-
Notifications
You must be signed in to change notification settings - Fork 0
/
biblio.bib
991 lines (879 loc) · 32 KB
/
biblio.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
@article{dunn46_recor_linkag,
author = {Halbert L. Dunn},
title = {Record Linkage},
journal = {American Journal of Public Health and the Nations Health},
volume = 36,
number = 12,
pages = {1412-1416},
year = 1946,
doi = {10.2105/ajph.36.12.1412},
url = {https://doi.org/10.2105/ajph.36.12.1412},
DATE_ADDED = {Fri Sep 20 14:06:15 2019},
}
@article{newcombe59_autom_linkag_vital_recor,
author = {H. B. Newcombe and J. M. Kennedy and S. J. Axford and A. P.
James},
title = {Automatic Linkage of Vital Records: Computers Can Be Used To
Extract "Follow-Up" Statistics of Families From Files of
Routine Records},
journal = {Science},
volume = 130,
number = 3381,
pages = {954-959},
year = 1959,
doi = {10.1126/science.130.3381.954},
url = {https://doi.org/10.1126/science.130.3381.954},
DATE_ADDED = {Fri Sep 20 14:18:40 2019},
}
@article{fellegi69_theor_recor_linkag,
author = {Ivan P. Fellegi and Alan B. Sunter},
title = {A Theory for Record Linkage},
journal = {Journal of the American Statistical Association},
volume = 64,
number = 328,
pages = {1183-1210},
year = 1969,
doi = {10.1080/01621459.1969.10501049},
url = {https://doi.org/10.1080/01621459.1969.10501049},
DATE_ADDED = {Fri Sep 20 14:28:21 2019},
}
@Book{christen12_data,
author = {Christen, Peter},
title = {Data matching : concepts and techniques for record linkage,
entity resolution, and duplicate detection},
year = 2012,
publisher = {Springer},
address = {Berlin New York},
isbn = 9783642311635,
}
@article{christen12_survey_index_techn_scalab_recor_linkag_dedup,
author = {Peter Christen},
title = {A Survey of Indexing Techniques for Scalable Record Linkage
and Deduplication},
journal = {IEEE Transactions on Knowledge and Data Engineering},
volume = 24,
number = 9,
pages = {1537-1555},
year = 2012,
doi = {10.1109/tkde.2011.127},
url = {https://doi.org/10.1109/tkde.2011.127},
DATE_ADDED = {Fri Sep 27 13:53:54 2019},
}
@inproceedings{winkler2006overview,
title={Overview of record linkage and current research directions},
author={Winkler, William E},
booktitle={Bureau of the Census},
year={2006},
organization={Citeseer},
DATE_ADDED = {Fri Sep 27 13:53:54 2019},
}
@inproceedings{Baxter2003ACO,
title={A Comparison of Fast Blocking Methods for Record Linkage},
author={Rohan A. Baxter and Peter Christen and Tim Churches},
booktitle={KDD 2003},
year={2003}
}
@article{Sayers2015,
doi = {10.1093/ije/dyv322},
url = {https://doi.org/10.1093/ije/dyv322},
year = {2015},
month = dec,
publisher = {Oxford University Press ({OUP})},
volume = {45},
number = {3},
pages = {954--964},
author = {Adrian Sayers and Yoav Ben-Shlomo and Ashley W Blom and Fiona Steele},
title = {Probabilistic record linkage},
journal = {International Journal of Epidemiology}
}
@article{@clark2004_rl_for_injury,
author = {Clark, D E},
title = {Practical introduction to record linkage for injury research.},
abstract = {The frequency of early fatality and the transient nature of emergency medical
care mean that a single database will rarely suffice for population based injury
research. Linking records from multiple data sources is therefore a promising
method for injury surveillance or trauma system evaluation. The purpose of this
article is to review the historical development of record linkage, provide a
basic mathematical foundation, discuss some practical issues, and consider some
ethical concerns. Clerical or computer assisted deterministic record linkage
methods may suffice for some applications, but probabilistic methods are
