GaryYufei/ACL2021MF
Source Code For ACL 2021 Paper "Mention Flags (MF): Constraining Transformer-based Text Generators"
This project offers an approach to training and evaluating text generation models that produce more accurate and constrained outputs. It takes raw text data for tasks like common sense generation or end-to-end data-to-text, and trains models to generate text that precisely references entities. Researchers and practitioners working with natural language generation would use this to ensure their models produce highly controlled and relevant text.
No commits in the last 6 months.
Use this if you are a researcher or NLP engineer focused on improving the factual accuracy and specific referencing capabilities of transformer-based text generation models.
Not ideal if you are looking for a pre-packaged application or a non-developer-centric tool for general text generation without a focus on research into model constraints.
Stars
20
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/GaryYufei/ACL2021MF"
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...