Text Generation

252 papers with code · Natural Language Processing

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

Latest papers with code

DART: Open-Domain Structured Data Record to Text Generation

6 Jul 2020Yale-LILY/dart

We consider the structured data record input as a set of RDF entity-relation triples, a format widely used for knowledge representation and semantics description.

DOMAIN GENERALIZATION TEXT GENERATION

33
06 Jul 2020

Unsupervised Evaluation of Interactive Dialog with DialoGPT

23 Jun 2020shikib/fed

It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research.

TEXT GENERATION

3
23 Jun 2020

Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

ACL 2020 microsoft/EA-VQ-VAE

Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs.

TEXT GENERATION

15
15 Jun 2020

A Generative Model for Joint Natural Language Understanding and Generation

ACL 2020 andy194673/Joint-NLU-NLG

This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG.

NATURAL LANGUAGE UNDERSTANDING TASK-ORIENTED DIALOGUE SYSTEMS TEXT GENERATION

12
12 Jun 2020

Cascaded Text Generation with Markov Transformers

1 Jun 2020harvardnlp/cascaded-generation

The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies.

MACHINE TRANSLATION TEXT GENERATION

96
01 Jun 2020

Fluent Response Generation for Conversational Question Answering

ACL 2020 abaheti95/QADialogSystem

In this work, we propose a method for situating QA responses within a SEQ2SEQ NLG approach to generate fluent grammatical answer responses while maintaining correctness.

DATA AUGMENTATION QUESTION ANSWERING TEXT GENERATION

8
21 May 2020

Syntax-guided Controlled Generation of Paraphrases

18 May 2020malllabiisc/SGCP

In these methods, syntactic-guidance is sourced from a separate exemplar sentence.

PARAPHRASE GENERATION

27
18 May 2020

MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform

ACL 2020 microsoft/MixingBoard

We present MixingBoard, a platform for quickly building demos with a focus on knowledge grounded stylized text generation.

TEXT GENERATION

13
17 May 2020

Token Manipulation Generative Adversarial Network for Text Generation

6 May 2020twidddj/tokmangan

MaskGAN opens the query for the conditional language model by filling in the blanks between the given tokens.

LANGUAGE MODELLING TEXT GENERATION

5
06 May 2020