particularly useful for larger studies. The probabilistic method attempts to
simulate human reasoning by comparing each of several elements from the two
records. The basic mathematical specifications are derived algebraically from
fundamental concepts of probability, although the theory can be extended to
include more advanced mathematics. Probabilistic, deterministic, and clerical
techniques may be combined in different ways depending upon the goal of the
record linkage project. If a population parameter is being estimated for a purely
statistical study, a completely probabilistic approach may be most efficient; for
other applications, where the purpose is to make inferences about specific
individuals based upon their data contained in two or more files, the need for a
high positive predictive value would favor a deterministic method or a
probabilistic method with careful clerical review. Whatever techniques are used,
researchers must realize that the combination of data sources entails additional
ethical obligations beyond the use of each source alone.},
journal = {Injury prevention : journal of the International Society for Child and Adolescent
Injury Prevention},
volume = {10},
number = {3},
year = {2004},
pages = {186-91},
doi = {10.1136/ip.2003.004580},
}
@article{Churches2002,
author = {Tim Churches and Peter Christen and Kim Lim and Justin Xi Zhu},
title = {Preparation of name and address data for record linkage using
hidden Markov models},
journal = {{BMC} Medical Informatics and Decision Making},
volume = 2,
number = 1,
year = 2002,
doi = {10.1186/1472-6947-2-9},
url = {https://doi.org/10.1186/1472-6947-2-9},
month = dec,
publisher = {Springer Nature},
}
@article{Rahm00datacleaning,
author = {Erhard Rahm and Hong Hai Do},
title = {Data Cleaning: Problems and Current Approaches},
journal = {IEEE Data Engineering Bulletin},
volume = 23,
pages = 2000,
year = 2000,
}
@inbook{gu06_decis_model_recor_linkag,
DATE_ADDED = {Sat Sep 28 13:10:08 2019},
author = {Lifang Gu and Rohan Baxter},
booktitle = {Lecture Notes in Computer Science},
doi = {10.1007/11677437_12},
pages = {146-160},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
title = {Decision Models for Record Linkage},
url = {https://doi.org/10.1007/11677437_12},
year = {2006},
}
@article{Hartigan1979,
doi = {10.2307/2346830},
url = {https://doi.org/10.2307/2346830},
year = {1979},
publisher = {{JSTOR}},
volume = {28},
number = {1},
pages = {100},
author = {J. A. Hartigan and M. A. Wong},
title = {Algorithm {AS} 136: A K-Means Clustering Algorithm},
journal = {Applied Statistics}
}
@inproceedings{levenshtein1966binary,
title={Binary codes capable of correcting deletions, insertions, and reversals},
author={Levenshtein, Vladimir I},
booktitle={Soviet physics doklady},
volume={10},
pages={707--710},
year={1966}
}
@article{Kalashnikov2006_collective_graph,
author = {Kalashnikov, Dmitri V. and Mehrotra, Sharad},
title = {Domain-independent Data Cleaning via Analysis of
Entity-relationship Graph},
journal = {ACM Trans. Database Syst.},
volume = 31,
number = 2,
pages = {716--767},
year = 2006,
doi = {10.1145/1138394.1138401},
url = {http://doi.acm.org/10.1145/1138394.1138401},
acmid = 1138401,
address = {New York, NY, USA},
issn = {0362-5915},
issue_date = {June 2006},
keywords = {Connection strength, RelDC, data cleaning, entity resolution,
graph analysis, reference disambiguation, relationship
analysis},
month = jun,
numpages = 52,
publisher = {ACM},
}
@inproceedings{Dong2005_reference_reconciliation,
author = {Dong, Xin and Halevy, Alon and Madhavan, Jayant},
