jeffchy/RE2RNN
Source code for the EMNLP 2020 paper "Cold-Start and Interpretability: Turning Regular Expressions intoTrainable Recurrent Neural Networks"
This project helps natural language processing researchers or practitioners convert complex textual patterns, defined as regular expressions, into a special type of neural network. You input your regular expressions and text data, and it outputs a trainable recurrent neural network that can classify text. It's designed for researchers exploring neural network interpretability or working with limited training data for text classification.
115 stars. No commits in the last 6 months.
Use this if you need to transform word-level regular expressions into trainable recurrent neural networks for text classification tasks, especially in 'cold-start' scenarios or when interpretability is crucial.
Not ideal if you are looking for an off-the-shelf text classification solution or if your primary goal is maximum performance without needing to understand the model's decision-making process.
Stars
115
Forks
19
Language
Python
License
—
Category
Last pushed
Aug 24, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/jeffchy/RE2RNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
JayYip/m3tl
BERT for Multitask Learning
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
sileod/tasknet
Easy modernBERT fine-tuning and multi-task learning
graykode/toeicbert
TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.