worker nodes configured as parallel processing units within a distributed cluster, wherein each worker node is executed on a separate physical or virtual machine and operates asynchronously;

retrieving a second plurality of sentences from one of the plurality of chunks of the corpus by one of the plurality of worker nodes;

extracting then sending a plurality of extracted entities and extracted relational phrases to the head node;

mapping the extracted relational phrases in a pretrained vector space using a pretrained

model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings;

retrieving, by the computing device, a first plurality of sentences containing the first entity and the second entity from the corpus;

identifying, by the computing device, a plurality of relational phrases by extracting a relational phrase from each of the first plurality of sentences; and

identifying, by the computing device, one or more relationships between the first entity and the second entity.

2. The method of claim 1 , wherein extracting the relational phrase from each of the first plurality of sentences comprises using a dependency parser to identify the relational phrase.

3. The method of claim 1 , wherein extracting the relational phrase from each of the first plurality of sentences comprises using a constituency parser to identify the relational phrases.

4. The method of claim 1 , further comprising

mapping each relational phrase in a pretrained vector space using a pretrained model; and

clustering the plurality of relational phrases in the pretrained vector space.

5. The method of claim 4 , wherein the pretrained model is trained using a supervised model.

6. The method of claim 4 , wherein the pretrained model is trained using a self- supervised model.

7. The method of claim 4 , wherein clustering the plurality of relational phrases in the pretrained vector space comprises

setting a threshold cosine distance;

calculating a cosine distance between each of pair of the plurality of relational phrases in the pretrained vector space;

clustering the plurality of relational phrases such that each pair of relational phrases whose cosine distance is within the threshold cosine distance share a cluster.

8. The method of claim 4 , wherein identifying one or more relationships between the first entity and the second entity is based on clustering the plurality of relational phrases in the pretrained vector space.

9. The method of claim 4 , further comprising providing a robustness score for each of the one or more relationships based on clustering of the plurality of relational phrases.

10. The method of claim 9 , wherein the robustness score is based on a cosine distance between the relational phrases in the pretrained vector space.

11. The method of claim 4 , further comprising ranking the one or more relationships based on clustering of the plurality of relational phrases.

12. The method of claim 1 , further comprising classifying the one or more relationships using a classification model.

13. The method of claim 12 , further comprising training the classification model on the corpus using example labels, wherein each example label comprises an entity pair and a class.

14. The method of claim 13 , wherein the example labels are generated by a human.

15. The method of claim 13 , wherein the example labels are generated by a supervised model.

16. The method of claim 13 , wherein training the classification model comprises receiving the example labels; and for each example label:

retrieving a plurality of training sentences containing the entity pairs from the corpus;

identifying a plurality of classification relational phrases by extracting a

relational phrase from each of the plurality of training sentences; and labeling the plurality of classification relational phrases with the class corresponding to the entity pair;

mapping the plurality of labeled classification relational phrases for each example label in the pretrained vector space using the pretrained model;

clustering the plurality of labeled classification relational phrases in the pretrained vector space.

17. The method of claim 12 , wherein the classification model comprises a plurality of classification relational phrases identified during training.

18. The method of claim 17 , further comprising mapping the plurality of relational phrases in the pretrained vector space;

clustering the relational phrases and the plurality of classification relational phrases in the pretrained vector space; and

assigning a label to each relational phrase based on the clustering of the plurality of relational phrases and the plurality of classification relational phrases in the pretrained vector space; and

assigning a classification to each of the one or more relationships between the first entity and the second entity.

19. The method of claim 18 , wherein assigning the label to each relational phrase comprises

calculating a cosine distance between each relational phrase and each classification relational phrase in the pretrained vector space;

identifying a plurality of closest classification relational phrases for each relational phrase; and

assigning each relational phrase a label corresponding to that of the closest classification relational phrases.

20. The method of claim 18 , further comprising assigning a confidence score to the classification.

21. The method of claim 20 , wherein assigning the confidence score comprises calculating a cosine distance between each relational phrase and each classification relational phrase in the pretrained vector space;

identifying a plurality of closest classification relational phrases for each relational phrase; and

calculating an average cosine distance between each relational phrase and the closest classification relational phrases.

