Natural Language Processing
 
Edit

Text Generation

823 papers with code • 158 benchmarks • 100 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:

( Image credit: Adversarial Ranking for Language Generation )

Libraries

Use these libraries to find Text Generation models and implementations
huggingface/transformers
7 papers
67,953
UFAL-DSG/tgen
6 papers
199
facebookresearch/fairseq
3 papers
18,832
pytorch/fairseq
3 papers
18,832
See all 6 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Show and Tell: A Neural Image Caption Generator

karpathy/neuraltalk • • CVPR 2015

Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions.

69
Paper
Code

Generating Sequences With Recurrent Neural Networks

karpathy/char-rnn • • 4 Aug 2013

This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time.

56
Paper
Code

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

huggingface/transformers • • ACL 2020

We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of the original sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token.

31
Paper
Code

SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

LantaoYu/SeqGAN • • 18 Sep 2016

As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data.

22
Paper
Code

Learning Transferable Visual Models From Natural Language Supervision

openai/CLIP • • 26 Feb 2021

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.

22
Paper
Code

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models

ashwinkalyan/dbs • • 7 Oct 2016

We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.

20
Paper
Code

BERTScore: Evaluating Text Generation with BERT

Tiiiger/bert_score • • ICLR 2020

We propose BERTScore, an automatic evaluation metric for text generation.

12
Paper
Code

Language Models are Unsupervised Multitask Learners

PaddlePaddle/PaddleNLP • • Preprint 2019

Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.

10
Paper
Code

Unified Language Model Pre-training for Natural Language Understanding and Generation

microsoft/unilm • • NeurIPS 2019

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.

8
Paper
Code

MASS: Masked Sequence to Sequence Pre-training for Language Generation

microsoft/MASS • • 7 May 2019

Pre-training and fine-tuning, e. g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks.

7
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy