cliff_summ
Contrastive Summarization Framework
Provides a framework for improving the faithfulness and factuality of abstractive summarization models through contrastive learning
Code for EMNLP 2021 paper "CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization"
45 stars
1 watching
8 forks
Language: Python
last commit: about 3 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 ibm/max-text-summarizer | Provides a pre-trained text summarization model that can be deployed as a web service in a Docker container | 27 |
 deepfryed/ots | Provides Ruby bindings to an open text summarizer library. | 43 |
 ryanwangzf/medclip | A deep learning framework for contrastive learning from unpaired medical images and texts | 473 |
 marcelrobeer/contrastiveexplanation | Provides explanations for why an instance has a certain outcome by contrasting it with what would have happened if the outcome had been different. | 45 |
 ssoper/summarize | A Ruby wrapper for the Open Text Summarizer library to summarize text content. | 204 |
 voidism/diffcse | An unsupervised contrastive learning framework for learning sentence embeddings sensitive to differences between original and edited sentences. | 292 |
 jaywongwang/densevideocaptioning | An implementation of a dense video captioning model with attention-based fusion and context gating | 149 |
 qinbinli/moon | A framework for collaborative machine learning model training that leverages similarity between model representations to correct local training. | 267 |
 chengzhag/deeppanocontext | A PyTorch-based framework for 3D scene understanding with holistic context graph and relation-based optimization in panoramic images | 90 |
 jihyongoh/demfi | Develops algorithms to restore sharp images from blurry ones and interpolate missing frames in video sequences with improved accuracy | 81 |
 keepcosmos/readability | An Elixir library that extracts and curates primary readable content from web pages. | 260 |
 cogcomp/saul | A language that facilitates designing machine learning models with flexible configurations | 64 |
 davidtellez/contrastive-predictive-coding | An unsupervised machine learning algorithm that extracts meaningful patterns from data using contrastive predictive coding | 527 |
 kata-ai/indosum | Provides a benchmark dataset and tools for training text summarization models in the Indonesian language. | 77 |
 yuliang-liu/monkey | An end-to-end image captioning system that uses large multi-modal models and provides tools for training, inference, and demo usage. | 1,849 |