title = {Reference Reconciliation in Complex Information Spaces},
booktitle = {Proceedings of the 2005 ACM SIGMOD International Conference on
Management of Data},
year = 2005,
pages = {85--96},
doi = {10.1145/1066157.1066168},
url = {http://doi.acm.org/10.1145/1066157.1066168},
acmid = 1066168,
address = {New York, NY, USA},
isbn = {1-59593-060-4},
location = {Baltimore, Maryland},
numpages = 12,
publisher = {ACM},
series = {SIGMOD '05},
}
@article{bhattacharya07_collec_entit_resol_relat_data,
author = {Indrajit Bhattacharya and Lise Getoor},
title = {Collective Entity Resolution in Relational Data},
journal = {ACM Transactions on Knowledge Discovery from Data},
volume = 1,
number = 1,
pages = {5-es},
year = 2007,
doi = {10.1145/1217299.1217304},
url = {https://doi.org/10.1145/1217299.1217304},
DATE_ADDED = {Sun Sep 29 11:54:31 2019},
}
@article{Powers2011_evaluation,
author = {Powers, David and Ailab,},
title = {Evaluation: From precision, recall and F-measure to ROC,
informedness, markedness \& correlation},
journal = {J. Mach. Learn. Technol},
volume = 2,
pages = {2229-3981},
year = 2011,
doi = {10.9735/2229-3981},
month = 01,
}
@article{hand17_note_using_f_measur_evaluat,
author = {David Hand and Peter Christen},
title = {A Note on Using the F-Measure for Evaluating Record Linkage
Algorithms},
journal = {Statistics and Computing},
volume = 28,
number = 3,
pages = {539-547},
year = 2017,
doi = {10.1007/s11222-017-9746-6},
url = {https://doi.org/10.1007/s11222-017-9746-6},
DATE_ADDED = {Sun Sep 29 12:36:42 2019},
}
@InProceedings{mckinney2010_pandas,
author = { Wes McKinney },
title = { Data Structures for Statistical Computing in Python },
booktitle = { Proceedings of the 9th Python in Science Conference },
year = { 2010 },
pages = { 51 - 56 },
editor = { St\'efan van der Walt and Jarrod Millman },
}
@article{scikit-learn,
author = {Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel,
V. and Thirion, B. and Grisel, O. and Blondel, M. and
Prettenhofer, P. and Weiss, R. and Dubourg, V. and Vanderplas,
J. and Passos, A. and Cournapeau, D. and Brucher, M. and
Perrot, M. and Duchesnay, E.},
title = {Scikit-learn: Machine Learning in {P}ython},
journal = {Journal of Machine Learning Research},
volume = 12,
pages = {2825--2830},
year = 2011,
}
@misc{recordlinkage-library,
author = {Jonathan de Bruin},
title = {{recordlinkage (version 0.13.2)}},
year = {2019},
howpublished={\url{https://recordlinkage.readthedocs.io/en/latest/about.html}},
note = "[Online; accessed 27-September-2019]",
}
@incollection{sqlalchemy,
author = {Bayer, Michael},
booktitle = {The Architecture of Open Source Applications Volume II:
Structure, Scale, and a Few More Fearless Hacks},
editor = {Brown, Amy and Wilson, Greg},
place = {Mountain View},
publisher = {aosabook.org},
title = {SQLAlchemy},
url = "http://aosabook.org/en/sqlalchemy.html",
year = 2012,
}
@misc{flennerhag:2017mlens,
author = {Flennerhag, Sebastian},
doi = {10.5281/zenodo.1042144},
month = nov,
title = {ML-Ensemble},
url = {https://dx.doi.org/10.5281/zenodo.1042144},
year = 2017,
}
@Techreport{python-tutorial,
address = {Amsterdam},
author = {G. van Rossum},
institution = {Centrum voor Wiskunde en Informatica (CWI)},
month = {May},
number = {CS-R9526},
title = {Python tutorial},
year = 1995,
}
@Article{Hunter_Matplotlib,
Author = {Hunter, J. D.},
Title = {Matplotlib: A 2D graphics environment},
Journal = {Computing in Science \& Engineering},
Volume = {9},
Number = {3},
Pages = {90--95},
abstract = {Matplotlib is a 2D graphics package used for Python for
application development, interactive scripting, and publication-quality
image generation across user interfaces and operating systems.},
