Comments (1)
Thanks @s20ss.
This is described in this section.
I did this using text-to-text approach. There are two ways we can do this
- Provide the context as input and ask the model to generate ans spans separated by
sep
token.
So for this examplePython is a programming language. Created by Guido Van Rossum and first released in 1991.
ans could bePython
,a programming language
,Guido Van Rossum
and1991
. So we can process input as follows
input text: Python is a programming language. Created by Guido Van Rossum and first released in 1991.
target text: Python <sep> a programming language <sep> Guido Van Rossum <sep> 1991 <sep>
But there's one problem with this approach. What if a particular answer span is repeated more than once in the context and depending on where it occurs it could be an answer or not, so how can we make the model to understand the position of answer spans.
So the second approach is (which is used in this project) to highlight the sentence which contains answer spans and ask the model to generate answers only for that sentence. In SQuAD we know the start index of of the answers, so here's how it works
- split the input into sentences.
- If a sentence contains ans spans highlight that sentence and prepare a training example ,and the target will be answer spans in that sentence separated by
<sep>
So for above example, we will have 2 input examples as there are two sentences and both of them contain answer spans
so first
input text: <hl> Python is a programming language. <hl> Created by Guido Van Rossum and first released in 1991.
target text: Python <sep> a programming language <sep>
and second
input text: Python is a programming language. <hl> Created by Guido Van Rossum and first released in 1991. <hl>
target text: Guido Van Rossum <sep> 1991 <sep>
the assumption is that, this should force the model to understand the position of the spans. And also for QG, ans spans are highlighted within the context, so we need to know the position of the answer spans. With this approach at inference time we can highlight each sentence, extract ans from that sentence then highlight those answers and ask the model to generate the question.
There's another way to do this, which is using BERT like models. Basically we can model the task of answer extraction as unconditional span extraction. This is described in this paper . I decided to not use this as I wanted to keep everything uniform and as simple as possible.
Hope this helps. ;)
from question_generation.
Related Issues (20)
- Can we generate questions based on the type of question?
- abbrevation in question generated are some times coming in small case such as it instead of IT/ai instead AI etc
- Retraining the model valhalla/t5-small-e2e-qg with questions only
- Model trained for e2e-qg does not generate any questions
- How to get the `char end` and `char start` in the generated question and answers from valhalla/t5-base-qg-hl? HOT 1
- error while using onnx runtime
- Requirements.txt needed HOT 1
- How would you fix these issues to get the project running HOT 1
- Fine tuning a T5 model with another language
- How can i get this to work with transformer 4.x HOT 1
- Loss Function multi-task
- AttributeError: module 'dill._dill' has no attribute 'PY3' HOT 5
- requirements.txt file would be very useful
- unexepect <pad> HOT 1
- ValueError: substring not found HOT 1
- How can i run this project with transformers 4?. HOT 1
- Which Bart model used in the pipeline
- Is it possible to add a parameter for number of question to be generated in the question generation model
- No such file or directory: '/root/.cache/huggingface/datasets/squad_multitask/highlight_qg_format/1.0.0/dataset_info.json' HOT 5
- Fine-tuning using GPU HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from question_generation.