22. The method of claim 1 , wherein the corpus comprises a preprocessed corpus comprising a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings.

23. The method of claim 1 , further comprising preprocessing the corpus by retrieving a second plurality of sentences from the corpus;

extracting a plurality of entities from each of the second plurality of sentences;

extracting a relational phrase for each pair of extracted entities;

mapping the extracted relational phrases in a pretrained vector space using a pretrained model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings.

24. The method of claim 1 , further comprising

accessing a preprocessed corpus, wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities; and

identifying the first plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre-extracted relational phrase embeddings for each of the first plurality of sentences.

25. The method of claim 1 , further comprising

sending the first entity and the second entity to each of a plurality of worker nodes;

accessing a portion of a preprocessed corpus by one of the plurality of worker nodes,

wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities by one of the plurality of worker nodes;

identifying the plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre-extracted relational phrase embeddings for each of the first plurality of sentences by one of the plurality of worker nodes;

sending the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences to the head node by one of the plurality of worker nodes;

wherein the head node is configured to perform the operation of merging the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences from each of the plurality of worker nodes to identify the one or more relationships.

26. The method of claim 24 , further comprising classifying the one or more relationships using a classification model.

27. A system comprising:

a non-transitory memory; and

one or more hardware processors configured to read instructions from the non-transitory memory that, when executed cause one or more of the hardware processors to perform operations comprising:

receiving a first entity and a second entity;

accessing a corpus;

preprocessing the corpus by:

grouping the corpus into a plurality of chunks at a head node;

distributing the plurality of chunks to a plurality of worker nodes configured as parallel processing units within a distributed cluster, wherein each worker node is executed on a separate physical or virtual machine and operates asynchronously;

retrieving a second plurality of sentences from one of the plurality of chunks of the corpus by one of the plurality of worker nodes;

extracting then sending a plurality of extracted entities and extracted relational phrases to the head node;

mapping the extracted relational phrases in a pretrained vector space using a pretrained

model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings;

retrieving a first plurality of sentences containing the first entity and the second entity from the corpus;

identifying a plurality of relational phrases by extracting a relational phrase from each of the first plurality of sentences; and

identifying one or more relationships between the first entity and the second entity.

28. The system of claim 27 , wherein extracting the relational phrase from each of the first plurality of sentences comprises using a dependency parser or a constituency parser to identify the relational phrase.

29. The system of claim 27 , wherein the operations further comprise mapping each relational phrase in a pretrained vector space using a pretrained model; and

clustering the plurality of relational phrases in the pretrained vector space.

30. The system of claim 29 , wherein the operations further comprise ranking the one or more relationships based on clustering of the plurality of relational phrases.

31. The system of claim 27 , wherein the operations further comprise classifying the one or more relationships using a classification model; and

training the classification model on the corpus using example labels, wherein each example label comprises an entity pair and a class, wherein training the classification model comprises

receiving example labels; and for each example label:

retrieving a plurality of training sentences containing the entity pairs from the corpus;

identifying a plurality of classification relational phrases by extracting a relational phrase from each of the plurality of training sentences; and

labeling the plurality of classification relational phrases with the class corresponding to the entity pair;

mapping the plurality of labeled classification relational phrases for each example label in the pretrained vector space using the pretrained model;

clustering the plurality of labeled classification relational phrases in the pretrained vector space.

32. The system of claim 31 , wherein the operations further comprise mapping the plurality of relational phrases in the pretrained vector space;

clustering the relational phrases and a plurality of classification relational phrases identified in training in the pretrained vector space; and

assigning a label to each relational phrase based on the clustering of the plurality of relational phrases and the plurality of classification relational phrases in the pretrained vector space; and

assigning a classification to each of the one or more relationships between the first entity and the second entity.

33. The system of claim 32 , wherein the operations further comprise assigning a confidence score to the classification.

34. The system of claim 27 , wherein the operations further comprise preprocessing the corpus by retrieving a second plurality of sentences from the corpus;

extracting a plurality of entities from each of the second plurality of sentences;

extracting a relational phrase for each pair of extracted entities;

mapping the extracted relational phrases in a pretrained vector space using a pretrained model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings.