publisher = {IEEE COMPUTER SOC},
doi = {10.1109/MCSE.2007.55},
year = 2007
}
@misc{Seaborn,
doi = {10.5281/ZENODO.12710},
url = {https://zenodo.org/record/12710},
author = {Waskom, Michael and Botvinnik, Olga and Hobson, Paul and Cole, John B. and Halchenko, Yaroslav and Hoyer, Stephan and Miles, Alistair and Augspurger, Tom and Yarkoni, Tal and Megies, Tobias and Coelho, Luis Pedro and Wehner, Daniel and {Cynddl} and Ziegler, Erik and {Diego0020} and Zaytsev, Yury V. and Hoppe, Travis and {Skipper Seabold} and Cloud, Phillip and Koskinen, Miikka and Meyer, Kyle and Qalieh, Adel and Allan, Dan},
title = {Seaborn: V0.5.0 (November 2014)},
publisher = {Zenodo},
year = {2014}
}
@article{singhal_modern_information_retrieval,
title = {Modern Information Retrieval: A Brief Overview},
author = {Amit Singhal},
year = {2001},
journal = {IEEE Data Eng. Bull.},
pages = {35-43},
volume = {24}
}
@misc{chollet2015keras,
title={Keras},
author={Chollet, Fran\c{c}ois and others},
year={2015},
howpublished={\url{https://keras.io}},
}
@incollection{Munro2011_bias_variance_decomp,
doi = {10.1007/978-0-387-30164-8_74},
url = {https://doi.org/10.1007/978-0-387-30164-8_74},
year = {2011},
publisher = {Springer {US}},
pages = {100--101},
author = {Paul Munro and Hannu Toivonen and Geoffrey I. Webb and Wray Buntine and Peter Orbanz and Yee Whye Teh and Pascal Poupart and Claude Sammut and Caude Sammut and Hendrik Blockeel and Dev Rajnarayan and David Wolpert and Wulfram Gerstner and C. David Page and Sriraam Natarajan and Geoffrey Hinton},
title = {Bias Variance Decomposition},
booktitle = {Encyclopedia of Machine Learning}
}
@Article{Breiman1996_bagging_predictors,
author="Breiman, Leo",
title="Bagging predictors",
journal="Machine Learning",
year="1996",
month="Aug",
day="01",
volume="24",
number="2",
pages="123--140",
abstract="Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy.",
issn="1573-0565",
doi="10.1007/BF00058655",
url="https://doi.org/10.1007/BF00058655"
}
@inproceedings{Kohavi:1995_study_of_cross_validation,
author = {Kohavi, Ron},
title = {A Study of Cross-validation and Bootstrap for Accuracy Estimation and Model Selection},
booktitle = {Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2},
series = {IJCAI'95},
year = {1995},
isbn = {1-55860-363-8},
location = {Montreal, Quebec, Canada},
pages = {1137--1143},
numpages = {7},
url = {http://dl.acm.org/citation.cfm?id=1643031.1643047},
acmid = {1643047},
publisher = {Morgan Kaufmann Publishers Inc.},
address = {San Francisco, CA, USA},
}
@inproceedings{clauset2011brief,
title={A brief primer on probability distributions},
author={Clauset, Aaron},
booktitle={Santa Fe Institute},
year={2011}
}
@article{Cawley:2010_crossval_model_selection,
author = {Cawley, Gavin C. and Talbot, Nicola L.C.},
title = {On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation},
journal = {J. Mach. Learn. Res.},
issue_date = {3/1/2010},
volume = {11},
month = aug,
year = {2010},
issn = {1532-4435},
pages = {2079--2107},
numpages = {29},
url = {http://dl.acm.org/citation.cfm?id=1756006.1859921},
acmid = {1859921},
publisher = {JMLR.org},
}
@misc{dusetzina_m_2014, title={An Overview of Record Linkage Methods}, url={https://www.ncbi.nlm.nih.gov/books/NBK253312/}, journal={Linking Data for Health Services Research: A Framework and Instructional Guide [Internet].}, publisher={U.S. National Library of Medicine}, author={Dusetzina, Stacie B and M, Meyer A}, year={2014}, month={Sep},
howpublished={\url{https://www.ncbi.nlm.nih.gov/books/NBK253312/}},
note = "[Online; accessed 28-September-2019]",
}
@book{Russell:2009:AIM:1671238,
