DeepTingle

By Ahmed Khalifa, Gabriella A. B. Barros, Julian Togelius. 2017

32 citations recorded by the source corpus.

DeepTingle is a text prediction and classification system trained on the collected works of the renowned fantastic gay erotica author Chuck Tingle. Whereas the writing assistance tools you use everyday (in the form of predictive text, translation, grammar checking and so on) are trained on generic, purportedly"neutral"datasets, DeepTingle is trained on a very specific, internally consistent but externally arguably eccentric dataset. This allows us to foreground and confront the norms embedded in data-driven creativity and productivity assistance tools. As such tools effectively function as extensions of our cognition into technology, it is important to identify the norms they embed within themselves and, by extension, us. DeepTingle is realized as a web application based on LSTM networks and the GloVe word embedding, implemented in JavaScript with Keras-JS.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mark O. Riedl
2. Brent Harrison
3. Lara J. Martin
4. Prithviraj Ammanabrolu
5. Pradyumna Tambwekar
6. Animesh Mehta
7. Murtaza Dhuliawala
8. Chris Purdy

In Computer Vision and Pattern Recognition

1. Mark O. Riedl
2. Brent Harrison
3. Prithviraj Ammanabrolu
4. Lara J. Martin
5. Pradyumna Tambwekar
6. Shahbuland Matiana
7. Louis Castricato
8. Chris Purdy

In Model Architectures

1. Lara J. Martin
2. Prithviraj Ammanabrolu
3. Mark O. Riedl
4. Brent Harrison
5. Chris Purdy

Citations in the corpus

• Controllable Neural Story Generation via Reinforcement Learning (2018, methodology): “Roemmele and Gordon (2015) and Khalifa et al. (2017) used Long Short-Term Memory (LSTM) networks (Hochreiter and Schmidhuber 1997) to generate stories.”
• Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning (2022, methodology): “based—capable of producing stories (Roemmele, 2016; Khalifa et al., 2017; Martin et al., 2018; Clark et al., 2018; Fan et al., 2018; Ammanabrolu et al., 2021).”
• Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks (2021, background): “Recently, recurrent neural networks (RNNs) have been proposed as a means of automated story generation (Roem-Copyright mele 2016; Martin et al. 2017; Khalifa, Barros, and Togelius 2017).”
• Event Representations for Automated Story Generation with Deep Neural Nets (2017, background): “Khalifa et al. (2017) argue that stories are better generated using recurrent neural networks trained on highly specialized textual corpora, such as the body of works from a single, prolific author.”
• Controllable Neural Story Plot Generation via Reward Shaping (2018, unknown): “Neural language modeling-based story generation approaches in particular [Roemmele and Gordon, 2015; Khalifa et al., 2017; Gehring et al., 2017; Martin et al., 2018] are prone to generating stories with little aim since each sentence, event, word,”