IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source

Sofia Reznikova; Leon Derczynski

doi:10.18653/v1/S18-1179

IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge. First, clustering and topic modeling are used to divide given texts into topics. Then, during the answering phase, other texts of the same topic are retrieved and used as commonsense knowledge. Finally, the answer is selected. While clustering itself shows good results, finding an answer proves to be more challenging. This paper reports the results of system evaluation and suggests potential improvements.

Originalsprog	Engelsk
Titel	Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018)
Forlag	Association for Computational Linguistics
Publikationsdato	2018
Sider	1068-1072
DOI	https://doi.org/10.18653/v1/S18-1179
Status	Udgivet - 2018
Begivenhed	The 12th International Workshop on Semantic Evaluation - New Orleans, USA Varighed: 5 jun. 2018 → 6 jun. 2018 Konferencens nummer: 12

Workshop

Workshop	The 12th International Workshop on Semantic Evaluation
Nummer	12
Land/Område	USA
By	New Orleans
Periode	05/06/2018 → 06/06/2018

Emneord

machine comprehension
commonsense knowledge
clustering
topic modeling
system evaluation

Adgang til dokumentet

10.18653/v1/S18-1179

https://www.aclweb.org/anthology/S18-1179Licens: CC BY-ND

Citationsformater

@inproceedings{3f81dc9053764411931a3a6f93bc4a6d,

title = "IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source",

abstract = "This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge. First, clustering and topic modeling are used to divide given texts into topics. Then, during the answering phase, other texts of the same topic are retrieved and used as commonsense knowledge. Finally, the answer is selected. While clustering itself shows good results, finding an answer proves to be more challenging. This paper reports the results of system evaluation and suggests potential improvements.",

keywords = "machine comprehension, commonsense knowledge, clustering, topic modeling, system evaluation, machine comprehension, commonsense knowledge, clustering, topic modeling, system evaluation",

author = "Sofia Reznikova and Leon Derczynski",

note = "No ISBN; The 12th International Workshop on Semantic Evaluation, SemEval ; Conference date: 05-06-2018 Through 06-06-2018",

year = "2018",

doi = "10.18653/v1/S18-1179",

language = "English",

pages = "1068--1072",

booktitle = "Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018)",

publisher = "Association for Computational Linguistics",

address = "United States",

}

Reznikova, S & Derczynski, L 2018, IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source. i Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018). Association for Computational Linguistics, s. 1068-1072, The 12th International Workshop on Semantic Evaluation, New Orleans, USA, 05/06/2018. https://doi.org/10.18653/v1/S18-1179

IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source. / Reznikova, Sofia; Derczynski, Leon.
Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018). Association for Computational Linguistics, 2018. s. 1068-1072.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source

AU - Reznikova, Sofia

AU - Derczynski, Leon

N1 - Conference code: 12

PY - 2018

Y1 - 2018

N2 - This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge. First, clustering and topic modeling are used to divide given texts into topics. Then, during the answering phase, other texts of the same topic are retrieved and used as commonsense knowledge. Finally, the answer is selected. While clustering itself shows good results, finding an answer proves to be more challenging. This paper reports the results of system evaluation and suggests potential improvements.

AB - This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge. First, clustering and topic modeling are used to divide given texts into topics. Then, during the answering phase, other texts of the same topic are retrieved and used as commonsense knowledge. Finally, the answer is selected. While clustering itself shows good results, finding an answer proves to be more challenging. This paper reports the results of system evaluation and suggests potential improvements.

KW - machine comprehension

KW - commonsense knowledge

KW - clustering

KW - topic modeling

KW - system evaluation

KW - machine comprehension

KW - commonsense knowledge

KW - clustering

KW - topic modeling

KW - system evaluation

U2 - 10.18653/v1/S18-1179

DO - 10.18653/v1/S18-1179

M3 - Article in proceedings

SP - 1068

EP - 1072

BT - Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018)

PB - Association for Computational Linguistics

T2 - The 12th International Workshop on Semantic Evaluation

Y2 - 5 June 2018 through 6 June 2018

ER -

IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source

Abstract

Workshop

Emneord

Adgang til dokumentet

Fingeraftryk

Citationsformater