author = {Russell, Stuart and Norvig, Peter},
title = {Artificial Intelligence: A Modern Approach},
year = {2009},
isbn = {0136042597, 9780136042594},
edition = {3rd},
publisher = {Prentice Hall Press},
address = {Upper Saddle River, NJ, USA},
}
@article{Vapnik1995_svm,
doi = {10.1007/bf00994018},
url = {https://doi.org/10.1007/bf00994018},
year = {1995},
month = sep,
publisher = {Springer Science and Business Media {LLC}},
volume = {20},
number = {3},
pages = {273--297},
author = {Corinna Cortes and Vladimir Vapnik},
title = {Support-vector networks},
journal = {Machine Learning}
}
@book{Cristianini2000_svm,
doi = {10.1017/cbo9780511801389},
url = {https://doi.org/10.1017/cbo9780511801389},
year = {2000},
publisher = {Cambridge University Press},
author = {Nello Cristianini and John Shawe-Taylor},
title = {An Introduction to Support Vector Machines and Other Kernel-based Learning Methods}
}
@inproceedings{Boser:1992_kernel_trick,
author = {Boser, Bernhard E. and Guyon, Isabelle M. and Vapnik, Vladimir N.},
title = {A Training Algorithm for Optimal Margin Classifiers},
booktitle = {Proceedings of the Fifth Annual Workshop on Computational Learning Theory},
series = {COLT '92},
year = {1992},
isbn = {0-89791-497-X},
location = {Pittsburgh, Pennsylvania, USA},
pages = {144--152},
numpages = {9},
url = {http://doi.acm.org/10.1145/130385.130401},
doi = {10.1145/130385.130401},
acmid = {130401},
publisher = {ACM},
address = {New York, NY, USA},
}
@article{Fan:2008_liblinear,
author = {Fan, Rong-En and Chang, Kai-Wei and Hsieh, Cho-Jui and Wang, Xiang-Rui and Lin, Chih-Jen},
title = {LIBLINEAR: A Library for Large Linear Classification},
journal = {J. Mach. Learn. Res.},
issue_date = {6/1/2008},
volume = {9},
month = jun,
year = {2008},
issn = {1532-4435},
pages = {1871--1874},
numpages = {4},
url = {http://dl.acm.org/citation.cfm?id=1390681.1442794},
acmid = {1442794},
publisher = {JMLR.org},
}
@inproceedings{Hsieh:2008_lsvm_coordinated_descent,
author = {Hsieh, Cho-Jui and Chang, Kai-Wei and Lin, Chih-Jen and Keerthi, S. Sathiya and Sundararajan, S.},
title = {A Dual Coordinate Descent Method for Large-scale Linear SVM},
booktitle = {Proceedings of the 25th International Conference on Machine Learning},
series = {ICML '08},
year = {2008},
isbn = {978-1-60558-205-4},
location = {Helsinki, Finland},
pages = {408--415},
numpages = {8},
url = {http://doi.acm.org/10.1145/1390156.1390208},
doi = {10.1145/1390156.1390208},
acmid = {1390208},
publisher = {ACM},
address = {New York, NY, USA},
}
@article{McCallum98acomparison_bayes,
author = {Mccallum, Andrew and Nigam, Kamal},
year = {2001},
month = {05},
pages = {},
title = {A Comparison of Event Models for Naive Bayes Text Classification},
volume = {752},
journal = {Work Learn Text Categ}
}
@INPROCEEDINGS{Metsis06spamfiltering_bayes,
author = {Vangelis Metsis and et al.},
title = {Spam Filtering with Naive Bayes -- Which Naive Bayes?},
booktitle = {THIRD CONFERENCE ON EMAIL AND ANTI-SPAM (CEAS},
year = {2006},
publisher = {}
}
@inproceedings{zhang2004_bayes_optimality,
author = {Zhang, Harry},
year = {2004},
month = {01},
pages = {},
title = {The Optimality of Naive Bayes},
volume = {2},
journal = {Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004}
}
@misc{claesen2015hyperparameter,
title={Hyperparameter Search in Machine Learning},
author={Marc Claesen and Bart De Moor},
year={2015},
eprint={1502.02127},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@article{Bergstra:2012_random_gs,
author = {Bergstra, James and Bengio, Yoshua},
title = {Random Search for Hyper-parameter Optimization},
journal = {J. Mach. Learn. Res.},
