Predicting Concrete and Abstract Entities in Modern Poetry
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Predicting Concrete and Abstract Entities in Modern Poetry. / Caccavale, Fiammetta; Søgaard, Anders.
Proceedings of 33nd AAAI Conference on Artificial Intelligence, AAAI 2019. AAAI Press, 2019. p. 858-864.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Predicting Concrete and Abstract Entities in Modern Poetry
AU - Caccavale, Fiammetta
AU - Søgaard, Anders
PY - 2019
Y1 - 2019
N2 - One dimension of modernist poetry is introducing entities in surprising contexts, such as wheelbarrow in Bob Dylan’s feel like falling in love with the first woman I meet/ putting her in a wheelbarrow. This paper considers the problem of teaching a neural language model to select poetic entities, based on local context windows. We do so by fine-tuning and evaluating language models on the poetry of American modernists, both on seen and unseen poets, and across a range of experimental designs. We also compare the performance of our poetic language model to human, professional poets. Our main finding is that, perhaps surprisingly, modernist poetry differs most from ordinary language when entities are concrete, like wheelbarrow, and while our fine-tuning strategy successfully adapts to poetic language in general, outperforming professional poets, the biggest error reduction is observed with concrete entities.
AB - One dimension of modernist poetry is introducing entities in surprising contexts, such as wheelbarrow in Bob Dylan’s feel like falling in love with the first woman I meet/ putting her in a wheelbarrow. This paper considers the problem of teaching a neural language model to select poetic entities, based on local context windows. We do so by fine-tuning and evaluating language models on the poetry of American modernists, both on seen and unseen poets, and across a range of experimental designs. We also compare the performance of our poetic language model to human, professional poets. Our main finding is that, perhaps surprisingly, modernist poetry differs most from ordinary language when entities are concrete, like wheelbarrow, and while our fine-tuning strategy successfully adapts to poetic language in general, outperforming professional poets, the biggest error reduction is observed with concrete entities.
U2 - 10.1609/aaai.v33i01.3301858
DO - 10.1609/aaai.v33i01.3301858
M3 - Article in proceedings
SP - 858
EP - 864
BT - Proceedings of 33nd AAAI Conference on Artificial Intelligence, AAAI 2019
PB - AAAI Press
T2 - 33rd AAAI Conference on Artificial Intelligence - AAAI 2019
Y2 - 27 January 2019 through 1 February 2019
ER -
ID: 240626959