Recent advances in recurrent neural networks

H Salehinejad, S Sankar, J Barfett, E Colak… - arxiv preprint arxiv …, 2017 - arxiv.org
Recurrent neural networks (RNNs) are capable of learning features and long term
dependencies from sequential and time-series data. The RNNs have a stack of non-linear …

FUDGE: Controlled text generation with future discriminators

K Yang, D Klein - arxiv preprint arxiv:2104.05218, 2021 - arxiv.org
We propose Future Discriminators for Generation (FUDGE), a flexible and modular method
for controlled text generation. Given a pre-existing model G for generating text from a …

Style transfer in text: Exploration and evaluation

Z Fu, X Tan, N Peng, D Zhao, R Yan - Proceedings of the AAAI …, 2018 - ojs.aaai.org
The ability to transfer styles of texts or images, is an important measurement of the
advancement of artificial intelligence (AI). However, the progress in language style transfer …

A survey on intelligent poetry generation: Languages, features, techniques, reutilisation and evaluation

HG Oliveira - Proceedings of the 10th international conference on …, 2017 - aclanthology.org
Poetry generation is becoming popular among researchers of Natural Language
Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that …

When creators meet the metaverse: A survey on computational arts

LH Lee, Z Lin, R Hu, Z Gong, A Kumar, T Li, S Li… - arxiv preprint arxiv …, 2021 - arxiv.org
The metaverse, enormous virtual-physical cyberspace, has brought unprecedented
opportunities for artists to blend every corner of our physical surroundings with digital …

Creative writing with a machine in the loop: Case studies on slogans and stories

E Clark, AS Ross, C Tan, Y Ji, NA Smith - Proceedings of the 23rd …, 2018 - dl.acm.org
As the quality of natural language generated by artificial intelligence systems improves,
writing interfaces can support interventions beyond grammar-checking and spell-checking …

Help me write a poem: Instruction tuning as a vehicle for collaborative poetry writing

T Chakrabarty, V Padmakumar, H He - arxiv preprint arxiv:2210.13669, 2022 - arxiv.org
Recent work in training large language models (LLMs) to follow natural language
instructions has opened up exciting opportunities for natural language interface design …

PlotMachines: Outline-conditioned generation with dynamic plot state tracking

H Rashkin, A Celikyilmaz, Y Choi, J Gao - arxiv preprint arxiv:2004.14967, 2020 - arxiv.org
We propose the task of outline-conditioned story generation: given an outline as a set of
phrases that describe key characters and events to appear in a story, the task is to generate …

Guided open vocabulary image captioning with constrained beam search

P Anderson, B Fernando, M Johnson… - arxiv preprint arxiv …, 2016 - arxiv.org
Existing image captioning models do not generalize well to out-of-domain images
containing novel scenes or objects. This limitation severely hinders the use of these models …

Targeted phishing campaigns using large scale language models

R Karanjai - arxiv preprint arxiv:2301.00665, 2022 - arxiv.org
In this research, we aim to explore the potential of natural language models (NLMs) such as
GPT-3 and GPT-2 to generate effective phishing emails. Phishing emails are fraudulent …