Giter VIP home page Giter VIP logo

Comments (14)

jd7h avatar jd7h commented on July 20, 2024 3

Narrative Generation in the Wild: Methods from NaNoGenMo

In text generation, generating long stories is still a challenge. Coherence tends to decrease rapidly as the output length increases. Especially for generated stories, coherence of the narrative is an important quality aspect of the output text. In this paper we examine how narrative coherence is attained in the submissions of NaNoGenMo 2018, an online text generation event where participants are challenged to generate a 50,000 word novel. We list the main approaches that were used to generate coherent narratives and link them to scientific literature. Finally, we give recommendations on when to use which approach.

The paper "Narrative Generation in the Wild: Methods from NaNoGenMo" was accepted for the StoryNLP workshop at ACL (a computational linguistics conference). I'm happy to report that all ACL publications are open access. The full text of the paper can be found here: https://www.aclweb.org/anthology/papers/W/W19/W19-3407/

from 2018.

hugovk avatar hugovk commented on July 20, 2024 2

COMPUTERS READING COMPUTERS' WRITING

http://zachwhalen.net/pg/pres/elo18/

The slides of @zachwhalen's meta-review applied methods of quantitative literary analysis to texts produced in NaNoGenMos past, and presented at the Electronic Literature Organization Conference (ELO 2018), cites, well, everything by everyone!

from 2018.

jd7h avatar jd7h commented on July 20, 2024 2

Analysis of NaNoGenMo 2018 techniques in completed projects

For a research workshop on story generation, I've written a research paper about the different techniques in narrative generation that were used by NaNoGenMo 2018 participants, linking their projects to scientific papers and listing advantages and disadvantages to the different approaches.
I really want to do the discussed NaNoGenMo projects justice, so I've published my data on Github. The repo contains a CSV-file with references to all completed issues from NaNoGenMo 2018, with their programming languages, output type, main generation techniques, source data, etc. If you spot any mistakes in the CSV-file, feel free to send in a Pull Request.

The review committee of the conference has asked that preprints are not posted online during the review period (which is still ongoing atm), to avoid jeopardizing the double blind review procedure. After the review period is over, I'll put a link to the paper here, and in my repo.

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Artificial still life: Artist Robert Todonai programs robot to paint an original

AI-generated language shows more of Nakawaza's machine aesthetic. US internet artist Darius Kozemi launched the annual NaNoGenMo contest in 2013 – instead of writing a novel during November (NaNoWriMo) entries of 50,000 words have to be generated by a program. "What I want to see is code that produces alien novels that astound us with their sheer alien-ness," he has said. "Computers writing novels for computers, in a sense."

Past entries include The Psychotherapy of Racter or The Descent into Madness of Dr Eliza, in which two chatbots asked each other questions. Dial "S" for Sudoku's 50,000 words told of "Alice" solving eight Sudoku puzzles at length plus excerpts from her dream diary.

https://www.afr.com/technology/artificial-still-life-artist-robert-todonai-programs-robot-to-paint-an-original-20180913-h15bxi

Cites dariusk/NaNoGenMo-2015#184 by @spc476, NaNoGenMo/2017#116 by @greg-kennedy.

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Morning Cup of Coding

I've be noticing a lot of articles referencing NaNoGenMo. So I took a closer look and found that it's about a yearly challenge where participants write novel generators that produce a 50,000-word novel and share both the work and its source code. Interesting to note that this started by a one-off tweet by Darius Kazemi. The name is a play on NaNoWriMo, the National Novel Writing Month. Here are some articles I found: Scene/Sequel: Post-Mortem of a Fiction Generator, Why I love National Novel Generation Month, A Python script that writes 800-page children's books, How I turned my discarded novel drafts into an AI.

https://mailchi.mp/humanreadablemag/national-novel-generation-month-confessions-of-a-disk-cracker-creating-the-d-language-oh-mymorning-cup-of-coding-issue-76?e=503c3c6995

from 2018.

hugovk avatar hugovk commented on July 20, 2024

A Python Script That Writes 800-Page Children's Books

@zachwhalen's write-up of his 2017 entry, NaNoGenMo/2017#61.

http://www.zachwhalen.net/posts/a-python-script-that-writes-800-page-childrens-books/

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Emic Automata & Thematic Automata

@maetl's write-up of his 2017 entries, NaNoGenMo/2017#123 and NaNoGenMo/2017#129.

https://maetl.net/notes/storyboard/generative-writing-with-cellular-automata

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Fiction generator post-mortem: comic book generation

@enkiv2's write-up of his 2017 entry, NaNoGenMo/2017#54.

https://hackernoon.com/fiction-generator-post-mortem-comic-book-generation-9df847dd4ada

from 2018.

hugovk avatar hugovk commented on July 20, 2024

NaNoGenMo 2017

@MichaelMartinez's write-up of his 2017 entry, NaNoGenMo/2017#103.

http://www.caffeineindustries.com/nanogenmo-2017.html

from 2018.

hugovk avatar hugovk commented on July 20, 2024

NaNoGenMo 2017

@mathias's write-up, NaNoGenMo/2017#114.

http://blog.mattgauger.com/2017/12/01/nanogenmo-2017/

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Preliminary Poetics of Procedural Generation in Games

@ikarth's paper (PDF) in the Proceedings of DiGRA 2018 mentions several NaNoGenMo projects.

http://www.digra.org/wp-content/uploads/digital-library/DIGRA_2018_paper_166.pdf

from 2018.

enkiv2 avatar enkiv2 commented on July 20, 2024

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Neighbouring Communities: Interaction, Lessons and Opportunities

Building, understanding and sharing software that works in
creative spaces is increasingly popular and widespread, with
many communities outside of academic research interested
in pursuing questions highly relevant to Computational Creativity.
We report here on several notable communities in
the area: the Procedural Generation Jam, the National Novel
Generating Month, the Twitterbot community and the #CreativeAI
movement. By studying these communities, we benefit
from different perspectives on building creative software,
as well as how communities of like-minded people form,
grow and sustain themselves. We reflect on these communities
as sources of lessons for our field and opportunities
for future growth and knowledge exchange, as well as raising
awareness of sources of inspiration beyond academia.

A study paper (PDF) by Michael Cook and Simon Colton.

http://metamakersinstitute.com/home/wp-content/uploads/2018/06/Communities_ICCC18.pdf

from 2018.

hugovk avatar hugovk commented on July 20, 2024

Forget NaNoWriMo, Read These Mad 'NaNoGenMo' Novels, Generated By Computer Programs

It's November, which means National Novel Writing Month, or NaNoWriMo, is in full swing. It also means its programmatic pal NaNoGenMo — National Novel Generation Month — is up and about too. And yes, it's exactly what it sounds like.

https://www.gizmodo.com.au/2018/11/forget-nanowrimo-read-these-mad-nanogenmo-novels-generated-by-computer-programs/

Cites NaNoGenMo/2017#127 by @filiph and NaNoGenMo/2017#130 by @hugovk.

from 2018.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.