# In C10 all my translated sentences have double .. or ! at the end

**URL:** <https://community.deeplearning.ai/t/in-c10-all-my-translated-sentences-have-double-or-at-the-end/477408>\
**Category:** NLP with Attention Models\
**Tags:** week-module-1\
**Created:** [October 25, 2023, 8:05pm UTC](https://community.deeplearning.ai/t/in-c10-all-my-translated-sentences-have-double-or-at-the-end/477408 "2023-10-25T20:05:02Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![arvyzukai](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/arvyzukai/32/165165_2.png) [@arvyzukai](https://community.deeplearning.ai/u/arvyzukai)\
**Post date:** [October 26, 2023, 5:27am UTC](https://community.deeplearning.ai/t/in-c10-all-my-translated-sentences-have-double-or-at-the-end/477408/2 "2023-10-26T05:27:37Z")

</div>

Hi @PZ2004

There is something wrong with the implementation because it was not intended that way.

The most obvious places to look for mistakes is UNQ\_C6 `next_symbol()` and UNQ\_C7 `sampling_decode` functions. In particular, how do you check for “end of sequence” token in `sampling_decode()` or how do you choose the next symbol in `next_symbol()` function (you can find some hints [here](https://community.deeplearning.ai/t/which-video-of-the-week-1-is-the-reference-for-next-symbol-function/330890/2)).

Cheers

---

_[View the full topic](https://community.deeplearning.ai/t/in-c10-all-my-translated-sentences-have-double-or-at-the-end/477408)._