Metaphor Generation with Conceptual Mappings

Stowe, Kevin; Chakrabarty, Tuhin; Peng, Nanyun; Muresan, Smaranda; Gurevych, Iryna

doi:10.18653/v1/2021.acl-long.524

Cited by 16 publications

(17 citation statements)

References 39 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The SI task (Shutova, 2010;Su et al, 2017) aims at finding a suitable attribute when given the tenor and vehicle, while the SG task (Yu and Wan, 2019) is to find a proper vehicle when given the tenor and its attribute. For simile interpretation, some works (Zheng et al, 2020;Bar et al, 2018;Xiao et al, 2016;Gagliano et al, 2016;Qadir et al, 2016) applied word vectors to decide which attribute words can fit into the tenor and vehicle domains and some other works (Gero and Chilton, 2019;Stowe et al, 2021) introduced knowledge base (Baker et al, 1998;Speer et al, 2017) to help find intermediate attributes.…”

Section: Simile Interpretation and Generationmentioning

confidence: 99%

“…For simile generation, some works focused on constructing limited training corpus to finetune a sequence-to-sequence model (Lewis et al, 2020) by pattern-based Bollegala and Shutova, 2013) or knowledge-based approaches (Chakrabarty et al, 2020Stowe et al, 2021). There are also some works (Abe et al, 2006;Hervás et al, 2007;Zheng et al, 2020) that focused more on the relationships between concepts (i.e.,…”

Section: Simile Interpretation and Generationmentioning

confidence: 99%

“…(Song et al, 2021) collected sentences containing comparator words from a Chinese essays corpus and manually annotated them to obtain the simile triple. Some works (Stowe et al, 2021;Gero and Chilton, 2019;Veale et al, 2016) relied on a knowledge base such as ConceptNet 2 , FrameNet 3 , which are scarce to other languages because it is time-consuming and labor-intensive to construct such a knowledge base. It is notable that pre-trained language models (PLMs) (Devlin et al, 2019;Radford et al, 2019) have made significant progress recently in many NLP tasks since it learns generic knowledge such as grammar, common sense from a large corpus (Davison et al, 2019;Liu et al, 2021a,b).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probing Simile Knowledge from Pre-trained Language Models

Chen¹,

Chang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Simile interpretation (SI) and simile generation (SG) are challenging tasks for NLP because models require adequate world knowledge to produce predictions. Previous works have employed many hand-crafted resources to bring knowledge-related into models, which is time-consuming and labor-intensive. In recent years, pre-trained language models (PLMs) based approaches have become the defacto standard in NLP since they learn generic knowledge from a large corpus. The knowledge embedded in PLMs may be useful for SI and SG tasks. Nevertheless, there are few works to explore it. In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time. The backbone of our framework is to construct masked sentences with manual patterns and then predict the candidate words in the masked position. In this framework, we adopt a secondary training process (Adjective-Noun mask Training) with the masked language model (MLM) loss to enhance the prediction diversity of candidate words in the masked position. Moreover, pattern ensemble (PE) and pattern search (PS) are applied to improve the quality of predicted words. Finally, automatic and human evaluations demonstrate the effectiveness of our framework in both SI and SG tasks.

show abstract

Section: Simile Interpretation and Generationmentioning

confidence: 99%

Section: Simile Interpretation and Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probing Simile Knowledge from Pre-trained Language Models

Chen¹,

Chang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Figurative Language Generation As a figure of speech, hyperbole generation is related to the general task of figurative language generation. Previous studies have tackled the generation of metaphor (Yu and Wan, 2019;Stowe et al, 2020;Stowe et al, 2021), simile (Chakrabarty et al, 2020b;, idiom (Zhou et al, 2021), pun (Yu et al, 2018;Luo et al, 2019b;He et al, 2019;, and sarcasm (Chakrabarty et al, 2020a). HypoGen (Tian et al, 2021) is a concurrent work with ours on hyperbole generation.…”

Section: Related Workmentioning

confidence: 99%

MOVER: Mask, Over-generate and Rank for Hyperbole Generation

Yun-xiang¹,

Wan

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Despite being a common figure of speech, hyperbole is under-researched in Figurative Language Processing. In this paper, we tackle the challenging task of hyperbole generation to transfer a literal sentence into its hyperbolic paraphrase. To address the lack of available hyperbolic sentences, we construct HYPO-XL, the first large-scale English hyperbole corpus containing 17,862 hyperbolic sentences in a non-trivial way. Based on our corpus, we propose an unsupervised method for hyperbole generation that does not require parallel literalhyperbole pairs. During training, we fine-tune BART (Lewis et al., 2020) to infill masked hyperbolic spans of sentences from HYPO-XL. During inference, we mask part of an input literal sentence and over-generate multiple possible hyperbolic versions. Then a BERT-based ranker selects the best candidate by hyperbolicity and paraphrase quality. Automatic and human evaluation results show that our model is effective at generating hyperbolic paraphrase sentences and outperforms several baseline systems.

show abstract

“…Thus, MetaPro has been employed for enhancing sentiment analysis (Mao et al, 2022a) and to detect mental health status, such as depression (Han et al, 2022). Apart from metaphor identification, linguistic and conceptual metaphor interpretation, metaphor processing has developed numerous works on metaphor generation (Yu and Wan, 2019;Chakrabarty et al, 2021;Stowe et al, 2021b) and application (Zheng et al, 2019;Cabot et al, 2020;Zhang et al, 2021a). However, Tong et al (2021) did not cover academic progress in these aspects.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Mao

Cambria

2022

Preprint

View full text Add to dashboard Cite

Metaphor is a figurative language that has been frequently used in our daily lives. Due to its significance for downstream natural language processing tasks, such as machine translation and sentiment analysis, computational metaphor processing has set off an upsurge in the community. With the development of Artificial Intelligence, an increasing number of technological tools and frameworks have been proposed in this domain. In this article, we aim to comprehensively summarize and categorize previous computational metaphor processing approaches regarding metaphor identification, interpretation, generation, and application. Meanwhile, we compare the strengths and weaknesses of current works and conceive future directions in this field.

show abstract

Metaphor Generation with Conceptual Mappings

Cited by 16 publications

References 39 publications

Probing Simile Knowledge from Pre-trained Language Models

Probing Simile Knowledge from Pre-trained Language Models

MOVER: Mask, Over-generate and Rank for Hyperbole Generation

A Survey on Computational Metaphor Processing Techniques: From Identification, Interpretation, Generation to Application

Contact Info

Product

Resources

About