35. The system of claim 27 , wherein the operations further comprise

accessing a preprocessed corpus, wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities; and

identifying the first plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre- extracted relational phrase embeddings for each of the first plurality of sentences.

36. The system of claim 28 , wherein the operations further comprise sending the first entity and the second entity to each of a plurality of worker nodes;

accessing a portion of a preprocessed corpus by one of the plurality of worker nodes,

wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a

plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities by one of the plurality of worker nodes;

identifying the plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre-extracted relational phrase embeddings for each of the first plurality of sentences by one of the plurality of worker nodes;

sending the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences to the head node by one of the plurality of worker nodes;

wherein the head node is configured to perform the operation of merging the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences from each of the plurality of worker nodes to identify the one or more relationships.

37. A non-transitory computer-readable medium storing instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to perform operations comprising:

receiving a first entity and a second entity;

accessing a corpus;

preprocessing the corpus by:

grouping the corpus into a plurality of chunks at a head node;

distributing the plurality of chunks to a plurality of worker nodes configured as parallel processing units within a distributed cluster, wherein each worker node is executed on a separate physical or virtual machine and operates asynchronously;

retrieving a second plurality of sentences from one of the plurality of chunks of the corpus by one of the plurality of worker nodes;

extracting then sending a plurality of extracted entities and extracted relational phrases to the head node;

mapping the extracted relational phrases in a pretrained vector space using a pretrained

model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings;

retrieving a first plurality of sentences containing the first entity and the second entity from the corpus;

identifying a plurality of relational phrases by extracting a relational phrase from each of the first plurality of sentences; and

identifying one or more relationships between the first entity and the second entity.

38. The non-transitory computer-readable medium of claim 37 , wherein extracting the relational phrase from each of the first plurality of sentences comprises using a dependency parser or a constituency parser to identify the relational phrase.

39. The non-transitory computer-readable medium of claim 37 , wherein the operations further comprise

mapping each relational phrase in a pretrained vector space using a pretrained model; and

clustering the plurality of relational phrases in the pretrained vector space.

40. The non-transitory computer-readable medium of claim 39 , wherein the operations further comprise ranking the one or more relationships based on clustering of the plurality of relational phrases.

41. The non-transitory computer-readable medium of claim 37 , wherein the operations further comprise

classifying the one or more relationships using a classification model; and training the classification model on the corpus using example labels, wherein each

example label comprises an entity pair and a class, wherein training the classification model comprises

receiving example labels; and for each example label:

retrieving a plurality of training sentences containing the entity pairs from the corpus;

identifying a plurality of classification relational phrases by extracting a

relational phrase from each of the plurality of training sentences; and labeling the plurality of classification relational phrases with the class corresponding to the entity pair;

mapping the plurality of labeled classification relational phrases for each example label in the pretrained vector space using the pretrained model;

clustering the plurality of labeled classification relational phrases in the pretrained vector space.

42. The non-transitory computer-readable medium of claim 41 , wherein the operations further comprise

mapping the plurality of relational phrases in the pretrained vector space; clustering the

relational phrases and a plurality of classification relational phrases identified in training in the pretrained vector space; and

assigning a label to each relational phrase based on the clustering of the plurality of relational phrases and the plurality of classification relational phrases in the pretrained vector space; and

assigning a classification to each of the one or more relationships between the first entity and the second entity.

43. The non-transitory computer-readable medium of claim 42 , wherein the operations further comprise assigning a confidence score to the classification.

44. The non-transitory computer-readable medium of claim 37 , wherein the operations further comprise preprocessing the corpus by retrieving a second plurality of sentences from the corpus;

extracting a plurality of entities from each of the second plurality of sentences;

extracting a relational phrase for each pair of extracted entities;

mapping the extracted relational phrases in a pretrained vector space using a pretrained model to generate a plurality of extracted relational phrase embeddings;

clustering the extracted relational phrases in the pretrained vector space to generate clustering information for the plurality of extracted relational phrase embeddings; and

storing a mapping of the plurality of extracted entities, the plurality of extracted relational phrase embeddings, and the clustering information for the plurality of extracted relational phrase embeddings.

