# Fill mask with subwords

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffill-mask-with-subwords%2F6598%3E%5C
**Category:** 🤗Transformers\
**Created:** [June 6, 2021, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffill-mask-with-subwords%2F6598 "2021-06-06T07:09:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ockapuh](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ockapuh/32/33342_2.png) [@ockapuh](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fockapuh)%5C
**Post date:** [June 6, 2021, 7:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffill-mask-with-subwords%2F6598%2F1 "2021-06-06T07:09:25Z")

</div>

Hi everyone.

Is it possible to use the fill mask pipeline with subwords? In spanish pronouns appear sometimes attached to the verbo.

For a given verbo “dile”, i´m trying to mask the pronoun “le” to compare its probability with another pronoun “la”.

I´ve tried things like “di[MASK]”, and targer like [“le”,“la”] and ["##le","##la"], but result is always unknown tokens.

Is it even possible to solve it? I have also tried to mask the whole verb, but since the tokenizer splits it it doesn´t work.

I cannot add every verb+pronoun to the bert vocab, and the pronouns are already there by themselves.

Thank everyone.