Text Generation
Text generation is the task of generating text with the goal of appearing indistinguishable to human-written text.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Subtasks
Greatest papers with code
MaskGAN: Better Text Generation via Filling in the______
Additionally, these models are typically trained via maxi- mum likelihood and teacher forcing.
#3 best model for
Multivariate Time Series Imputation
on Basketball Players Movement
HuggingFace's Transformers: State-of-the-art Natural Language Processing
In this paper, we present Huggingface's Transformers library, a library for state-of-the-art NLP, making these developments available to the community by gathering state-of-the-art general-purpose pretrained models under a unified API together with an ecosystem of libraries, examples, tutorials and scripts targeting many downstream NLP tasks.
Language Models are Unsupervised Multitask Learners
Preprint 2019
• huggingface/pytorch-transformers
• 
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
SOTA for Language Modelling on Text8 (using extra training data)
COMMON SENSE REASONING DOCUMENT SUMMARIZATION LANGUAGE MODELLING MACHINE TRANSLATION QUESTION ANSWERING READING COMPREHENSION TEXT GENERATION
Generating Sequences With Recurrent Neural Networks
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.
Boundary-Seeking Generative Adversarial Networks
We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator.
fairseq: A Fast, Extensible Toolkit for Sequence Modeling
NAACL 2019
• facebookresearch/fairseq-py
•
fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks.
Mixture Models for Diverse Machine Translation: Tricks of the Trade
• pytorch/fairseq
•
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
• pytorch/fairseq
•
We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.
IMAGE CAPTIONING MACHINE TRANSLATION QUESTION GENERATION TEXT GENERATION TIME SERIES
Sequence-to-Sequence Learning as Beam-Search Optimization
EMNLP 2016
• facebookresearch/fairseq-py
•
In this work, we introduce a model and beam-search training scheme, based on the work of Daume III and Marcu (2005), that extends seq2seq to learn global sequence scores.
#16 best model for
Machine Translation
on IWSLT2015 German-English
Show and Tell: A Neural Image Caption Generator
CVPR 2015
• karpathy/neuraltalk
• 
Experiments on several datasets show the accuracy of the model and the fluency of the language it learns solely from image descriptions.