Abstract
| Original language | English |
|---|---|
| Title of host publication | The 1st InternationalWorkshop on Computational Approaches to Historical Language Change : Proceedings of the Workshop |
| Number of pages | 11 |
| Place of Publication | Stroudsburg |
| Publisher | ACL |
| Publication date | Jul 2019 |
| Pages | 56-66 |
| ISBN (Electronic) | 978-1-950737-31-4 |
| Publication status | Published - Jul 2019 |
| MoE publication type | A4 Article in conference proceedings |
| Event | International Workshop on Computational Approaches to Historical Language Change - Florence, Italy Duration: 2 Aug 2019 → 2 Aug 2019 Conference number: 1 |
Fields of Science
- 112 Statistics and probability
- 6121 Languages
Cite this
}
Approaches to Historical Language Change, Florence, Italy, 02/08/2019.
GASC: Genre-Aware Semantic Change for Ancient Greek. / Perrone, Valerio; Palma, Marco; Hengchen, Simon; Vatri, Alessandro; Smith, Jim Q.; McGillivray, Barbara.
The 1st InternationalWorkshop on Computational Approaches to Historical Language Change: Proceedings of the Workshop. Stroudsburg : ACL, 2019. p. 56-66.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
TY - GEN
T1 - GASC: Genre-Aware Semantic Change for Ancient Greek
AU - Perrone, Valerio
AU - Palma, Marco
AU - Hengchen, Simon
AU - Vatri, Alessandro
AU - Smith, Jim Q.
AU - McGillivray, Barbara
PY - 2019/7
Y1 - 2019/7
N2 - Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document time-stamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy (the fact that a word has several senses) and semantic change (the process of acquiring, losing, or changing senses), and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts' genre to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, our model achieves improved predictive performance compared to the state of the art.
AB - Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document time-stamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy (the fact that a word has several senses) and semantic change (the process of acquiring, losing, or changing senses), and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts' genre to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, our model achieves improved predictive performance compared to the state of the art.
KW - 112 Statistics and probability
KW - 6121 Languages
M3 - Conference contribution
SP - 56
EP - 66
BT - The 1st InternationalWorkshop on Computational Approaches to Historical Language Change
PB - ACL
CY - Stroudsburg
ER -