issue_date = {3/1/2012},
volume = {13},
month = feb,
year = {2012},
issn = {1532-4435},
pages = {281--305},
numpages = {25},
url = {http://dl.acm.org/citation.cfm?id=2188385.2188395},
acmid = {2188395},
publisher = {JMLR.org},
keywords = {deep learning, global optimization, model selection, neural networks, response surface modeling},
}
@techreport{breiman1996_perturbing,
title={Bias, variance, and arcing classifiers},
author={Breiman, Leo},
year={1996},
institution={Tech. Rep. 460, Statistics Department, University of California, Berkeley~…}
}
@article{breiman2001random_forest,
title={Random forests},
author={Breiman, Leo},
journal={Machine learning},
volume={45},
number={1},
pages={5--32},
year={2001},
publisher={Springer}
}
@book{Goodfellow-et-al-2016,
title={Deep Learning},
author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
publisher={MIT Press},
note={\url{http://www.deeplearningbook.org}},
year={2016}
}
@inproceedings{Wilson2011_slp_in_rl,
doi = {10.1109/ijcnn.2011.6033192},
url = {https://doi.org/10.1109/ijcnn.2011.6033192},
year = {2011},
month = jul,
publisher = {{IEEE}},
author = {D. Randall Wilson},
title = {Beyond probabilistic record linkage: Using neural networks and complex features to improve genealogical record linkage},
booktitle = {The 2011 International Joint Conference on Neural Networks}
}
@book{minsky2017_paupert_xor,
title={Perceptrons: An introduction to computational geometry},
author={Minsky, Marvin and Papert, Seymour A},
year={2017},
publisher={MIT press}
}
@misc{klambauer2017selfnormalizing,
title={Self-Normalizing Neural Networks},
author={Günter Klambauer and Thomas Unterthiner and Andreas Mayr and Sepp Hochreiter},
year={2017},
eprint={1706.02515},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@article{csaji2001approximation,
title={Approximation with artificial neural networks},
author={Cs{\'a}ji, Bal{\'a}zs Csan{\'a}d},
journal={Faculty of Sciences, Etvs Lornd University, Hungary},
volume={24},
pages={48},
year={2001},
publisher={Citeseer}
}
@article{Hornik1991_approximation,
doi = {10.1016/0893-6080(91)90009-t},
url = {https://doi.org/10.1016/0893-6080(91)90009-t},
year = {1991},
publisher = {Elsevier {BV}},
volume = {4},
number = {2},
pages = {251--257},
author = {Kurt Hornik},
title = {Approximation capabilities of multilayer feedforward networks},
journal = {Neural Networks}
}
@article{dozat2016incorporating_nadam,
title={Incorporating nesterov momentum into adam},
author={Dozat, Timothy},
year={2016}
}
@article{Rumelhart1986,
doi = {10.1038/323533a0},
url = {https://doi.org/10.1038/323533a0},
year = {1986},
month = oct,
publisher = {Springer Nature},
volume = {323},
number = {6088},
pages = {533--536},
author = {David E. Rumelhart and Geoffrey E. Hinton and Ronald J. Williams},
title = {Learning representations by back-propagating errors},
journal = {Nature}
}
@misc{zeiler2012adadelta,
title={ADADELTA: An Adaptive Learning Rate Method},
author={Matthew D. Zeiler},
year={2012},
eprint={1212.5701},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
@article{opitz1999popular,
title={Popular ensemble methods: An empirical study},
author={Opitz, David and Maclin, Richard},
journal={Journal of artificial intelligence research},
volume={11},
pages={169--198},
year={1999}
}
@inproceedings{dietterich2000ensemble,
title={Ensemble methods in machine learning},
author={Dietterich, Thomas G},
booktitle={International workshop on multiple classifier systems},
pages={1--15},
year={2000},
organization={Springer}
}
@book{zhou2012ensemble,
title={Ensemble methods: foundations and algorithms},
author={Zhou, Zhi-Hua},
year={2012},
