SemEval-2016 Task~10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

Nathan Schneider; Dirk Hovy; Anders Johannsen; Marine Carpuat

SemEval-2016 Task~10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

Nathan Schneider, Dirk Hovy, Anders Johannsen, Marine Carpuat

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	Proceedings of SemEval-2016
Place of Publication	San Diego, California, USA
Publisher	Association for Computational Linguistics
Pages	546–559
Number of pages	14
ISBN (Print)	978-1-941643-95-2
Publication status	Published - Jun 2016
Event	10th International Workshop on Semantic Evaluation - San Diego, United States Duration: 16 Jun 2016 → 17 Jun 2016 http://alt.qcri.org/semeval2016/

Conference

Conference	10th International Workshop on Semantic Evaluation
Abbreviated title	SemEval 2016
Country/Territory	United States
City	San Diego
Period	16/06/16 → 17/06/16
Internet address	http://alt.qcri.org/semeval2016/

Access to Document

S16-1084Final published version, 469 KB

https://aclweb.org/anthology/S/S16/

Cite this

@inproceedings{f25489fc609e4f5995428215ee0b2124,

title = "SemEval-2016 Task\textasciitilde{}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 Anders Johannsen and Marine Carpuat",

year = "2016",

month = jun,

language = "English",

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

pages = "546–559",

booktitle = "Proceedings of SemEval-2016",

publisher = "Association for Computational Linguistics",

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

url = "http://alt.qcri.org/semeval2016/",

}

Schneider, N, Hovy, D, Johannsen, A & Carpuat, M 2016, SemEval-2016 Task~10: Detecting Minimal Semantic Units and their Meanings (DiMSUM). in Proceedings of SemEval-2016. Association for Computational Linguistics, San Diego, California, USA, pp. 546–559, 10th International Workshop on Semantic Evaluation, San Diego, California, United States, 16/06/16. <https://aclweb.org/anthology/S/S16/>

TY - GEN

T1 - SemEval-2016 Task~10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

AU - Schneider, Nathan

AU - Hovy, Dirk

AU - Johannsen, Anders

AU - Carpuat, Marine

PY - 2016/6

Y1 - 2016/6

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 - Conference contribution

SN - 978-1-941643-95-2

SP - 546

EP - 559

BT - Proceedings of SemEval-2016

PB - Association for Computational Linguistics

CY - San Diego, California, USA

T2 - 10th International Workshop on Semantic Evaluation

Y2 - 16 June 2016 through 17 June 2016

ER -

SemEval-2016 Task~10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

Abstract

Conference

Access to Document

Fingerprint

Cite this