# Sequence segmentation

**URL:** <https://support.prodi.gy/t/sequence-segmentation/164>\
**Category:** Uncategorized\
**Tags:** usage\
**Created:** [December 27, 2017, 3:17pm UTC](https://support.prodi.gy/t/sequence-segmentation/164 "2017-12-27T15:17:27Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![RahulKulhari](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/rahulkulhari/32/109_2.png) [@RahulKulhari](https://support.prodi.gy/u/RahulKulhari)\
**Post date:** [December 27, 2017, 3:17pm UTC](https://support.prodi.gy/t/sequence-segmentation/164/1 "2017-12-27T15:17:27Z")

</div>

Is there any plan to release sequence segmentation into classes for large text like 400 chars ?

for eg.

> In single-label ZSL, each label can be uniquely represented  
> in a semantics space; in other words, the meaning  
> of a label and the relatedness between two different labels  
> are all fixed. In this paper, we refer to such semantics as  
> global semantics. To obtain a global semantic representation,  
> there are two approaches in general: manually converting  
> a label into a list of pre-defined attributes that can  
> characterize all possible labels in a specific domain [5],  
> and automatically learning a continuous semantic embedding  
> space from linguistic resources, e.g., semantic  
> embedding learning from Wikipedia leads to the wellknown  
> word2vec space.

Tag sub sequence into multiple classes

---

<div class="post-metadata">

**Author:** ![honnibal](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/honnibal/32/35_2.png) [@honnibal](https://support.prodi.gy/u/honnibal)\
**Post date:** [December 28, 2017, 11:49pm UTC](https://support.prodi.gy/t/sequence-segmentation/164/2 "2017-12-28T23:49:18Z")

</div>

Could you explain a little further? It would be helpful to have a link to the publication — it’s hard to make anything of just that paragraph!
