Update README.md
Browse files
README.md
CHANGED
@@ -6,12 +6,12 @@ library_name: transformers
|
|
6 |
---
|
7 |
# Opinerium: Fine-Tuned flan-T5 for Generating Subjective Inquiries
|
8 |
|
9 |
-
## Introduction
|
10 |
-
Opinerium is a groundbreaking model fine-tuned from the flan-T5-large architecture, designed to generate poll or opinion-based questions from textual content. This innovation aims to foster public engagement by inviting personal perspectives on various topics, primarily focusing on news media posts. Unlike traditional models that target factual questions with definitive answers, Opinerium delves into the realm of subjective questioning, enabling a deeper interaction with trending media topics.
|
11 |
-
|
12 |
## Abstract
|
13 |
This model is the culmination of extensive research into generating subjective inquiries to enhance public interaction with media content. Our approach diverges from the norm by shifting focus from objective to subjective question generation, aiming to elicit personal preferences and opinions based on given texts. Employing fine-tuning techniques on flan-T5 and GPT3 models for Seq2Seq generation, this model has undergone rigorous evaluation against a custom dataset of 40,000 news articles, supplemented with human-generated questions. The comparative analysis highlights Opinerium's superiority, especially when measured against a suite of lexical and semantic metrics.
|
14 |
|
|
|
|
|
|
|
15 |
## Model Training
|
16 |
Opinerium was meticulously fine-tuned using the flan-T5 variants from the Hugging Face platform, specifically tailored for the task of generating subjective questions. The fine-tuning process was meticulously crafted to address the unique challenges of subjective question generation, such as capturing nuances in tone, understanding context deeply, and generating engaging, open-ended questions that prompt personal reflection.
|
17 |
|
@@ -22,9 +22,6 @@ The training was conducted on a Tesla P100-16GB GPU, utilizing the Transformer l
|
|
22 |
- Learning rate: Initially set to 3e-4, with careful adjustments based on performance metrics to ensure steady and effective learning.
|
23 |
- Optimizer: AdaFactor was chosen for its efficiency and effectiveness in handling sparse data and adapting learning rates dynamically.
|
24 |
|
25 |
-
### Challenges and Solutions
|
26 |
-
One of the primary challenges in fine-tuning was adapting the model to generate questions that not only relate to the text but also invite subjective responses. To address this, we incorporated feedback loops with human evaluators to iteratively refine the model's outputs. Additionally, we employed techniques such as attention mechanism tweaking and targeted data augmentation to improve the model's ability to understand and generate nuanced, engaging questions.
|
27 |
-
|
28 |
## Dataset
|
29 |
The training dataset comprised 40,000 news articles spanning a wide array of topics, ensuring the model's exposure to diverse content and question formats. Each article was paired with binary subjective questions, providing a rich ground for learning how to formulate inquiries that elicit personal opinions. The multilingual nature of the original articles added an extra layer of complexity, which was mitigated by translating all content into English to leverage the extensive training data available for English-centric models.
|
30 |
|
@@ -41,9 +38,6 @@ Poll: Do you think a universal charging socket helps sustainability?
|
|
41 |
## Conclusion
|
42 |
Opinerium stands at the forefront of subjective question generation, offering a novel tool for engaging with content across multiple domains. By fostering the creation of opinion-based inquiries, it encourages more interactive and thought-provoking discussions, contributing to a richer public discourse.
|
43 |
|
44 |
-
## Acknowledgments
|
45 |
-
We extend our deepest appreciation to all the researchers, developers, and contributors who played a part in bringing Opinerium to life. Their dedication and innovative spirit have been instrumental in achieving this milestone.
|
46 |
-
|
47 |
---
|
48 |
|
49 |
## Hugging Face Web UI Usage
|
|
|
6 |
---
|
7 |
# Opinerium: Fine-Tuned flan-T5 for Generating Subjective Inquiries
|
8 |
|
|
|
|
|
|
|
9 |
## Abstract
|
10 |
This model is the culmination of extensive research into generating subjective inquiries to enhance public interaction with media content. Our approach diverges from the norm by shifting focus from objective to subjective question generation, aiming to elicit personal preferences and opinions based on given texts. Employing fine-tuning techniques on flan-T5 and GPT3 models for Seq2Seq generation, this model has undergone rigorous evaluation against a custom dataset of 40,000 news articles, supplemented with human-generated questions. The comparative analysis highlights Opinerium's superiority, especially when measured against a suite of lexical and semantic metrics.
|
11 |
|
12 |
+
## Introduction
|
13 |
+
Opinerium is a groundbreaking model fine-tuned from the flan-T5-large architecture, designed to generate poll or opinion-based questions from textual content. This innovation aims to foster public engagement by inviting personal perspectives on various topics, primarily focusing on news media posts. Unlike traditional models that target factual questions with definitive answers, Opinerium delves into the realm of subjective questioning, enabling a deeper interaction with trending media topics.
|
14 |
+
|
15 |
## Model Training
|
16 |
Opinerium was meticulously fine-tuned using the flan-T5 variants from the Hugging Face platform, specifically tailored for the task of generating subjective questions. The fine-tuning process was meticulously crafted to address the unique challenges of subjective question generation, such as capturing nuances in tone, understanding context deeply, and generating engaging, open-ended questions that prompt personal reflection.
|
17 |
|
|
|
22 |
- Learning rate: Initially set to 3e-4, with careful adjustments based on performance metrics to ensure steady and effective learning.
|
23 |
- Optimizer: AdaFactor was chosen for its efficiency and effectiveness in handling sparse data and adapting learning rates dynamically.
|
24 |
|
|
|
|
|
|
|
25 |
## Dataset
|
26 |
The training dataset comprised 40,000 news articles spanning a wide array of topics, ensuring the model's exposure to diverse content and question formats. Each article was paired with binary subjective questions, providing a rich ground for learning how to formulate inquiries that elicit personal opinions. The multilingual nature of the original articles added an extra layer of complexity, which was mitigated by translating all content into English to leverage the extensive training data available for English-centric models.
|
27 |
|
|
|
38 |
## Conclusion
|
39 |
Opinerium stands at the forefront of subjective question generation, offering a novel tool for engaging with content across multiple domains. By fostering the creation of opinion-based inquiries, it encourages more interactive and thought-provoking discussions, contributing to a richer public discourse.
|
40 |
|
|
|
|
|
|
|
41 |
---
|
42 |
|
43 |
## Hugging Face Web UI Usage
|