TY - GEN
T1 - Room to Glo
T2 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
AU - Shoemark, Philippa
AU - Liza, Farhana Ferdousi
AU - Nguyen, Dong
AU - Hale, Scott A.
AU - McGillivray, Barbara
N1 - Funding Information:
This work was supported by The Alan Tur ing Institute under the UK Engineering and Physical Sciences Research Council (EPSRC) grant EP/N510129/1. P.S. was supported in part by the EPSRC Centre for Doctoral Training in Data Science, funded by the UK EP-SRC (grant EP/L016427/1) and the University of Edinburgh. D.N. was supported by Turing award TU/A/000006 and B.McG. by Turing award TU/A/000010 (RG88751). S.A.H. was supported in part by The Volkswagen Foundation.
Funding Information:
This work was supported by The Alan Turing Institute under the UK Engineering and Physical Sciences Research Council (EPSRC) grant EP/N510129/1. P.S. was supported in part by the EPSRC Centre for Doctoral Training in Data Science, funded by the UK EPSRC (grant EP/L016427/1) and the University of Edinburgh. D.N. was supported by Turing award TU/A/000006 and B.McG. by Turing award TU/A/000010 (RG88751). S.A.H. was supported in part by The Volkswagen Foundation.
Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2019
Y1 - 2019
N2 - Word embeddings are increasingly used for the automatic detection of semantic change; yet, a robust evaluation and systematic comparison of the choices involved has been lacking. We propose a new evaluation framework for semantic change detection and find that (i) using the whole time series is preferable over only comparing between the first and last time points; (ii) independently trained and aligned embeddings perform better than continuously trained embeddings for long time periods; and (iii) that the reference point for comparison matters. We also present an analysis of the changes detected on a large Twitter dataset spanning 5.5 years.
AB - Word embeddings are increasingly used for the automatic detection of semantic change; yet, a robust evaluation and systematic comparison of the choices involved has been lacking. We propose a new evaluation framework for semantic change detection and find that (i) using the whole time series is preferable over only comparing between the first and last time points; (ii) independently trained and aligned embeddings perform better than continuously trained embeddings for long time periods; and (iii) that the reference point for comparison matters. We also present an analysis of the changes detected on a large Twitter dataset spanning 5.5 years.
UR - http://www.scopus.com/inward/record.url?scp=85084291181&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084291181
SP - 66
EP - 76
BT - EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PB - Association for Computational Linguistics
Y2 - 3 November 2019 through 7 November 2019
ER -