On the Transferability of Neural Models of Morphological Analogies

Safa Alsaidi; Amandine Decker; Puthineath Lay; Esteban Marquer; Pierre-Alexandre Murena; Miguel Couceiro

doi:10.1007/978-3-030-93736-2_7

On the Transferability of Neural Models of Morphological Analogies

Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

5 Citations (Scopus)

Abstract

Analogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.

Original language	English
Title of host publication	Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Subtitle of host publication	International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II
Publisher	Springer
ISBN (Electronic)	978-3-030-93736-2
ISBN (Print)	9783030937355
DOIs	https://doi.org/10.1007/978-3-030-93736-2_7
Publication status	Published - Sept 2021
MoE publication type	A4 Conference publication
Event	European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - Virtual, Online Duration: 13 Sept 2021 → 17 Sept 2021

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	1524
ISSN (Electronic)	1865-0929

Conference

Conference	European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
Abbreviated title	ECML PKDD
City	Virtual, Online
Period	13/09/2021 → 17/09/2021

Access to Document

10.1007/978-3-030-93736-2_7

Cite this

Alsaidi, S., Decker, A., Lay, P., Marquer, E., Murena, P.-A., & Couceiro, M. (2021). On the Transferability of Neural Models of Morphological Analogies. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II (Communications in Computer and Information Science; Vol. 1524). Springer. https://doi.org/10.1007/978-3-030-93736-2_7

Alsaidi, Safa ; Decker, Amandine ; Lay, Puthineath et al. / On the Transferability of Neural Models of Morphological Analogies. Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II. Springer, 2021. (Communications in Computer and Information Science).

@inproceedings{3debbad46a9f43e0a0abe16631913e55,

title = "On the Transferability of Neural Models of Morphological Analogies",

abstract = "Analogical proportions are statements expressed in the form {"}A is to B as C is to D{"} and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model. ",

author = "Safa Alsaidi and Amandine Decker and Puthineath Lay and Esteban Marquer and Pierre-Alexandre Murena and Miguel Couceiro",

note = "| openaire: EC/H2020/952215/EU//TAILOR ; European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD ; Conference date: 13-09-2021 Through 17-09-2021",

year = "2021",

month = sep,

doi = "10.1007/978-3-030-93736-2_7",

language = "English",

isbn = "9783030937355",

series = "Communications in Computer and Information Science",

publisher = "Springer",

booktitle = "Machine Learning and Principles and Practice of Knowledge Discovery in Databases",

address = "Germany",

}

Alsaidi, S, Decker, A, Lay, P, Marquer, E, Murena, P-A & Couceiro, M 2021, On the Transferability of Neural Models of Morphological Analogies. in Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II. Communications in Computer and Information Science, vol. 1524, Springer, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Virtual, Online, 13/09/2021. https://doi.org/10.1007/978-3-030-93736-2_7

On the Transferability of Neural Models of Morphological Analogies. / Alsaidi, Safa; Decker, Amandine; Lay, Puthineath et al.
Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II. Springer, 2021. (Communications in Computer and Information Science; Vol. 1524).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - On the Transferability of Neural Models of Morphological Analogies

AU - Alsaidi, Safa

AU - Decker, Amandine

AU - Lay, Puthineath

AU - Marquer, Esteban

AU - Murena, Pierre-Alexandre

AU - Couceiro, Miguel

N1 - | openaire: EC/H2020/952215/EU//TAILOR

PY - 2021/9

Y1 - 2021/9

N2 - Analogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.

AB - Analogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.

UR - https://hal.inria.fr/INRIA/hal-03313591v1

U2 - 10.1007/978-3-030-93736-2_7

DO - 10.1007/978-3-030-93736-2_7

M3 - Conference article in proceedings

SN - 9783030937355

T3 - Communications in Computer and Information Science

BT - Machine Learning and Principles and Practice of Knowledge Discovery in Databases

PB - Springer

T2 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

Y2 - 13 September 2021 through 17 September 2021

ER -

Alsaidi S, Decker A, Lay P, Marquer E, Murena PA, Couceiro M. On the Transferability of Neural Models of Morphological Analogies. In Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021, Virtual Event, September 13-17, 2021, Proceedings, Part II. Springer. 2021. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-93736-2_7

On the Transferability of Neural Models of Morphological Analogies

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this