# Keyword generation using T5
**URL:**
**Author:**  [@JulesBelveze](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJulesBelveze)%5C
**Post date:** [May 6, 2022, 8:54am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fkeyword-generation-using-t5%2F17597%2F1 "2022-05-06T08:54:09Z")
Hey folks,
I am trying to fine-tune a T5 for some sort of **keyword generation**.
Due to the way I’ve created my dataset (extracting keywords from a summary of the actual text) the gold keywords that I have might not be present in the actual text. For this reason a token classification task would not work. Thus my idea of text to text generation !
Ideally this would work like:
```auto
>>> input_text = "question: What are the keywords? context: [DOCUMENT]"
>>> inputs = tokenizer(input_text)
>>> outputs = model.generate(**inputs)
>>> print(tokenizer.decode(outputs))
finance - crisis - stocks
```
My main concern is that LM are actually trained to generate syntactically correct sentence. Would this be problematic?
Has anyone tried to perform a similar task or has any suggestion on how I could tackle this problem from a different angle? 🤓
Cheers!
---
**Author:**  [@ahadda5](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fahadda5)%5C
**Post date:** [July 14, 2022, 11:14am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fkeyword-generation-using-t5%2F17597%2F2 "2022-07-14T11:14:35Z")
Interested to know how this one is coming along?
---
**Author:**  [@iratxeMoya](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FiratxeMoya)%5C
**Post date:** [September 12, 2022, 9:04am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fkeyword-generation-using-t5%2F17597%2F3 "2022-09-12T09:04:27Z")
What model are you using? QA model or Seq2seqLM model? I’m just trying to do something similar…
---
**Author:**  [@JulesBelveze](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJulesBelveze)%5C
**Post date:** [September 12, 2022, 9:21am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fkeyword-generation-using-t5%2F17597%2F4 "2022-09-12T09:21:39Z")
I actually tried both and none led to promising result (I didn’t really dug much tbh)
---
**Author:**  [@loghai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Floghai)%5C
**Post date:** [November 2, 2022, 4:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fkeyword-generation-using-t5%2F17597%2F5 "2022-11-02T04:41:11Z")
Hi, so text2text is not returning promising results, should I try token classification if my keywords are present in the context?