45. The non-transitory computer-readable medium of claim 39 , wherein the operations further comprise

accessing a preprocessed corpus, wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities; and

identifying the first plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre-extracted relational phrase embeddings for each of the first plurality of sentences.

46. The non-transitory computer-readable medium of claim 39 , wherein the operations further comprise

sending the first entity and the second entity to each of a plurality of worker nodes;

accessing a portion of a preprocessed corpus by one of the plurality of worker nodes,

wherein the preprocessed corpus comprises a mapping of a plurality of pre-extracted entities, a plurality of pre-extracted relational phrase embeddings, and clustering information for the plurality of pre-extracted relational phrase embeddings;

retrieving the first plurality of sentences containing the first entity and the second entity from the corpus using the mapping of the plurality of pre-extracted entities by one of the plurality of worker nodes;

identifying the plurality of relational phrases by using the pre-extracted relational phrase embeddings and the clustering information for the plurality of pre-extracted relational phrase embeddings for each of the first plurality of sentences by one of the plurality of worker nodes;

sending the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences to the head node by one of the plurality of worker nodes;

wherein the head node is configured to perform the operation of merging the first plurality of sentences and the pre-extracted relational phrase embeddings and clustering information for the pre-extracted relational phrase embeddings for each of the first plurality of sentences from each of the plurality of worker nodes to identify the one or more relationships.

47. The method of claim 1 , wherein preprocessing the corpus further comprises:

executing, at each worker node, a model configured to extract a plurality of entities from each sentence of the second plurality of sentences by splitting the sentences into a list of entities while maintaining sentence boundaries using a sentence tokenizer, wherein the extracted entities are stored in an index mapping entities to sentences in which they occur;

executing, at each worker node, a model trained to extract a relational phrase for each pair of extracted entities by creating a constituency tree for each tokenized sentence, wherein the constituency tree is parsed to identify a hierarchy of phrases.

48. The system of claim 27 , wherein preprocessing the corpus further comprises:

executing, at each worker node, a model configured to extract a plurality of entities from each sentence of the second plurality of sentences by splitting the sentences into a list of entities while maintaining sentence boundaries using a sentence tokenizer, wherein the extracted entities are stored in an index mapping entities to sentences in which they occur;

executing, at each worker node, a model trained to extract a relational phrase for each pair of extracted entities by creating a constituency tree for each tokenized sentence, wherein the constituency tree is parsed to identify a hierarchy of phrases.

49. The non-transitory computer-readable medium of claim 37 , wherein preprocessing the corpus further comprises:

executing, at each worker node, a model configured to extract a plurality of entities from each sentence of the second plurality of sentences by splitting the sentences into a list of entities while maintaining sentence boundaries using a sentence tokenizer, wherein the extracted entities are stored in an index mapping entities to sentences in which they occur;

