Guess who? Multilingual Approach For The Automated Generation Of Author-Stylized Poetry

Tikhonov, Alexey; Yamshchikov, Ivan P.

doi:10.1109/slt.2018.8639573

Cited by 22 publications

(21 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying the obtained sound symbolism information to generative tasks, one can expect to generate more expressive poetry in line with the results of (Auracher et al, 2010). This new approach combined with such generative methods as (Potash et al, 2016), (Tikhonov and Yamshchikov, 2018), (Vechtomova et al, 2018) or (Wołk et al, 2019). The possibility of testing specific associations between sounds and semantics computationally without any behavioral laboratory experiments or surveys might also significantly facilitate further studies of semantic symbolism.…”

Section: Resultsmentioning

confidence: 99%

Dyr Bul Shchyl. Proxying Sound Symbolism With Word Embeddings

Yamshchikov

Shibaev²,

Tikhonov

2019

Proceedings of the 3rd Workshop on Evaluating Vector Space Representations For

Self Cite

View full text Add to dashboard Cite

This paper explores modern word embeddings in the context of sound symbolism. Using basic properties of the representations space one can construct semantic axes. A method is proposed to measure if the presence of individual sounds in a given word shifts its semantics of that word along a specific axis. It is shown that, in accordance with several experimental and statistical results, word embeddings capture symbolism for certain sounds. * https://en.wikipedia.org/wiki/Dyr bul shchyl 1 We also want to explicitly state that we do not see any reason why other embeddings that to a certain extent support semantic arithmetic can not be used for this task.

show abstract

Section: Resultsmentioning

confidence: 99%

Dyr Bul Shchyl. Proxying Sound Symbolism With Word Embeddings

Yamshchikov

Shibaev²,

Tikhonov

2019

Proceedings of the 3rd Workshop on Evaluating Vector Space Representations For

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper is an extension of work presented initially in [1] enhanced with the reasoning and experiments described in [2] and [3].…”

Section: Introductionmentioning

confidence: 93%

“…However, as the generated sequence gets longer, the network often 'forgets' the parameters of the document. We want to develop a model to address the problem given in (1). To do that, we support our model at every step with the embeddings of the document that is currently being analyzed (these are variables from the set S on which we want to condition our model during the generation process, such as the name of a document or its author).…”

Section: Modelmentioning

confidence: 99%

Learning Literary Style End-to-end with Artificial Neural Networks

Yamshchikov

Tikhonov²

2019

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

This paper addresses the generation of stylized texts in a multilingual setup. A long short-term memory (LSTM) language model with extended phonetic and semantic embeddings is shown to capture poetic style when trained end-to-end without any expert knowledge. Phonetics seems to have a comparable contribution to the overall model performance as the information on the target author. The quality of the generated texts is estimated through bilingual evaluation understudy (BLEU), a new cross-entropy based metric, and a survey of human peers. When a style of target author is recognized by the humans, they do not seem to distinguish generated texts and originals.

show abstract

“…Different proposals for the language unit are considered [8]. Words [2] [10] are the most common element of learning and creating process, but there are also many systems based on characters or even phonemes [11]. In our work we introduce a new approach, using sub-word units for our implementation.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning and Sub-Word-Unit Approach in Written Art Generation

Wołk

Zawadzka-Gosk

Czarnowski³

2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Automatic poetry generation is novel and interesting application of natural language processing research. It became more popular during the last few years due to the rapid development of technology and neural computing power. This line of research can be applied to the study of linguistics and literature, for social science experiments, or simply for entertainment. The most effective known method of artificial poem generation uses recurrent neural networks (RNN). We also used RNNs to generate poems in the style of Adam Mickiewicz. Our network was trained on the 'Sir Thaddeus' poem. For data pre-processing, we used a specialized stemming tool, which is one of the major innovations and contributions of this work. Our experiment was conducted on the source text, divided into sub-word units (at a level of resolution close to syllables). This approach is novel and is not often employed in the published literature. The subwords units seem to be a natural choice for analysis of the Polish language, as the language is morphologically rich due to cases, gender forms and a large vocabulary. Moreover, 'Sir Thaddeus' contains rhymes, so the analysis of syllables can be meaningful. We verified our model with different settings for the temperature parameter, which controls the randomness of the generated text. We also compared our results with similar models trained on the same text but divided into characters (which is the most common approach alongside the use of full word units). The differences were tremendous. Our solution generated much better poems that were able to follow the metre and vocabulary of the source data text.

show abstract

Guess who? Multilingual Approach For The Automated Generation Of Author-Stylized Poetry

Cited by 22 publications

References 20 publications

Dyr Bul Shchyl. Proxying Sound Symbolism With Word Embeddings

Dyr Bul Shchyl. Proxying Sound Symbolism With Word Embeddings

Learning Literary Style End-to-end with Artificial Neural Networks

Deep Learning and Sub-Word-Unit Approach in Written Art Generation

Contact Info

Product

Resources

About