atapour/rank-over-class
Source code for the training pipeline of the text ranking model used in the paper entitled "Rank over Class: The Untapped Potential of Ranking in Natural Language Processing" (https://arxiv.org/abs/2009.05160).
This project helps machine learning practitioners improve the accuracy of text-based applications like sentiment analysis or spam detection. It takes in pairs of text sequences and their relevance scores, then trains a Transformer network to rank them by relevance. The output is a highly accurate text ranking model that can be converted into classification labels.
No commits in the last 6 months.
Use this if you are a machine learning engineer working on text classification tasks where traditional methods struggle due to imbalanced datasets or ambiguous text.
Not ideal if you do not have access to an NVIDIA GPU or are looking for a plug-and-play solution without the need for model training and configuration.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Sep 02, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/atapour/rank-over-class"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yuanzhoulvpi2017/DocumentSearch
基于sentence transformers和chatglm实现的文档搜索工具
IAmPara0x/Yuno
Yuno is context based search engine for anime.
canjiali/PARADE
code and data to faciliate BERT/ELECTRA for document ranking. Details refer to the paper -...
gentaiscool/miners
MINERS ⛏️: The semantic retrieval benchmark for evaluating multilingual language models. (EMNLP...
D-Roberts/transformers-retrieval-ranking-nli-ECIR2021
Multilingual retrieval, ranking and natural language inference with transformers (mBERT);...