yangheng95/PyABSA

Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;

What it solves

PyABSA provides a modular framework for Aspect-based Sentiment Analysis (ABSA), allowing users to move from research to production by unifying the training, evaluation, and inference processes for various ABSA subtasks.

How it works

It offers a unified API that supports multiple ABSA tasks, including Aspect Polarity Classification (APC), Aspect Term Extraction & Polarity Classification (ATEPC), and Aspect Sentiment Triplet Extraction (ASTE). The framework includes a model zoo with auto-downloading checkpoints, tools for dataset preparation and human-in-the-loop annotation, and text augmentation for classification and adversarial defense.

Who it’s for

It is designed for researchers and developers who need to perform detailed sentiment analysis that goes beyond general sentiment, focusing on specific aspects of a text.

Highlights

  • Unified API: Simplifies training, evaluation, and inference across different ABSA tasks.
  • Model Zoo: Provides ready-to-use checkpoints that are automatically downloaded.
  • Comprehensive Task Support: Handles everything from simple polarity classification to complex quadruple extraction (aspect, category, opinion, sentiment).
  • Tooling: Includes visualization for evaluation metrics and text augmentation for adversarial defense.

Related

  • Dispatch
    SetFitABSA: Few-Shot Aspect Based Sentiment Analysis

    Hugging Face and Intel Labs introduced SetFitABSA, a prompt-less, few-shot framework for Aspect-Based Sentiment Analysis that outperforms larger generative models like Llama 2 and T5 in low-data scenarios.

  • Project
    mesa/mesa

    A Python framework for agent-based modeling that allows users to create, visualize, and analyze simulations of complex systems.

  • Project
    sstary/SSRS

    A PyTorch collection of deep learning models for remote sensing semantic segmentation, featuring single-modal, multimodal fusion, and unsupervised domain adaptation techniques.

  • Project
    sloria/TextBlob

    A Python library for processing textual data that provides a simple API for common NLP tasks like sentiment analysis, tagging, and classification.

  • Project
    facebookresearch/mmf

    MMF is a modular PyTorch-based framework for vision and language multimodal research, providing reference implementations of state-of-the-art models and tools for distributed training.