SemEval-2016 task 10: Detecting minimal semantic units and their meanings (DiMSUM).

Nathan Schneider; Dirk Hovy; Anders Trærup Johannsen; Marine Carpuat

SemEval-2016 task 10: Detecting minimal semantic units and their meanings (DiMSUM).

Nathan Schneider, Dirk Hovy, Anders Trærup Johannsen, Marine Carpuat

Institut for Nordiske Studier og Sprogvidenskab

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Abstract

This task combines the labeling of multiword expressions and supersenses (coarse-grained classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems participated; the best scored 57.7% F1 in a multi-domain evaluation setting, indicating that the task remains largely unresolved. An error analysis reveals that a large number of instances in the data set are either hard cases, which no systems get right, or easy cases, which all systems correctly solve.

Originalsprog	Engelsk
Titel	Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)
Antal sider	14
Forlag	Association for Computational Linguistics
Publikationsdato	2016
Sider	546-559
ISBN (Trykt)	978-1-941643-95-2
Status	Udgivet - 2016
Begivenhed	10th International Workshop on Semantic Evaluation - San Diego, USA Varighed: 16 jun. 2016 → 17 jun. 2016 Konferencens nummer: 10

Konference

Konference	10th International Workshop on Semantic Evaluation
Nummer	10
Land/Område	USA
By	San Diego
Periode	16/06/2016 → 17/06/2016

Adgang til dokumentet

http://aclweb.org/anthology/S/S16/S16-1084.pdf

Biblioteksadgang?

Tjek tilgængelighed hos det Kgl. Bibliotek

Citationsformater

SemEval-2016 task 10: Detecting minimal semantic units and their meanings (DiMSUM). / Schneider, Nathan; Hovy, Dirk; Johannsen, Anders Trærup et al.
Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). Association for Computational Linguistics, 2016. s. 546-559.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Schneider, N, Hovy, D, Johannsen, AT & Carpuat, M 2016, SemEval-2016 task 10: Detecting minimal semantic units and their meanings (DiMSUM). i Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). Association for Computational Linguistics, s. 546-559, 10th International Workshop on Semantic Evaluation, San Diego, USA, 16/06/2016. <http://aclweb.org/anthology/S/S16/S16-1084.pdf>

@inproceedings{3c708030cf674d119a90d3b44269ae26,

title = "SemEval-2016 task 10: Detecting minimal semantic units and their meanings (DiMSUM).",

abstract = "This task combines the labeling of multiword expressions and supersenses (coarse-grained classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems participated; the best scored 57.7% F1 in a multi-domain evaluation setting, indicating that the task remains largely unresolved. An error analysis reveals that a large number of instances in the data set are either hard cases, which no systems get right, or easy cases, which all systems correctly solve.",

author = "Nathan Schneider and Dirk Hovy and Johannsen, {Anders Tr{\ae}rup} and Marine Carpuat",

year = "2016",

language = "English",

isbn = "978-1-941643-95-2",

pages = "546--559",

booktitle = "Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)",

publisher = "Association for Computational Linguistics",

note = "10th International Workshop on Semantic Evaluation ; Conference date: 16-06-2016 Through 17-06-2016",

}

TY - GEN

T1 - SemEval-2016 task 10

T2 - 10th International Workshop on Semantic Evaluation

AU - Schneider, Nathan

AU - Hovy, Dirk

AU - Johannsen, Anders Trærup

AU - Carpuat, Marine

N1 - Conference code: 10

PY - 2016

Y1 - 2016

N2 - This task combines the labeling of multiword expressions and supersenses (coarse-grained classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems participated; the best scored 57.7% F1 in a multi-domain evaluation setting, indicating that the task remains largely unresolved. An error analysis reveals that a large number of instances in the data set are either hard cases, which no systems get right, or easy cases, which all systems correctly solve.

AB - This task combines the labeling of multiword expressions and supersenses (coarse-grained classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems participated; the best scored 57.7% F1 in a multi-domain evaluation setting, indicating that the task remains largely unresolved. An error analysis reveals that a large number of instances in the data set are either hard cases, which no systems get right, or easy cases, which all systems correctly solve.

M3 - Article in proceedings

SN - 978-1-941643-95-2

SP - 546

EP - 559

BT - Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

PB - Association for Computational Linguistics

Y2 - 16 June 2016 through 17 June 2016

ER -