165 Commits

Author	SHA1	Message	Date
Jack Morris	6a44f04f95	update docs & things; TP	2020-06-10 16:21:23 -04:00
Jack Morris	889954aaa9	test huggingface models; test attack from file; remove old files	2020-06-10 15:34:52 -04:00
Jack Morris	8b924362a5	standardize tokenization	2020-06-10 10:16:11 -04:00
Jack Morris	824cd9be8e	figured out huggingface tokenizers for benchmarking, now integrating into attack	2020-06-09 17:30:18 -04:00
Jack Morris	719514645c	good inference; problems with xlnet & roberta mnli	2020-06-09 16:37:10 -04:00
Jack Morris	753d429629	diagnosing tokenization discrepancies	2020-06-09 16:08:32 -04:00
Jack Morris	b1c262fada	merge & add boolean to transformation	2020-06-08 15:36:40 -04:00
Jack Morris	00170fe52c	fix master [duplicate line in args_helper]	2020-06-08 14:54:48 -04:00
Jack Morris	d66acde7ea	progress on all GLUE tasks	2020-06-08 14:46:23 -04:00
Jack Morris	f4d7ba0f1a	add --attack-from-file, unify tokenizers, add models from huggingface model hub [still need to verify acc]	2020-06-07 15:12:02 -04:00
Jin Yong Yoo	798a26efb9	add worklist for dealing with async logging	2020-06-07 11:59:14 -04:00
Jack Morris	3c68d02fb0	remove input reduction, change original_word_idx map to nparray, ignore first/last char for textbugger	2020-06-06 15:16:34 -04:00
Jack Morris	74b7dbb70a	default autotokenizer; add huggingface pre-loaded pre-trained stuff	2020-06-06 13:15:17 -04:00
Jack Morris	62d3a1070c	README; get_logger()->logger	2020-06-05 20:12:14 -04:00
Jack Morris	721a88978a	pretrained & file models/datasets; tests; get_logger() -> logger	2020-06-05 19:06:22 -04:00
uvafan	252b9d2064	fix typo	2020-06-05 18:24:46 -04:00
uvafan	298518afca	discussed fixes	2020-06-05 18:22:48 -04:00
Jack Morris	5222d4c604	successfully loading datasets from file	2020-06-05 18:01:53 -04:00
Jack Morris	b6dd920c08	support custom models; waiting on datasets integration	2020-06-05 17:35:52 -04:00
uvafan	ee95b82895	add query budget	2020-06-05 15:40:20 -04:00
Jack Morris	ab965e292b	account for idx shifts	2020-06-04 16:53:27 -04:00
Jack Morris	cab61ec436	typo	2020-06-04 16:11:59 -04:00
Jack Morris	e02b8e3e68	type validation for TT	2020-06-04 12:53:53 -04:00
Jack Morris	0261c4742e	fix tokenizers, tests pass	2020-06-03 20:41:29 -04:00
Jack Morris	7ca1473a8e	update tests and tokenizers	2020-06-03 19:56:29 -04:00
Jack Morris	f2fe8e1ad7	new -> newly	2020-06-03 18:24:45 -04:00
Jack Morris	0b98045ed5	refactor to combine insertions and deletions (delete is a negative insert)]	2020-06-03 17:26:59 -04:00
Jack Morris	e464296eb5	insertion works. need to [1] simplify into original_modification_indices, [2] restore punctuation	2020-06-03 16:36:00 -04:00
Jack Morris	87ba014c7e	deletion [input reduction] works -- now to add insertion [textbugger]	2020-06-03 15:46:07 -04:00
uvafan	216e73acfa	remove adjusted recipes and mturk prep folder	2020-06-01 15:38:26 -04:00
Jin Yong Yoo	f73509a942	changes requested by eli	2020-05-31 03:59:10 -04:00
Jin Yong Yoo	18ffe94b32	fix recovery logic 2	2020-05-25 04:36:36 -04:00
Jin Yong Yoo	171af100c9	fix recovery log	2020-05-25 04:16:19 -04:00
Jin Yong Yoo	11f295b908	made requested changes	2020-05-24 11:21:05 -04:00
Jin Yong Yoo	a793bd8aa3	free unncessary memory in TokenizedText	2020-05-24 09:24:37 -04:00
Jin Yong Yoo	0191c4ac5c	add missing logger	2020-05-23 04:55:29 -04:00
Jin Yong Yoo	14aa7d0f60	fix typo	2020-05-22 14:04:51 -04:00
Jin Yong Yoo	8c24c71bb2	fix additional bugs for parallel scripting	2020-05-22 13:12:14 -04:00
Jin Yong Yoo	9c06550d07	fix bug with checkpoint for parallel	2020-05-22 10:37:08 -04:00
uvafan	d32b685dc3	rename things, update README	2020-05-21 14:26:56 -04:00
Jack Morris	44ba2f4f40	tests pass	2020-05-20 16:58:31 -04:00
Jack Morris	f145f42298	Merge branch 'master' of github.com:QData/TextAttack into augmentation-many	2020-05-20 16:42:16 -04:00
Jack Morris	ef5f44cd97	Merge pull request #101 from QData/fix-docs ... Fix docs	2020-05-20 16:40:35 -04:00
uvafan	1aaf419a37	datasets, models, misc section	2020-05-20 16:34:22 -04:00
Jack Morris	f030a16c71	improve augmentation; merge in fix-docs	2020-05-20 16:32:25 -04:00
uvafan	93741a7b8b	more docs updates	2020-05-20 14:26:46 -04:00
Jin Yong Yoo	88e950bb63	fix parallel script	2020-05-20 14:20:02 -04:00
uvafan	49bcce8101	update docs	2020-05-20 12:31:04 -04:00
Jack Morris	48364c2dfc	update constraint docs	2020-05-19 16:50:56 -04:00
Jack Morris	222b2b4f2a	Merge branch 'refactor' of github.com:QData/TextAttack into refactor	2020-05-19 16:12:38 -04:00