publisher={Chapman and Hall/CRC}
}
@article{Bell:2007_netflix_competition,
author = {Bell, Robert M. and Koren, Yehuda},
title = {Lessons from the Netflix Prize Challenge},
journal = {SIGKDD Explor. Newsl.},
issue_date = {December 2007},
volume = {9},
number = {2},
month = dec,
year = {2007},
issn = {1931-0145},
pages = {75--79},
numpages = {5},
url = {http://doi.acm.org/10.1145/1345448.1345465},
doi = {10.1145/1345448.1345465},
acmid = {1345465},
publisher = {ACM},
address = {New York, NY, USA},
}
@article{Hansen1990,
doi = {10.1109/34.58871},
url = {https://doi.org/10.1109/34.58871},
year = {1990},
publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
volume = {12},
number = {10},
pages = {993--1001},
author = {L.K. Hansen and P. Salamon},
title = {Neural network ensembles},
journal = {{IEEE} Transactions on Pattern Analysis and Machine Intelligence}
}
@article{Schapire1990,
doi = {10.1007/bf00116037},
url = {https://doi.org/10.1007/bf00116037},
year = {1990},
month = jun,
publisher = {Springer Nature},
volume = {5},
number = {2},
pages = {197--227},
author = {Robert E. Schapire},
title = {The strength of weak learnability},
journal = {Machine Learning}
}
@article{Domingos1997,
doi = {10.1023/a:1007413511361},
url = {https://doi.org/10.1023/a:1007413511361},
year = {1997},
publisher = {Springer Nature},
volume = {29},
number = {2/3},
pages = {103--130},
author = {Pedro Domingos and Michael Pazzani},
journal = {Machine Learning},
title = {On the Optimality of the Simple Bayesian Classifier under Zero-One Loss},
}
@article{wolpert1992stacked,
doi = {10.1016/S0893-6080(05)80023-1},
url = {https://doi.org/10.1016/S0893-6080(05)80023-1},
title={Stacked generalization},
author={Wolpert, David H},
journal={Neural networks},
volume={5},
number={2},
pages={241--259},
year={1992},
publisher={Elsevier}
}
@article{Breiman1996_stack,
doi = {10.1007/bf00117832},
url = {https://doi.org/10.1007/bf00117832},
year = {1996},
month = jul,
publisher = {Springer Nature},
volume = {24},
number = {1},
pages = {49--64},
author = {Leo Breiman},
title = {Stacked regressions},
journal = {Machine Learning}
}
@article{van2007super,
doi ={10.2202/1544-6115.1309},
url= {https://doi.org/10.2202/1544-6115.1309},
title={Super learner},
author={Van der Laan, Mark J and Polley, Eric C and Hubbard, Alan E},
journal={Statistical applications in genetics and molecular biology},
volume={6},
number={1},
year={2007},
publisher={De Gruyter}
}
@inproceedings{Bhattacharya:2004_iterative,
author = {Bhattacharya, Indrajit and Getoor, Lise},
title = {Iterative Record Linkage for Cleaning and Integration},
booktitle = {Proceedings of the 9th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery},
series = {DMKD '04},
year = {2004},
isbn = {1-58113-908-X},
location = {Paris, France},
pages = {11--18},
numpages = {8},
url = {http://doi.acm.org/10.1145/1008694.1008697},
doi = {10.1145/1008694.1008697},
acmid = {1008697},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {clustering, deduplication, distance measure, record linkage},
}
@article{Newcombe:1962_proba_rl,
author = {Newcombe, Howard B. and Kennedy, James M.},
title = {Record Linkage: Making Maximum Use of the Discriminating Power of Identifying Information},
journal = {Commun. ACM},
issue_date = {Nov. 1962},
volume = {5},
number = {11},
month = nov,
year = {1962},
issn = {0001-0782},
pages = {563--566},
numpages = {4},
url = {http://doi.acm.org/10.1145/368996.369026},
doi = {10.1145/368996.369026},
acmid = {369026},
publisher = {ACM},
address = {New York, NY, USA},
}
@inproceedings{porter1997approximate,
title={Approximate string comparison and its effect on an advanced record linkage system},
