18 Commits
Author SHA1 Message Date
Ralph Tang 3855254870 Tidy up some code (#174) 2019-02-06 13:36:48 -05:00
Victor Yang 56e29c886e add seperator (#167) 2018-12-03 18:41:32 -05:00
Ralph Tang f510fa6bae Fix VDPWI focus cube padding (#162) 2018-11-12 19:35:11 -05:00
Victor Yang 5afb845a4b Add PIT2015 dataset (#141)
* add prediction/qrel files dump option

* fix comment

* upgrade to torchtext 0.3

* remove ngram

* update device

* minor update

* add pit2015

* revert update torchtext

* revert update torchtext

* revert update torchtext
2018-08-12 18:56:08 -04:00
Linqing Liu fae229eba4 Update VDPWI README with new results (#131)
- Update with results on SICK, TrecQA, and WikiQA datasets
2018-07-03 09:37:18 -04:00
Linqing Liu a4e847725c Change default hyperparameters for VDPWI (#130)
- Default hyperparameters on SICK now use different batch size, RNN hidden dimension, learning rate, optimizer, and number of epochs.
2018-06-27 15:00:42 -04:00
Ralph Tang 62f8abec7f Add README (#110)
* Make *QA/MSRVID work with VDPWI

* Add README
2018-05-25 11:52:25 -04:00
Ralph Tang 494ce36575 Refactor VDPWI to use common API (#109) 2018-05-25 01:30:53 -04:00
Ralph Tang 73823fcc32 Make model parallel wrt batch size 2018-02-06 19:49:12 -05:00
Ralph Tang 4b266431ff Add hyperparameter tuning script 2018-02-05 17:57:52 -05:00
Ralph Tang 901ce4d6a4 Add tensorboard visualization 2018-02-05 15:25:59 -05:00
Ralph Tang b06547b36e Fix norm gradient explosion 2018-02-05 02:48:34 -05:00
Ralph Tang a110b03164 Add GPU loop unrolling for SimCube computation 2018-02-04 23:20:22 -05:00
Ralph Tang 28f62623be Workaround PT padding_idx bug 2018-02-04 22:00:55 -05:00
Ralph Tang 5df6123aba Add training code 2018-02-04 21:39:25 -05:00
Ralph Tang 579d187d8e Add VDPWI core models 2018-02-04 16:10:38 -05:00
Ralph Tang e08f85dc09 Fix sigma bug 2018-02-04 14:17:51 -05:00
Ralph Tang 9e2aaf2788 Add preprocessing scripts 2018-02-03 22:54:58 -05:00