Update README.md
Browse files
README.md
CHANGED
@@ -9,5 +9,6 @@ datasets:
|
|
9 |
This model is based on [An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification](https://arxiv.org/abs/2210.05529). Ilias Chalkidis, Xiang Dai, Manos Fergadiotis, Prodromos Malakasiotis, and Desmond Elliott. 2022. arXiv:2210.05529 (Preprint).
|
10 |
|
11 |
Initial weights were taken from [google/bert_uncased_L-8_H-256_A-4](https://huggingface.co/google/bert_uncased_L-8_H-256_A-4).
|
|
|
12 |
|
13 |
Maximum input length is 512 tokens that is enoungh to encode dialog with few previous utterances (average sentence length per utterance in SWDA, MAPTASK, MRDA, BT_OASIS, FRAMES, AMI, DSTC3 is less than 11 tokens).
|
|
|
9 |
This model is based on [An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification](https://arxiv.org/abs/2210.05529). Ilias Chalkidis, Xiang Dai, Manos Fergadiotis, Prodromos Malakasiotis, and Desmond Elliott. 2022. arXiv:2210.05529 (Preprint).
|
10 |
|
11 |
Initial weights were taken from [google/bert_uncased_L-8_H-256_A-4](https://huggingface.co/google/bert_uncased_L-8_H-256_A-4).
|
12 |
+
Model was additionally pretrained for 20_000 steps on 5m lines of text from english version of [OpenSubtitles](http://www.opensubtitles.org/) dataset.
|
13 |
|
14 |
Maximum input length is 512 tokens that is enoungh to encode dialog with few previous utterances (average sentence length per utterance in SWDA, MAPTASK, MRDA, BT_OASIS, FRAMES, AMI, DSTC3 is less than 11 tokens).
|