ABDN at SemEval-2018 Task 10

Recognising Discriminative Attributes using Context Embeddings and WordNet

Rui Mao, Guanyi Chen, Ruizhe Li, Chenghua Lin

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

Abstract

This paper describes the system that we submitted for SemEval-2018 task 10: Capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word's similarity with each of the two semantically similar words, based on an extended word embedding method, and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.
Original languageEnglish
Title of host publicationThe International Workshop on Semantic Evaluation
Subtitle of host publicationProceedings of the Twelfth Workshop
Place of PublicationNew Orleans, USA
PublisherAssociation for Computational Linguistics (ACL)
Pages1017–1021
Number of pages4
ISBN (Print)978-1-948087-20-9
Publication statusPublished - 1 Jun 2018
Event12th International Workshop on Semantic Evaluation (SemEval-2018) - New Orleans, United States
Duration: 5 Jun 2018 → 6 Jun 2018

Conference

Conference12th International Workshop on Semantic Evaluation (SemEval-2018)
CountryUnited States
CityNew Orleans
Period5/06/18 → 6/06/18

Cite this

Mao, R., Chen, G., Li, R., & Lin, C. (2018). ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet. In The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop (pp. 1017–1021). New Orleans, USA: Association for Computational Linguistics (ACL).

ABDN at SemEval-2018 Task 10 : Recognising Discriminative Attributes using Context Embeddings and WordNet. / Mao, Rui; Chen, Guanyi; Li, Ruizhe; Lin, Chenghua.

The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop. New Orleans, USA : Association for Computational Linguistics (ACL), 2018. p. 1017–1021.

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

Mao, R, Chen, G, Li, R & Lin, C 2018, ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet. in The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop. Association for Computational Linguistics (ACL), New Orleans, USA, pp. 1017–1021, 12th International Workshop on Semantic Evaluation (SemEval-2018), New Orleans, United States, 5/06/18.
Mao R, Chen G, Li R, Lin C. ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet. In The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop. New Orleans, USA: Association for Computational Linguistics (ACL). 2018. p. 1017–1021
Mao, Rui ; Chen, Guanyi ; Li, Ruizhe ; Lin, Chenghua. / ABDN at SemEval-2018 Task 10 : Recognising Discriminative Attributes using Context Embeddings and WordNet. The International Workshop on Semantic Evaluation: Proceedings of the Twelfth Workshop. New Orleans, USA : Association for Computational Linguistics (ACL), 2018. pp. 1017–1021
@inproceedings{e3457d25def34f0497b4e83749365d74,
title = "ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet",
abstract = "This paper describes the system that we submitted for SemEval-2018 task 10: Capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word's similarity with each of the two semantically similar words, based on an extended word embedding method, and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.",
author = "Rui Mao and Guanyi Chen and Ruizhe Li and Chenghua Lin",
year = "2018",
month = "6",
day = "1",
language = "English",
isbn = "978-1-948087-20-9",
pages = "1017–1021",
booktitle = "The International Workshop on Semantic Evaluation",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - ABDN at SemEval-2018 Task 10

T2 - Recognising Discriminative Attributes using Context Embeddings and WordNet

AU - Mao, Rui

AU - Chen, Guanyi

AU - Li, Ruizhe

AU - Lin, Chenghua

PY - 2018/6/1

Y1 - 2018/6/1

N2 - This paper describes the system that we submitted for SemEval-2018 task 10: Capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word's similarity with each of the two semantically similar words, based on an extended word embedding method, and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.

AB - This paper describes the system that we submitted for SemEval-2018 task 10: Capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word's similarity with each of the two semantically similar words, based on an extended word embedding method, and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.

M3 - Conference contribution

SN - 978-1-948087-20-9

SP - 1017

EP - 1021

BT - The International Workshop on Semantic Evaluation

PB - Association for Computational Linguistics (ACL)

CY - New Orleans, USA

ER -

Access to Document