# Is it possible to tokenize multiple text modalities?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-it-possible-to-tokenize-multiple-text-modalities%2F1566%3E%5C
**Category:** 🤗Transformers\
**Created:** [October 15, 2020, 5:38pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-it-possible-to-tokenize-multiple-text-modalities%2F1566 "2020-10-15T17:38:54Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![erezsheffi](https://avatars.discourse-cdn.com/v4/letter/e/f04885/32.png) [@erezsheffi](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ferezsheffi)%5C
**Post date:** [October 15, 2020, 5:38pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-it-possible-to-tokenize-multiple-text-modalities%2F1566%2F1 "2020-10-15T17:38:55Z")

</div>

Do the tokenizers in the transformers package support tokenization of triplets?  
For example:

Lets assume we’re dealing with a VQA dataset. Each entry in the dataset contains the following information:

1. Image name
2. Question
3. 5 possible answers (1 is correct)
4. Image captions

I would like to able to represent each input as:  
[CLS] Q + [SEP] + A + [SEP] + CAPTIONS

---

<div class="post-metadata">

**Author:** ![UriVendict](https://avatars.discourse-cdn.com/v4/letter/u/6bbea6/32.png) [@UriVendict](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FUriVendict)%5C
**Post date:** [September 1, 2022, 8:27am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fis-it-possible-to-tokenize-multiple-text-modalities%2F1566%2F2 "2022-09-01T08:27:51Z")

</div>

Did you figure out an answer to this?