Emotional Poetry Generation

Astigarraga, Aitzol; Martínez-Otzeta, José María; Rodriguez, Igor; Sierra, Basilio; Lazkano, Elena

doi:10.1007/978-3-319-66429-3_32

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Astigarraga et al [8] proposed a model to generate poetry in the Basque language using two Markov chains. Poetry is one of the exhibitions of traditional Basque culture, especially in events and competitions.…”

Section: Related Workmentioning

confidence: 99%

Arabic Poems Generation using LSTM, Markov-LSTM and Pre-Trained GPT-2 Models

Hakami¹,

Alqarni²,

Almutairi³

et al. 2021

Advances in Machine Learning

View full text Add to dashboard Cite

Nowadays, artificial intelligence applications are increasingly integrated into every aspect of our lives. One of the newest applications in artificial intelligence and natural language is text generation, which has received considerable attention in recent years due to the advancements in deep learning and language modeling techniques. Text generation has been investigated in different domains to generate essays and books. Writing poetry is a highly complex intellectual process for humans that requires creativity and high linguistic capability. Several researchers have examined automatic poem generation using deep learning techniques, but only a few attempts have looked into Arabic poetry. Attempts to evaluate the generated pomes coherence in terms of meaning and themes still require further investigation. In this paper, we examined character-based LSTM, Markov-LSTM, and pre-trained GPT-2 models in generating Arabic praise poems. The results of all models were evaluated using BLEU scores and human evaluation. The results of both BLEU scores and human evaluation show that the Markov-LSTM has outperformed both LSTM and GPT-2, where the character-based LSTM model gave the lowest yields in terms of meaning due to its tendency to create unknown words.

show abstract

Section: Related Workmentioning

confidence: 99%

Arabic Poems Generation using LSTM, Markov-LSTM and Pre-Trained GPT-2 Models

Hakami¹,

Alqarni²,

Almutairi³

et al. 2021

Advances in Machine Learning

View full text Add to dashboard Cite

show abstract

“…Structural, stylistic, and generative features on generative poetry have been studied [25]. Emotional poetry generation has been experimented [32].…”

Section: Literature Surveymentioning

confidence: 99%

Po-Miner: A Web Mining Poem Generator and its Security Model

et al. 2021

View full text Add to dashboard Cite

The growing importance of data science and analytics has led to innovative applications spread across various fields and genres over a short period of time. While data and the associated science are challenges in themselves, the applications using them to solve existing problems have instigated and brought to the spotlight new obstacles. To explore the new found understanding of the data middle ground between natural language and computer grammar, we propose a data science application model, Po-Miner. Po-Miner is an online poem generator based on scraped online web data. Along with syllable counts, rhymes, and other poem notions, Po-Miner induces clustering, and other data mining techniques via the Po-Select algorithm for random poem generation. Though a random poem lacks completeness and meaning, the very aspect of randomness brings in creativity and depth. Po-Miner operates on the grammar rules to generate a poem structured in a 5 × 5 grid. The paper presents the Po-Miner model, implementation, poems, analysis, and further, extends to its applicability in the security domain using the gird poem model. The poem generated by the Po-Miner can be used as an alternative and an enhancement to the one-time password system as its application. The Po-Miner appears to be a promising application that can be extended to several other domains.

show abstract

Emotional Poetry Generation

Cited by 2 publications

References 13 publications

Arabic Poems Generation using LSTM, Markov-LSTM and Pre-Trained GPT-2 Models

Arabic Poems Generation using LSTM, Markov-LSTM and Pre-Trained GPT-2 Models

Po-Miner: A Web Mining Poem Generator and its Security Model

Contact Info

Product

Resources

About