Jingxin Lee

This problem is start from [doc = merge_phrases(doc)](https://github.com/explosion/sense2vec/blob/d689bb65ce0f6c597c891cea3ba279ad1f92916f/scripts/02_preprocess.py#L53)， end in https://github.com/explosion/sense2vec/blob/d689bb65ce0f6c597c891cea3ba279ad1f92916f/sense2vec/util.py#L117 I mannully create a syntax_iterators.py within zh. But it doesn't work.

`encoder_hidden[:decoder.n_layers]` If decoder.n_layer=1, encoder_hidden[:1] is the first hidden state. not the LAST hidden state, right?

Yes. For example, given the question: What's the weather like today? and generate "Is it going to rain today?", "Is it sunny today?" or something similar.

Sorry I only have Chinese examples. I will translate some sentences. 什么时候你能给我开发票？ When will you send me the invoice? 几号能开发票？Which day can I get the invoice? 可以把近几个月的费用给我开到一张票上吗？ Can you send...

> @JingxinLee check out the latest version for updates that address what you are looking for > > ``` > from text2text import Variator > sr = Variator() > bacteria_str...

nlp.utils.info_utils.NonMatchingSplitsSizesError: [{'expected': SplitInfo(name='train', num_bytes=226286197, num_examples=253276, dataset_name='squad_multitask'), 'recorded': SplitInfo(name='train', num_bytes=226284739, num_examples=253275, dataset_name='squad_multitask')}]

Same issue.

> Could you explain a bit more why you can't paste it? On my side, I get the login window like on a regular notebook/colab and can paste the token...

> Hi! Could you please send me a public link where I can reproduce this? > Thanks! https://edu.google.com/

> Thanks! I will look into that. As a temporary solution, you can disable the extension on https://edu.google.com/ until the problem is fixed. Okay, Thanks a lot! By the way,...