limteng-rpi/mlmt
Code for the paper "A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling" (ACL2018)
This project provides code for training natural language processing (NLP) models that can identify and classify elements within text, like names or parts of speech. It takes raw text data with specific labels and outputs a trained model capable of performing sequence labeling tasks. It's intended for researchers or NLP practitioners working with text from multiple languages or needing to train models efficiently on limited data.
No commits in the last 6 months.
Use this if you need to train robust text labeling models across several languages simultaneously, especially when individual languages have scarce training data.
Not ideal if you only need a basic, monolingual named entity recognition model; a simpler solution might be more appropriate.
Stars
29
Forks
7
Language
Python
License
—
Category
Last pushed
Nov 06, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/limteng-rpi/mlmt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...