executing, at each worker node, a model trained to extract a relational phrase for each pair of extracted entities by creating a constituency tree for each tokenized sentence, wherein the constituency tree is parsed to identify a hierarchy of phrases.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2023
From: RAGHUNATHAN, BHARATHWAJ; JAIN, VISHAL; WAGNER, TYLER; FEENER, TYLER; CHEN, SHIMENG; BRINE, ERIC; ANELE, LORENZO KOGLER; OLIYNYK, DANYLO; SHAHJAHAN, RASHIK
To: NFERENCE, INC.
Reel/Frame 062722/0085 →
Continuity (2)
Provisional Application 63276342 · Nov 5, 2021
Related Publication 20230143418A1 · May 11, 2023
References Cited (94)
US 7003442B1 · Tsuda · 2006 [cited by applicant]
US 7464043B1 · Dussia · 2008 [cited by applicant]
US 8601361B2 · Berger et al. · 2013 [cited by applicant]
US 8943126B1 · Feldman · 2015 [cited by applicant]
US 9088532B1 · Dorsey et al. · 2015 [cited by applicant]
US 9183203B1 · Tuchman et al. · 2015 [cited by applicant]
US 9514405B2 · Chen et al. · 2016 [cited by applicant]
US 9734181B2 · Wang et al. · 2017 [cited by applicant]
US 10360507B2 · Aravamudan et al. · 2019 [cited by applicant]
US 20020052901A1 · Guo et al. · 2002 [cited by applicant]
US 20040013302A1 · Ma et al. · 2004 [cited by applicant]
US 20040220925A1 · Liu et al. · 2004 [cited by applicant]
US 20060122976A1 · Baluja et al. · 2006 [cited by applicant]
US 20070073690A1 · Boal et al. · 2007 [cited by applicant]
US 20070118506A1 · Kao et al. · 2007 [cited by applicant]
US 20080243825A1 · Staddon et al. · 2008 [cited by applicant]
US 20090116736A1 · Neogi et al. · 2009 [cited by applicant]
US 20110137921A1 · Inagaki · 2011 [cited by applicant]
US 20110255788A1 · Duggan et al. · 2011 [cited by applicant]
US 20120079372A1 · Kandekar · 2012 [cited by examiner]
US 20120204104A1 · Walsh · 2012 [cited by applicant]
US 20120254188A1 · Koperski et al. · 2012 [cited by applicant]
US 20120323590A1 · Udani · 2012 [cited by applicant]
US 20130132331A1 · Kowalczyk et al. · 2013 [cited by applicant]
US 20140080428A1 · Rhoads et al. · 2014 [cited by applicant]
US 20150112664A1 · Srinivasan · 2015 [cited by applicant]
US 20150254555A1 · Williams, Jr. et al. · 2015 [cited by applicant]
US 20150310115A1 · Ryger et al. · 2015 [cited by applicant]
US 20160378808A1 · Hopcroft et al. · 2016 [cited by applicant]
US 20180268023A1 · Korpusik · 2018 [cited by applicant]
US 20180336183A1 · Lee · 2018 [cited by examiner]
US 20190005049A1 · Mittal · 2019 [cited by applicant]
US 20190130024A1 · Burchfield et al. · 2019 [cited by applicant]
US 20190354544A1 · Hertz · 2019 [cited by examiner]
US 20190354883A1 · Aravamudan et al. · 2019 [cited by applicant]
US 20190370337A1 · Lee · 2019 [cited by examiner]
US 20200184278A1 · Zadeh et al. · 2020 [cited by applicant]
US 20200380202A1 · Cass et al. · 2020 [cited by applicant]
US 20210019287A1 · Prasad et al. · 2021 [cited by applicant]
US 20210073225A1 · Nelson et al. · 2021 [cited by applicant]
US 20210117509A1 · Aditya · 2021 [cited by examiner]
US 20210191925A1 · Sianez · 2021 [cited by applicant]
US 20210218570A1 · Manasse et al. · 2021 [cited by applicant]
US 20210224264A1 · Barve · 2021 [cited by examiner]
US 20220019907A1 · Georgopoulos · 2022 [cited by examiner]
CN 101976170 · 2016 [cited by applicant]
JP 2019536178A · 2019 [cited by applicant]
WO WO2018057945 · 2018 [cited by applicant]
WO WO2021011776 · 2021 [cited by applicant]
WO WO2021146694A1 · 2021 [cited by applicant]
Yu, Juntao, Bernd Bohnet, and Massimo Poesio. “Named entity recognition as dependency parsing.” arXiv preprint arXiv: 2005.07150 (2020). (Year: 2020). [cited by examiner]
Zhang, Yue, et al. “Entity relation extraction as dependency parsing in visually rich documents.” arXiv preprint arXiv:2110.09915 (Oct. 19, 2021). (Year: 2021). [cited by examiner]
