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 All-POS 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.

Neural Metaphor Detection with Visibility Embeddings

“…Impressive results 1 were presented in the 2018 Metaphor Detection Shared Task (Leong et al, 2018), with most of the groups using neural models with other linguistic elements like POS tags, Word-Net features, concreteness scores and more (Wu et al, 2018;Swarnkar and Singh, 2018;Pramanick et al, 2018;Bizzoni and Ghanimifard, 2018), as well as in the more recent 2020 Shared Task , with the majority of groups using some variation of BERT in addition to the other features Gao and Zhang, 2002;Kuo and Carpuat, 2020;Torres Rivera et al, 2020;Kumar and Sharma, 2020;Hall Maudslay et al, 2020;Stemle and Onysko, 2020;Liu et al, 2020;Brooks and Youssef, 2020;Alnafesah et al, 2020;Wan et al, 2020;Dankers et al, 2020).…”

Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics

“…In its classical form, the thematic fit estimation task consists in comparing a candidate argument or filler (e.g., wine) with the typical fillers of a given verb role (e.g., agent, patient, etc. ), either in the form of exemplars previously attested in a corpus (Erk, 2007;Vandekerckhove et al, 2009;Erk et al, 2010) or in the form of a vector-based prototype (Baroni and Lenci, 2010;Sayeed and Demberg, 2014;Sayeed et al, 2015;Greenberg et al, 2015a,b;Sayeed et al, 2016;Santus et al, 2017;Chersoni et al, 2020). Additionally, recent studies explored the use of masked language modeling with BERT for scoring the candidate arguments (Metheniti et al, 2020).…”

“…Impressive results 1 were presented in the 2018 Metaphor Detection Shared Task (Leong et al, 2018), with most of the groups using neural models with other linguistic elements like POS tags, Word-Net features, concreteness scores and more Swarnkar and Singh, 2018;Pramanick et al, 2018;Bizzoni and Ghanimifard, 2018), as well as in the more recent 2020 Shared Task , with the majority of groups using some variation of BERT in addition to the other features Gao and Zhang, 2002;Kuo and Carpuat, 2020;Torres Rivera et al, 2020;Kumar and Sharma, 2020;Hall Maudslay et al, 2020;Stemle and Onysko, 2020;Brooks and Youssef, 2020;Chen et al, 2020;Alnafesah et al, 2020;Wan et al, 2020;Dankers et al, 2020).…”

Contextualized Sensorimotor Norms: multi-dimensional measures of sensorimotor strength for ambiguous English words, in context

“…The LS Norms provide human ratings about the extent to which an isolated word (e.g., "table ") is strongly associated with various sensory modalities (e.g., Vision vs. Touch) and action effectors (e.g., Hand/Arm vs. Foot/Leg). Recent work (Kennington, 2021;Wan et al, 2020b,a) has found that integrating these norms improves the performance of language models on several NLP tasks, such as GLUE (Wang et al, 2018) and metaphor detection (Wan et al, 2020a).…”