Text Generation
526 papers with code • 13 benchmarks • 66 datasets
Text generation is the task of generating text with the goal of appearing indistinguishable to human-written text.
( Image credit: Adversarial Ranking for Language Generation )
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
BookCorpus
PERSONA-CHAT
DailyDialog
COCO Captions
VQG
Sentence Compression
MTNT
Subtasks
-
Dialogue Generation
-
Data-to-Text Generation
-
Multi-Document Summarization
-
Text Style Transfer
-
Text Style Transfer
-
Paraphrase Generation
-
Spelling Correction
-
Conditional Text Generation
-
Table-to-Text Generation
-
Visual Storytelling
-
Text Infilling
-
Distractor Generation
-
News Generation
-
Question-Answer-Generation
-
Paper generation
-
Story Completion
-
Concept-To-Text Generation
-
Sonnet Generation
-
Fact-based Text Editing
Greatest papers with code
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
huggingface/transformers
•
•
NeurIPS 2020
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks.
Ranked #7 on
Question Answering
on Natural Questions (short)
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
huggingface/transformers
•
•
ICLR 2020
Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities.
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.
Ranked #3 on
Text Summarization
on X-Sum
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks.
Language Models are Unsupervised Multitask Learners
huggingface/transformers
•
•
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.
Ranked #1 on
Language Modelling
on enwik8
(using extra training data)
Stepwise Extractive Summarization and Planning with Structured Transformers
google-research/google-research
•
•
EMNLP 2020
We propose encoder-centric stepwise models for extractive summarization using structured transformers -- HiBERT and Extended Transformers.
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach
google-research/google-research
•
•
An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affordable for large-scale experiments.
fairseq: A Fast, Extensible Toolkit for Sequence Modeling
pytorch/fairseq
•
•
NAACL 2019
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.
Pre-trained Language Model Representations for Language Generation
pytorch/fairseq
•
•
NAACL 2019
Pre-trained language model representations have been successful in a wide range of language understanding tasks.
Mixture Models for Diverse Machine Translation: Tricks of the Trade
pytorch/fairseq
•
•
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
