Filters








8 Hits in 0.73 sec

DopeLearning

Eric Malmi, Pyry Takala, Hannu Toivonen, Tapani Raiko, Aristides Gionis
2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16  
We present a rap lyrics generation method that captures both of these aspects. First, we develop a prediction model to identify the next line of existing lyrics from a set of candidate next lines.  ...  Writing rap lyrics requires both creativity to construct a meaningful, interesting story and lyrical skills to produce complex rhyme patterns, which form the cornerstone of good flow.  ...  Acknowledgments We would like to thank Jelena Luketina, Miquel Perelló Nieto, and Vikram Kamath for useful comments on the manuscript, and Stephen Fenech for helping with the implementation and optimization  ... 
doi:10.1145/2939672.2939679 dblp:conf/kdd/MalmiTTRG16 fatcat:pnkjr4hfxjfariupiyciuzzc7m

A general framework for learning prosodic-enhanced representation of rap lyrics

Hongru Liang, Haozheng Wang, Qian Li, Jun Wang, Guandong Xu, Jiawei Chen, Jin-Mao Wei, Zhenglu Yang
2019 World wide web (Bussum)  
A comprehensive empirical evaluation demonstrates that the proposed framework outperforms the state-of-the-art approaches under various metrics in different rap lyrics learning tasks.  ...  Learning and analyzing rap lyrics is a significant basis for many web applications, such as music recommendation, automatic music categorization, and music information retrieval, due to the abundant source  ...  A previous work [20] generated 100 verses by using 100 random rap lines with the DopeLearning approach. In this work, we use the same 100 first rap lines, and generate 100 verses.  ... 
doi:10.1007/s11280-019-00672-2 fatcat:cdunorjugbdvhpvrbgml4wm6n4

G-Rap: interactive text synthesis using recurrent neural network suggestions

Udo Schlegel, Eren Cakmak, Juri Buchmüller, Daniel A. Keim
2018 The European Symposium on Artificial Neural Networks  
G-Rap enables an iterative result generation process that allows a user to evaluate the outputs with contextual statistics.  ...  Finding the best neural network configuration for a given goal can be challenging, especially when it is not possible to assess the output quality of a network automatically.  ...  DopeLearning [8] generates rap lyrics by combining existing lines from rap songs. The user is able to create rap songs by inserting a set of words and let the system suggest new lines.  ... 
dblp:conf/esann/SchlegelCBK18 fatcat:govkkba4dbffzbwzuiqkq6yffm

A Ballad of the Mexicas: Automated Lyrical Narrative Writing

Divya Singh, Margareta Ackerman, Rafael Pérez y Pérez
2017 International Conference on Computational Creativity  
In addition to lyrics by MABLE, we have also included an artifact by a rap lyrics generator (Hieu Nguyen 2009) .  ...  Another system for Rap lyrics, DopeLearning by (Malmi et al. 2015) , combines sentences from existing human-made lyrics.  ... 
dblp:conf/icccrea/SinghAP17 fatcat:ufsfondsdjb23hp2hfi4ftej54

Proceedings of the 2nd Symposium on Problem-solving, Creativity and Spatial Reasoning in Cognitive Systems, ProSocrates 2017 [article]

Ana-Maria Olteteanu, Zoe Falomir
2019 arXiv   pre-print
This was the second edition of this symposium which aims to bring together researchers interested in spatial reasoning, problem solving and creativity.  ...  We would like also to thank the members of the Scientific Committee for their valuable work during the reviewing process and the additional reviews.  ...  We also thank Easychair, which was used to manage paper submissions and reviewing the proceedings, and CEUR Workshop Proceedings (CEUR-WS.org) for indexing these proceedings.  ... 
arXiv:1901.04199v1 fatcat:zxbxjbb245gyhgvz2jvuoogvci

Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting

Peter Potash, Alexey Romanov, Anna Rumshisky
2018 Proceedings of the Second Workshop on Stylistic Variation   unpublished
We provide a corpus of lyrics for 13 rap artists, annotated for stylistic similarity, which allows us to assess the feasibility of manual evaluation for generated verse.  ...  The goal of this paper is to develop evaluations methods for one such task, ghostwriting of rap lyrics, and to provide an explicit, quantifiable foundation for the goals and future directions for this  ...  Dopelearning: A computational approach to rap lyrics generation. arXiv preprint arXiv:1505.04771. Gonçalo Oliveira, Raquel Hervás, Alberto Díaz, and Pablo Gervás. 2014.  ... 
doi:10.18653/v1/w18-1604 fatcat:5iaj2ov2gbbcfki7buiahvympi

Augmenting Poetry Composition with Verse by Verse

David Uthus, Maria Voitovich, R.j. Mical
2022 Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track   unpublished
We have created a group of AI poets, styled after various American classic poets, that are able to offer as suggestions generated lines of verse while a user is composing a poem.  ...  This includes a generative model, which is tasked with generating a large corpus of lines of verse offline and which are then stored in an index, and a dual-encoder model that is tasked with recommending  ...  Users were then allowed to edit lines and use suggested lines as seeds for further generation of suggestions. DopeLearning (Malmi et al., 2016) was focused on generating rap lyrics.  ... 
doi:10.18653/v1/2022.naacl-industry.3 fatcat:ja5dphgdivgwtpbvxxp247t3ri

Akceptace právní osobnosti v případě umělé inteligence

Jan Zibner
2018 Revue pro právo a technologie  
Generally speaking, the artificial intelligence is a software with a variety of capabilities and it is an object of legal relations.  ...  However, before the shift to the position of subject, a legal personality as a fundamental legal status must be granted to the artificial intelligence.  ...  DopeLearning: A Computational Approach to Rap Lyrics Generation [online]. In: SIGKDD. The Association for Computing Machinery, 2016 [cit. 6. 3. 2018]. Dostupný z: https://www.jukedeck.com/; srov.  ... 
doi:10.5817/rpt2018-1-2 fatcat:fpqyv7iodjbopiijphqxs24cz4