Using Conceptual Norms for Metaphor Detection

Mingyu Wan; Kathleen Ahrens; Rong Xiang; Emmanuele Chersoni; Menghan Jiang; Qi Su; Chu-ren Huang

Using Conceptual Norms for Metaphor Detection

Mingyu Wan, Kathleen Ahrens, Rong Xiang, Emmanuele Chersoni, Menghan Jiang, Qi Su, Chu-ren Huang

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

10 Citations (Scopus)

Abstract

This paper reports a linguistically-enriched method of detecting token-level metaphors for the second shared task on Metaphor Detection. We participate in all four phases of competition with both datasets, i.e. Verbs and AllPOS on the VUA and the TOFEL datasets. We use the modality exclusivity and embodiment norms for constructing a conceptual representation of the nodes and the context. Our system obtains an F-score of 0.652 for the VUA Verbs track, which is 5% higher than the strong baselines. The experimental results across models and datasets indicate the salient contribution of using modality exclusivity and modality shift information for predicting metaphoricity.

Original language	English
Title of host publication	Proceedings of The Second Workshop on Figurative Language Processing
Publisher	Association for Computational Linguistics (ACL)
Pages	104-109
Publication status	Published - Jul 2020

More information

http://hdl.handle.net/10397/92408

Cite this

@inproceedings{d34105a6ea8f4ef1b609e49b40c6a0f4,

title = "Using Conceptual Norms for Metaphor Detection",

abstract = "This paper reports a linguistically-enriched method of detecting token-level metaphors for the second shared task on Metaphor Detection. We participate in all four phases of competition with both datasets, i.e. Verbs and AllPOS on the VUA and the TOFEL datasets. We use the modality exclusivity and embodiment norms for constructing a conceptual representation of the nodes and the context. Our system obtains an F-score of 0.652 for the VUA Verbs track, which is 5% higher than the strong baselines. The experimental results across models and datasets indicate the salient contribution of using modality exclusivity and modality shift information for predicting metaphoricity.",

author = "Mingyu Wan and Kathleen Ahrens and Rong Xiang and Emmanuele Chersoni and Menghan Jiang and Qi Su and Chu-ren Huang",

year = "2020",

month = jul,

language = "English",

pages = "104--109",

booktitle = "Proceedings of The Second Workshop on Figurative Language Processing",

publisher = "Association for Computational Linguistics (ACL)",

}

Using Conceptual Norms for Metaphor Detection. / Wan, Mingyu; Ahrens, Kathleen; Xiang, Rong et al.
Proceedings of The Second Workshop on Figurative Language Processing. Association for Computational Linguistics (ACL), 2020. p. 104-109.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Using Conceptual Norms for Metaphor Detection

AU - Wan, Mingyu

AU - Ahrens, Kathleen

AU - Xiang, Rong

AU - Chersoni, Emmanuele

AU - Jiang, Menghan

AU - Su, Qi

AU - Huang, Chu-ren

PY - 2020/7

Y1 - 2020/7

N2 - This paper reports a linguistically-enriched method of detecting token-level metaphors for the second shared task on Metaphor Detection. We participate in all four phases of competition with both datasets, i.e. Verbs and AllPOS on the VUA and the TOFEL datasets. We use the modality exclusivity and embodiment norms for constructing a conceptual representation of the nodes and the context. Our system obtains an F-score of 0.652 for the VUA Verbs track, which is 5% higher than the strong baselines. The experimental results across models and datasets indicate the salient contribution of using modality exclusivity and modality shift information for predicting metaphoricity.

AB - This paper reports a linguistically-enriched method of detecting token-level metaphors for the second shared task on Metaphor Detection. We participate in all four phases of competition with both datasets, i.e. Verbs and AllPOS on the VUA and the TOFEL datasets. We use the modality exclusivity and embodiment norms for constructing a conceptual representation of the nodes and the context. Our system obtains an F-score of 0.652 for the VUA Verbs track, which is 5% higher than the strong baselines. The experimental results across models and datasets indicate the salient contribution of using modality exclusivity and modality shift information for predicting metaphoricity.

M3 - Conference article published in proceeding or book

SP - 104

EP - 109

BT - Proceedings of The Second Workshop on Figurative Language Processing

PB - Association for Computational Linguistics (ACL)

ER -

Using Conceptual Norms for Metaphor Detection

Abstract

More information

Fingerprint

Cite this