# Network applications may have bugs

**URL:** https://support.prodi.gy/t/network-applications-may-have-bugs/6749
**Category:** Uncategorized
**Created:** [August 21, 2023, 4:38pm UTC](https://support.prodi.gy/t/network-applications-may-have-bugs/6749 "2023-08-21T16:38:25Z")
**Posts on this page:** 1
**Showing post:** 2

<div class="post-metadata">

### Author: ![ryanwesslen](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ryanwesslen/32/2969_2.png) [@ryanwesslen](https://support.prodi.gy/u/ryanwesslen)
#### Post date: [August 21, 2023, 6:10pm UTC](https://support.prodi.gy/t/network-applications-may-have-bugs/6749/2 "2023-08-21T18:10:29Z")

</div>

Per your earlier [message](https://support.prodi.gy/t/iterative-meaning-of-data-format-after-using-bert-model-correct/6746/2), I think misaligned tokenization is the problem, not a bug.

In fact, we've had that same error message (`reading 'start'`) from a similar problem:

> [@TypeError: Cannot read properties of undefined (reading 'start')](https://support.prodi.gy/t/typeerror-cannot-read-properties-of-undefined-reading-start/5172/7):
>
> Hi @ljvmiranda921, sorry for reply late, I was busy with other things and forgot to check the progress here. As you said, these values take the token index , not the character index. I have fix the bug when I replace character index with token index. Everything works fine now. And in case you might need it, the vocab.txt is the same as the "bert-base-cased" in huggingface transformers. Thanks again for you advice and I will try to write a "validator" to check the input data next time.

But I think this indicates the problem could be character-based tokenization (like in Chinese) versus token-based tokenization. You may want to set character-based tokenization in your Prodigy annotations. The [docs](https://prodi.gy/docs/named-entity-recognition#highlight-chars) describe this:

> The [` ner.manual`](https://prodi.gy/docs/recipes#ner-manual) recipe also lets you set a `--highlight-chars` flag to allow highlighting individual characters instead of only tokens. This will only store the character offsets of your annotation and won’t add a `"tokens"` property to the saved task.

> When using character-based highlighting, annotation may be slower and there’s no guarantee that the spans you annotate map to actual tokens later on. If your goal is to train a named entity recognizer, you should consider using the **same tokenizer** during annotation, to make sure that your data can be used. Also see the section on [efficient annotation for transformers](https://prodi.gy/docs/named-entity-recognition/#transformers-tokenizers) if you’re training a transformer-based model (e.g. BERT) with subword tokenization.

---

_[View the full topic](https://support.prodi.gy/t/network-applications-may-have-bugs/6749)._