language:
- en
base_model:
- google-t5/t5-large
library_name: transformers
Model: t5-standard-ABSA
Task: Aspect-Based Sentiment Analysis (ABSA) - specifically, Aspect Pair Sentiment Extraction
Model Description
t5-standard-ABSA is a fine-tuned t5-large model designed to perform Aspect-Based Sentiment Analysis (ABSA), particularly for the task of Aspect Pair Sentiment Extraction.
Dataset
The dataset consisted of customer reviews of mobile apps that were originally unannotated. They were scraped and collected by Martens et al. for their paper titled "On the Emotion of Users in App Reviews". The data was annotated via the OpenAI API and the model gpt-3.5-turbo, with each review labeled for specific aspects (e.g., UI, functionality, performance) and the corresponding sentiment (positive, negative, neutral).
Training was performed using Hugging Face's Trainer API in Google Colaboratory using 1 L4 GPU with 22.5 GB of VRAM.
Training took around 3 hours with a cost of about 30 compute units.
All code can be found at my My GitHub Repository
Hyperparameters
Some of the key hyperparameters used for fine-tuning:
Batch Size: 8
Gradient Accumulation Steps: 1
Optimizer: AdamW
Learning Rate: 1e-4
Epochs: 5
Max Sequence Length: 512