Zhang, Yunquan, et al. “Parallel processing systems for big data: a survey.” Proceedings of the IEEE 104.11 (2016): 2114-2136. (Year: 2016). [cited by examiner]
AMD Secure Encrypted Virtualization (SEV), https://developer.amd.com/sev/, accessed Sep. 23, 2020 (5 pages). [cited by applicant]
Arora, S. et al., “A Simple But Tough-To-Beat Baseline for Sentence Embeddings”, ICLR, 2017 (16 pages). [cited by applicant]
AWS Key Management Service (KMS), https://aws.amazon.com/kms, accessed Sep. 23, 2020 (6 pages). [cited by applicant]
Bartunov, S. et al., “Breaking Sticks And Ambiguities With Adaptive Skip-Gram”, retrieved online from URL:< https://arxiv.org/pdf/1502.07257.pdf>, [cs.CL], Nov. 15, 2015 (15 pages). [cited by applicant]
Bojanowski, P. et al., “Enriching Word Vectors with Subword Information”, retrieved online from URL:<https://arxiv.org/pdf/1607.04606.pdf>, [cs.CL], Jun. 19, 2017 (12 pages). [cited by applicant]
Confidental Computing Consortium, “What is the Confidential Computing Consortium?”, https://confidentialcomputing.io, accessed Sep. 24, 2020 (2 pages). [cited by applicant]
de Guzman, C.G. et al., “Hematopoietic Stem Cell Expansion and Distinct Myeloid Developmental Abnormalities in a Murine Model of the [cited by applicant]
Desagulier, G., “A lesson from associative learning: asymmetry and productivity in multiple-slot constructions”, Corpus Linguisitic and Linguistic Theory, 12(2):173-219, 2016, submitted Aug. 13, 2015, <http://www.degruy… [cited by applicant]
Devlin, J. et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, <https://arXiv:1810.04805v2> [cs.CL], May 24, 2019 (16 pages). [cited by applicant]
Divatia, A., “The Fact and Fiction of Homomorphic Encryption”, Dark Reading, www.darkreading.com/attacks-breaches/the-fact-and-fiction-of-homomorphic-encryption/a/d-id/1333691, Jan. 22, 2019 (2 pages). [cited by applicant]
Dwork, C., “Differential Privacy: A Survey of Results”, Lecture Notes in Computer Science, vol. 4978, pp. 1-19, 2008 (19 pages). [cited by applicant]
Genkin, D. et al., “Privacy in Decentralized Cryptocurrencies”, Communications of the ACM, 61(6):78-88, Jun. 2018 (11 pages). [cited by applicant]
Hageman, G.S et al., “A common haplotype in the complement regulatory gene factor H ( [cited by applicant]
Ikeda, T. et al., “Anticorresponding mutations of the [cited by applicant]
Intel, “What is Intel® SGX?”, https://www.intel.com/content/www/us/en/architecture-and-technology/software-guard-extensions.html, accessed Sep. 23, 2020 (8 pages). [cited by applicant]
International Preliminary Report on Patentabilty issued in International Application PCT/US21/13897, dated Jul. 19, 2022 (7 pages). [cited by applicant]
International Preliminary Report on Patentability issued in International Application No. PCT/US20/42336, dated Jan. 18, 2022 (9 pages). [cited by applicant]
International Search Report and Written Opinion issued by the European Patent Office as International Searching Authority in International Application PCT/US2017/053039, dated Dec. 20, 2017 (15 pages). [cited by applicant]
International Search Report and Written Opinion issued by the U.S. Patent and Trademark Office as International Searching Authority in International Application No. PCT/US22/79269 dated Feb. 3, 2023 (9 pages). [cited by applicant]
International Search Report and Written Opinion issued by U.S. Patent and Trademark Office as International Searching Authority in International Application No. PCT/US20/42336, dated Sep. 30, 2020 (10 pages). [cited by applicant]
International Search Report and Written Opinion, issued by U.S. Patent and Trademark Office as International Searching Authority, in International Application No. PCT/US21/13897, dated Apr. 5, 2021 (8 pages). [cited by applicant]
