3260 papers • 126 benchmarks • 313 datasets
Text generation is the task of generating text with the goal of appearing indistinguishable to human-written text. This task if more formally known as "natural language generation" in the literature. Text generation can be addressed with Markov processes or deep generative models like LSTMs. Recently, some of the most advanced methods for text generation include BART, GPT and other GAN-based approaches. Text generation systems are evaluated either through human ratings or automatic evaluation metrics like METEOR, ROUGE, and BLEU. Further readings: The survey: Text generation models in deep learning Modern Methods for Text Generation ( Image credit: Adversarial Ranking for Language Generation )
(Image credit: Papersgraph)
These leaderboards are used to track progress in text-generation-5
Use these libraries to find text-generation-5 models and implementations
This paper presents a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image.
BART is presented, a denoising autoencoder for pretraining sequence-to-sequence models, which matches the performance of RoBERTa on GLUE and SQuAD, and achieves new state-of-the-art results on a range of abstractive dialogue, question answering, and summarization tasks.
It is demonstrated that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet.
Diverse Beam Search is proposed, an alternative to BS that decodes a list of diverse outputs by optimizing for a diversity-augmented objective and consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.
Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update.
This work proposes BERTScore, an automatic evaluation metric for text generation that correlates better with human judgments and provides stronger model selection performance than existing metrics.
A new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks that compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks.
The \textit{Transformers} library is an open-source library that consists of carefully engineered state-of-the art Transformer architectures under a unified API and a curated collection of pretrained models made by and available for the community.
Adding a benchmark result helps the community track progress.