IBM / low-resource-text-classification-framework
Research framework for low resource text classification that allows the user to experiment with classification models and active learning strategies on a large number of sentence classification datasets, and to simulate real-world scenarios. The framework is easily expandable to new classification models, active learning strategies and datasets.
☆99Updated 2 years ago
Alternatives and similar repositories for low-resource-text-classification-framework:
Users that are interested in low-resource-text-classification-framework are comparing it to the libraries listed below
- [NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self…☆201Updated 2 years ago
- Collection of NLP model explanations and accompanying analysis tools☆145Updated last year
- Multi^2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (Findings of ACL: EMNLP 2020)☆57Updated 2 years ago
- Source code for paper "Learning from Noisy Labels for Entity-Centric Information Extraction", EMNLP 2021☆55Updated 3 years ago
- Master thesis with code investigating methods for incorporating long-context reasoning in low-resource languages, without the need to pre…☆32Updated 3 years ago
- ☆85Updated 3 years ago
- Self-supervised NER prototype - updated version (69 entity types - 17 broad entity groups). Uses pretrained BERT models with no fine tuni…☆79Updated 2 years ago
- ☆93Updated 2 years ago
- [EMNLP 2021] Improving and Simplifying Pattern Exploiting Training☆154Updated 2 years ago
- ☆120Updated 4 years ago
- CrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)☆124Updated 4 years ago
- https://arxiv.org/pdf/1909.04054☆78Updated 2 years ago
- A benchmark for understanding and evaluating rationales: http://www.eraserbenchmark.com/☆96Updated 2 years ago
- ☆57Updated 2 years ago
- ☆67Updated 3 years ago
- Automatically detect errors in annotated corpora.☆46Updated last year
- Framework for weakly supervised deep sequence taggers, focused on named entity recognition☆79Updated last year
- State of the art Semantic Sentence Embeddings☆98Updated 2 years ago
- Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling☆47Updated 5 years ago
- The PyTorch implementation the Smooth Grad [https://arxiv.org/pdf/1706.03825.pdf] and Integrated Gradients [https://arxiv.org/pdf/1703.01…☆46Updated 4 years ago
- ☆63Updated last year
- Examples for aligning, padding and batching sequence labeling data (NER) for use with pre-trained transformer models☆65Updated 2 years ago
- Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper☆132Updated last year
- SUPERT: Unsupervised multi-document summarization evaluation & generation☆92Updated 2 years ago
- This repo supports various cross-lingual transfer learning & multilingual NLP models.☆92Updated last year
- Evaluation script for named entity recognition (NER) systems based on entity-level F1 score.☆71Updated 3 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".☆63Updated 4 years ago
- Data/Code Repository for https://api.semanticscholar.org/CorpusID:218470122☆128Updated 5 months ago
- Code accompanying EMNLP 2020 paper "Cold-start Active Learning through Self-supervised Language Modeling".☆40Updated 3 years ago
- Materials for the EMNLP 2020 Tutorial on "Interpreting Predictions of NLP Models"☆198Updated 4 years ago