Standard
Living Machines: A study of atypical animacy. / Coll-Ardanuy, Mariona; Nanni, Federico; Beelen, Kaspar et al.
Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, 2020. p. 4534–4545.
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Coll-Ardanuy, M, Nanni, F, Beelen, K, Hosseini, K, Ahnert, R, Lawrence, J
, McDonough, K, Tolfo, G, Wilson, DCS & McGillivray, B 2020,
Living Machines: A study of atypical animacy. in
Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, pp. 4534–4545.
https://doi.org/10.18653/v1/2020.coling-main.400APA
Coll-Ardanuy, M., Nanni, F., Beelen, K., Hosseini, K., Ahnert, R., Lawrence, J.
, McDonough, K., Tolfo, G., Wilson, D. C. S., & McGillivray, B. (2020).
Living Machines: A study of atypical animacy. In
Proceedings of the 28th International Conference on Computational Linguistics (pp. 4534–4545). International Committee on Computational Linguistics.
https://doi.org/10.18653/v1/2020.coling-main.400Vancouver
Coll-Ardanuy M, Nanni F, Beelen K, Hosseini K, Ahnert R, Lawrence J et al.
Living Machines: A study of atypical animacy. In Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics. 2020. p. 4534–4545 doi: 10.18653/v1/2020.coling-main.400
Author
Coll-Ardanuy, Mariona ; Nanni, Federico ; Beelen, Kaspar et al. /
Living Machines: A study of atypical animacy. Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, 2020. pp. 4534–4545
Bibtex
@inproceedings{37c6a66df07d4d168d84897bf257ed3f,
title = "Living Machines: A study of atypical animacy",
abstract = "This paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate objects, specifically machines, are given animate attributes. To address it, we have created the first dataset for atypical animacy detection, based on nineteenth-century sentences in English, with machines represented as either animate or inanimate. Our method builds upon recent innovations in language modeling, specifically BERT contextualized word embeddings, to better capture fine-grained contextual properties of words. We present a fully unsupervised pipeline, which can be easily adapted to different contexts, and report its performance on an established animacy dataset and our newly introduced resource. We show that our method provides a substantially more accurate characterization of atypical animacy, especially when applied to highly complex forms of language use.",
author = "Mariona Coll-Ardanuy and Federico Nanni and Kaspar Beelen and Kasra Hosseini and Ruth Ahnert and Jon Lawrence and Katherine McDonough and Giorgia Tolfo and Wilson, {Daniel C. S.} and Barbara McGillivray",
year = "2020",
month = may,
day = "22",
doi = "10.18653/v1/2020.coling-main.400",
language = "English",
pages = "4534–4545",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
publisher = "International Committee on Computational Linguistics",
}
RIS
TY - GEN
T1 - Living Machines: A study of atypical animacy
AU - Coll-Ardanuy, Mariona
AU - Nanni, Federico
AU - Beelen, Kaspar
AU - Hosseini, Kasra
AU - Ahnert, Ruth
AU - Lawrence, Jon
AU - McDonough, Katherine
AU - Tolfo, Giorgia
AU - Wilson, Daniel C. S.
AU - McGillivray, Barbara
PY - 2020/5/22
Y1 - 2020/5/22
N2 - This paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate objects, specifically machines, are given animate attributes. To address it, we have created the first dataset for atypical animacy detection, based on nineteenth-century sentences in English, with machines represented as either animate or inanimate. Our method builds upon recent innovations in language modeling, specifically BERT contextualized word embeddings, to better capture fine-grained contextual properties of words. We present a fully unsupervised pipeline, which can be easily adapted to different contexts, and report its performance on an established animacy dataset and our newly introduced resource. We show that our method provides a substantially more accurate characterization of atypical animacy, especially when applied to highly complex forms of language use.
AB - This paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate objects, specifically machines, are given animate attributes. To address it, we have created the first dataset for atypical animacy detection, based on nineteenth-century sentences in English, with machines represented as either animate or inanimate. Our method builds upon recent innovations in language modeling, specifically BERT contextualized word embeddings, to better capture fine-grained contextual properties of words. We present a fully unsupervised pipeline, which can be easily adapted to different contexts, and report its performance on an established animacy dataset and our newly introduced resource. We show that our method provides a substantially more accurate characterization of atypical animacy, especially when applied to highly complex forms of language use.
U2 - 10.18653/v1/2020.coling-main.400
DO - 10.18653/v1/2020.coling-main.400
M3 - Conference contribution/Paper
SP - 4534
EP - 4545
BT - Proceedings of the 28th International Conference on Computational Linguistics
PB - International Committee on Computational Linguistics
ER -