Joulin, A. et al., “Bag of Tricks for Efficient Text Classification”, retrieved online from URL:<https://arXiv.org/pdf/1607.01759v3.pdf>, [cs.CL], Aug. 9, 2016 (5 pages). [cited by applicant]
Kiros, R. et al., “Skip-Thought Vectors”, retrieved online from URL:<https://arXiv.org/abs/1506.06726v1>, [cs.CL], Jun. 22, 2015 (11 pages). [cited by applicant]
Kolte, P. “Why Is Homomorphic Encryption Not Ready For Primetime?”, Baffle, https://baffle.io/blog/why-is-homomorphic-encryption-not-ready-for-primetime/, Mar. 17, 2017 (4 pages). [cited by applicant]
Korger, C., “Clustering of Distributed Word Representations and its Applicability for Enterprise Search”, Doctoral Thesis, Dresden University of Technology, Faculty of Computer Science, Institute of Software and Multime… [cited by applicant]
Kutuzov, A. et al., “Cross-lingual Trends Detection for Named Entities in News Texts with Dynamic Neural Embedding Models”, Proceedings of the NewsIR'16 Workshop at ECIR, Padua, Italy, Mar. 20, 2016 (6 pages). [cited by applicant]
Le, Q. et al., “Distributed Representations of Sentences and Documents”, Proceedings of the 31st International Conference of Machine Learning, Beijing, China, vol. 32, 2014 (9 pages). [cited by applicant]
Li, H. et al., “Cheaper and Better: Selecting Good Workers for Crowdsourcing,” retrieved online from URL: https://arXiv.org/abs/1502.00725v1, Feb. 3, 2015 (16 pages). [cited by applicant]
Ling, W. et al., “Two/Too Simple Adaptations of Word2Vec for Syntax Problems”, retrieved online from URL:<https://cs.cmu.edu/˜lingwang/papers/naacl2015.pdf>, 2015 (6 pages). [cited by applicant]
Maxwell, K.N. et al., “Adenoviral-mediated expression of Pcsk9 in mice results in a low-density lipoprotein receptor knockout phenotype”, PNAS, 101(18):7100-7105, May 4, 2004 (6 pages). [cited by applicant]
Mikolov, T. et al., “Distributed Representations for Words and Phrases and their Compositionality”, retrieved online from URL:https://arXiv.org/abs/1310.4546v1 [cs.CL], Oct. 16, 2013 (9 pages). [cited by applicant]
Mikolov, T. et al., “Efficient Estimation of Word Representations in Vector Space”, retrieved online from URL: https://arXiv.org/abs/1301.3781v3 [cs.CL] Sep. 7, 2013 (12 pages). [cited by applicant]
Murray, K., “A Semantic Scan Statistic for Novel Disease Outbreak Detection”, Master's Thesis, Carnegie Mellon University, Aug. 16, 2013 (68 pages). [cited by applicant]
Neelakantan, A., et al., “Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space,” Department of Computer Science, University of Massachusetts, (2015) (11 pages). [cited by applicant]
Pennington, J. et al., “GloVe: Global Vectors for Word Representation”, retrieved online from URL:<https://nlp.stanford.edu/projects/glove.pdf>, 2014 (12 pages). [cited by applicant]
Rajagopalan, H., et al., “Tumorigenesis: RAF/RAS oncogenes and mismatch-repair status”, Nature, 418:934, Aug. 29, 2002 (1 page). [cited by applicant]
Shamir, A. “How to Share a Secret”, Communications of the ACM, 22(11):612-613, Nov. 1979 (2 pages). [cited by applicant]
Shweta, Fnu et al., “Augmented Curation of Unstructured Clinical Notes from a Massive EHR System Reveals Specific Phenotypic Signature of Impending COVID-19 Diagnosis”, https://www.medrxiv.org/content/10.1101/2020.04.19… [cited by applicant]
Wieting, J. et al., “Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings”, retrieved online from URL:<https://arXiv.org/pdf/1705.00364v1.pdf>, [cs.CL], Apr. 30, 2017 (12 pages). [cited by applicant]
Yao, Z. et al., “Dynamic Word Embeddings for Evolving Semantic Discovery”, WSDM 2018, Marina Del Rey, CA, USA, Feb. 5-9, 2018 (9 pages). [cited by applicant]
Zuccon, G., et al., “Integrating and Evaluating Neural Word Embeddings in Information Retrieval”, ADCS, Parramatta, NSW, Australia, Dec. 8-9, 2015 (8 pages). [cited by applicant]