Modelling the interplay of metaphor and emotion through multitask learning

Dankers, Verna; Rei, Marek; Lewis, Martha; Shutova, Ekaterina

doi:10.18653/v1/d19-1227

Cited by 61 publications

(73 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preoţiuc-Pietro and Ungar (2018) focused on correlation across demographic information (e.g., age, gender, race) and with some other factors such as emotions. Dankers et al (2019); Mohammad et al (2016) studied the interplay of metaphor and emotion in text. In sarcasm detection, sentiment is also used as a subproblem for an additional feature (Liu et al, 2010).…”

Section: Related Workmentioning

confidence: 99%

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Wang

Singh

Michael

et al. 2018

Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

3,020

2,755

View full text Add to dashboard Cite

Every natural text is written in some style. The style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphor, etc. Some factors implicitly reflect the author's personality, while others are explicitly controlled by the author's choices in order to achieve some personal or social goal. One cannot form a complete understanding of a text and its author without considering these factors. The factors combine and co-vary in complex ways to form styles. Studying the nature of the covarying combinations sheds light on stylistic language in general, sometimes called crossstyle language understanding. This paper provides a benchmark corpus (xSLUE) with an online platform (http://xslue.com) for crossstyle language understanding and evaluation. The benchmark contains text in 15 different styles and 23 classification tasks. For each task, we provide the fine-tuned classifier for further analysis. Our analysis shows that some styles are highly dependent on each other (e.g., impoliteness and offense), and some domains (e.g., tweets, political debates) are stylistically more diverse than others (e.g., academic manuscripts). We discuss the technical challenges of cross-style understanding and potential directions for future research: crossstyle modeling which shares the internal representation for low-resource or low-performance styles and other applications such as crossstyle generation.

show abstract

Section: Related Workmentioning

confidence: 99%

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Wang

Singh

Michael

et al. 2018

Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

3,020

2,755

View full text Add to dashboard Cite

show abstract

“…Mao et al (2019) also proposed employing multi-head attention to compare the targeted word representation with its context. An interesting approach was introduced by Dankers et al (2019) to model the interplay between metaphor identification and emotion regression. The authors introduced multiple multi-task learning tech-niques that employ hard and soft parameter sharing methods to optimise LSTM-based and BERT-based models.…”

Section: Related Workmentioning

confidence: 99%

Contextual Modulation for Relation-Level Metaphor Identification

Zayed¹,

McCrae²,

Buitelaar³

2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Identifying metaphors in text is very challenging and requires comprehending the underlying comparison. The automation of this cognitive process has gained wide attention lately. However, the majority of existing approaches concentrate on word-level identification by treating the task as either single-word classification or sequential labelling without explicitly modelling the interaction between the metaphor components. On the other hand, while existing relation-level approaches implicitly model this interaction, they ignore the context where the metaphor occurs. In this work, we address these limitations by introducing a novel architecture for identifying relation-level metaphoric expressions of certain grammatical relations based on contextual modulation. In a methodology inspired by works in visual reasoning, our approach is based on conditioning the neural network computation on the deep contextualised features of the candidate expressions using feature-wise linear modulation. We demonstrate that the proposed architecture achieves state-of-the-art results on benchmark datasets. The proposed methodology is generic and could be applied to other textual classification problems that benefit from contextual interaction.

show abstract

“…Alternative approaches perform metaphor detection from distributional properties of words (Shutova et al, 2010;Gutiérrez et al, 2016) or by training deep neural models (Rei et al, 2017;Gao et al, 2018). Dankers et al (2019) developed a joint model of metaphor and emotion by fine-tuning BERT in an MTL setting.…”

Section: Related Workmentioning

confidence: 99%

“…The MTL architecture uses hard parameter sharing for the first eleven transformer layers. The last layer of RoBERTa, the classification and attention layers are task-specific to allow for specialisation, similar to the approach of Dankers et al (2019).…”

Section: Multi-task Learningmentioning

confidence: 99%

The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse

Cabot¹,

Dankers²,

Abadi³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

There has been an increased interest in modelling political discourse within the natural language processing (NLP) community, in tasks such as political bias and misinformation detection, among others. Metaphor-rich and emotion-eliciting communication strategies are ubiquitous in political rhetoric, according to social science research. Yet, none of the existing computational models of political discourse has incorporated these phenomena. In this paper, we present the first joint models of metaphor, emotion and political rhetoric, and demonstrate that they advance performance in three tasks: predicting political perspective of news articles, party affiliation of politicians and framing of policy issues.

show abstract

Modelling the interplay of metaphor and emotion through multitask learning

Cited by 61 publications

References 54 publications

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Contextual Modulation for Relation-Level Metaphor Identification

The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse

Contact Info

Product

Resources

About