v2.6.0
What's new
Added π
- Added support for NLVR2 visual entailment, including a data loader, two models, and training configs.
- Added
StanfordSentimentTreeBankDatasetReader.apply_token_indexers()
to add token_indexers rather than intext_to_instance
- Added
AdversarialBiasMitigator
tests. - Added
adversarial-binary-gender-bias-mitigated-roberta-snli
model. - Added support for Flickr30k image retrieval, including a dataset reader, a model, and a training config.
- Added
label_smoothing
parameter toCopyNetSeq2Rel
to smooth generation targets. - Added
vocab
as argument tobeam_search.construct
in allgeneration
models.
Fixed β
- Fixed
binary-gender-bias-mitigated-roberta-snli
model card to indicate that model requires[email protected]
. - Fixed registered model name in the
pair-classification-roberta-rte
andvgqa-vilbert
model cards.
Changed β οΈ
- The multiple choice models now use the new
TransformerTextField
and the transformer toolkit generally.
Commits
146ea76 Pass vocab to beam search (#288)
698b7ef TransformerTextField in the MC models (#286)
07fa124 Add label smoothing to CopyNet (#287)
e47da99 Flickr30k (#285)
fb35b2d Bump mypy from 0.812 to 0.910 (#284)
90f6259 Update Python environment setup in GitHub Actions (#283)
bdf82a1 added AdversarialBiasMitigator tests and model (#281)
8d2d84f Test fixes (#282)
ef004d3 Update torch requirement from <1.9.0,>=1.7.0 to >=1.7.0,<1.10.0 (#280)
8cb4b08 small CI fix
d721487 add StanfordSentimentTreeBankDatasetReader.apply_token_indexers()
(#273)
996adff Update pair-classification-binary-gender-bias-mitigated-roberta-snli.json with correct versions of allennlp-models and allennlp (#272)
b17d114 some model card fixes (#274)
0a7901c Revert "CHANGELOG"
38064e1 CHANGELOG
664f38f Nlvr2 (#265)
e395e63 tick version for nightly releases