language-model

As reported by some people (see NielsRogge/Transformers-Tutorials#53 and on the forum), the generate() method currently does not take into account config.decoder.eos_token_id, only config.eos_token_id to properly stop generation.

Hence, models that are made using EncoderDecoderModel/`VisionEnco

From paper, it mentioned

Instead, the training data generator chooses 15% of tokens at random, e.g., in the sentence my
dog is hairy it chooses hairy.

It means that 15% of token will be choose for sure.

From https://github.com/codertimo/BERT-pytorch/blob/master/bert_pytorch/dataset/dataset.py#L68,
for every single token, it has 15% of chance that go though the followup procedure.

Proposed changes:

• Section that tells the reader about what companies already use Haystack, this helps strengthen the horizontal relationships in the community

The inspiration is taken from the Apache Superset repository

Status (please check what you already did):

• First draft (up for discussions & feedb

目前的多音字使用 pypinyin 或者 g2pM，精度有限，想做一个基于 BERT (或者 ERNIE) 多音字预测模型，简单来说就是假设某语言有 100 个多音字，每个多音字最多有 3 个发音，那么可以在 BERT 后面接 100 个 3 分类器（简单的 fc 层即可），在预测时，找到对应的分类器进行分类即可。
参考论文：
tencent_polyphone.pdf

数据可以用 https://github.com/kakaobrain/g2pM 提供的数据

进阶：多任务的 BERT
![image](https://user-images.githubusercontent.com/24568452

Issue to track tutorial requests:

• Deep Learning with PyTorch: A 60 Minute Blitz - #69
• Sentence Classification - #79