author={Porter, Edward H and Winkler, William E and others},
booktitle={Advanced record linkage system. US Bureau of the Census, Research Report},
year={1997},
organization={Citeseer}
}
@article{winkler1990string,
title={String Comparator Metrics and Enhanced Decision Rules in the Fellegi-Sunter Model of Record Linkage.},
author={Winkler, William E},
year={1990},
publisher={ERIC}
}
@article{Cochinwala2001,
doi = {10.1016/s0020-0255(00)00070-0},
url = {https://doi.org/10.1016/s0020-0255(00)00070-0},
year = {2001},
month = sep,
publisher = {Elsevier {BV}},
volume = {137},
number = {1-4},
pages = {1--15},
author = {Munir Cochinwala and Verghese Kurien and Gail Lalk and Dennis Shasha},
title = {Efficient data reconciliation},
journal = {Information Sciences}
}
@inproceedings{Elfeky_tailor,
doi = {10.1109/icde.2002.994694},
url = {https://doi.org/10.1109/icde.2002.994694},
publisher = {{IEEE} Comput. Soc},
author = {M.G. Elfeky and V.S. Verykios and A.K. Elmagarmid},
title = {{TAILOR}: a record linkage toolbox},
booktitle = {Proceedings 18th International Conference on Data Engineering}
}
@inproceedings{Bilenko:2003:svm,
author = {Bilenko, Mikhail and Mooney, Raymond J.},
title = {Adaptive Duplicate Detection Using Learnable String Similarity Measures},
booktitle = {Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
series = {KDD '03},
year = {2003},
isbn = {1-58113-737-0},
location = {Washington, D.C.},
pages = {39--48},
numpages = {10},
url = {http://doi.acm.org/10.1145/956750.956759},
doi = {10.1145/956750.956759},
acmid = {956759},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {SVM applications, data cleaning, distance metric learning, record linkage, string edit distance, trained similarity measures},
}
@inproceedings{Christen:2008_svm,
author = {Christen, Peter},
title = {Automatic Record Linkage Using Seeded Nearest Neighbour and Support Vector Machine Classification},
booktitle = {Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
series = {KDD '08},
year = {2008},
isbn = {978-1-60558-193-4},
location = {Las Vegas, Nevada, USA},
pages = {151--159},
numpages = {9},
url = {http://doi.acm.org/10.1145/1401890.1401913},
doi = {10.1145/1401890.1401913},
acmid = {1401913},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {data linkage, data matching, deduplication, entity resolution, nearest neighbour, support vector machine},
}
@article{gottapu2016entity,
title={Entity resolution using convolutional neural network},
author={Gottapu, Ram Deepak and Dagli, Cihan and Ali, Bharami},
journal={Procedia Computer Science},
volume={95},
pages={153--158},
year={2016},
publisher={Elsevier}
}
@article{ektefa2011comparative,
title={A comparative study in classification techniques for unsupervised record linkage model},
author={Ektefa, Mohammadreza and Sidi, Fatimah and Ibrahim, Hamidah and Jabar, Marzanah A and Memar, Sara},
journal={Journal of Computer Science},
volume={7},
number={3},
pages={341},
year={2011}
}
@misc{kim2016random_forest_dbscan,
title={Random Forest DBSCAN for USPTO Inventor Name Disambiguation},
author={Kunho Kim and Madian Khabsa and C. Lee Giles},
year={2016},
eprint={1602.01792},
archivePrefix={arXiv},
primaryClass={cs.IR}
}
@article{KhaVo2019_metaensemble,
doi = {10.1016/j.jbi.2019.103220},
url = {https://doi.org/10.1016/j.jbi.2019.103220},
year = {2019},
month = jul,
publisher = {Elsevier {BV}},
volume = {95},
pages = {103220},
author = {Kha Vo and Jitendra Jonnagaddala and Siaw-Teng Liaw},
title = {Statistical supervised meta-ensemble algorithm for medical record linkage},
journal = {Journal of Biomedical Informatics}
}