PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing

Zhou, Jianhui; Gong, Honghan; Bhat, Suma

doi:10.18653/v1/2021.mwe-1.5

Cited by 9 publications

(8 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to identification, the interpretation of idioms has been less explored. Approaches for representing idiomatic expressions include substituting idioms with literal paraphrases (Liu and Hwa, 2016;Zhou et al, 2021), representing them as a single token, or learning to compose them at the character level rather than the word level .…”

Section: Idiomsmentioning

confidence: 99%

It’s not Rocket Science: Interpreting Figurative Language in Narratives

Chakrabarty

Choi

Shwartz

2022

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representations by design rely on compositionality, while figurative language is often non- compositional. In this paper, we study the interpretation of two non-compositional figurative languages (idioms and similes). We collected datasets of fictional narratives containing a figurative expression along with crowd-sourced plausible and implausible continuations relying on the correct interpretation of the expression. We then trained models to choose or generate the plausible continuation. Our experiments show that models based solely on pre-trained language models perform substantially worse than humans on these tasks. We additionally propose knowledge-enhanced models, adopting human strategies for interpreting figurative language types: inferring meaning from the context and relying on the constituent words’ literal meanings. The knowledge-enhanced models improve the performance on both the discriminative and generative tasks, further bridging the gap from human performance.

show abstract

Section: Idiomsmentioning

confidence: 99%

It’s not Rocket Science: Interpreting Figurative Language in Narratives

Chakrabarty

Choi

Shwartz

2022

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…The selection of its initial list of idioms differ from our dataset: after a semi automatic selection of idiomatic expressions, a crowdsourced annotation approach is adopted to determine whether the expression is used metaphorically or literally. In a similar design than the dataset used for Subtask B, Zhou et al (2021) constructed a curated dataset of sentences pairs: one element containing an idiomatic expression and the second element being the same sentences with the IEs replaced by its literal paraphrase.…”

Section: Related Workmentioning

confidence: 99%

CardiffNLP-Metaphor at SemEval-2022 Task 2: Targeted Fine-tuning of Transformer-based Language Models for Idiomaticity Detection

Boisson¹,

Camacho-Collados²,

Espinosa-Anke³

2022

Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)

View full text Add to dashboard Cite

This paper describes the experiments ran for SemEval-2022 Task 2, subtask A, zero-shot and one-shot settings for idiomaticity detection. Our main approach is based on fine-tuning transformer-based language models as a baseline to perform binary classification. Our system, CardiffNLP-Metaphor, ranked 8th and 7th (respectively on zero-and one-shot settings on this task. Our main contribution lies in the extensive evaluation of transformer-based language models and various configurations, showing, among others, the potential of large multilingual models over base monolingual models. Moreover, we analyse the impact of various input parameters, which offer interesting insights on how language models work in practice.

show abstract

“…Compared to identification, the interpretation of idioms has been less-explored. Approaches for representing idiomatic expressions include substituting idioms with literal paraphrases (Liu and Hwa, 2016;Zhou et al, 2021), representing them as a single token, or learning to compose them at the character rather than word-level .…”

Section: Idiomsmentioning

confidence: 99%

It's not Rocket Science : Interpreting Figurative Language in Narratives

Chakrabarty¹,

Choi²,

Shwartz³

2021

Preprint

View full text Add to dashboard Cite

Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representations by design rely on compositionality, while figurative language is often non-compositional. In this paper, we study the interpretation of two noncompositional figurative languages (idioms and similes). We collected datasets of fictional narratives containing a figurative expression along with crowd-sourced plausible and implausible continuations relying on the correct interpretation of the expression. We then trained models to choose or generate the plausible continuation. Our experiments show that models based solely on pretrained language models perform substantially worse than humans on these tasks. We additionally propose knowledge-enhanced models, adopting human strategies for interpreting figurative language: inferring meaning from the context and relying on the constituent word's literal meanings. The knowledge-enhanced models improve the performance on both the discriminative and generative tasks, further bridging the gap from human performance.

show abstract

PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing

Cited by 9 publications

References 53 publications

It’s not Rocket Science: Interpreting Figurative Language in Narratives

It’s not Rocket Science: Interpreting Figurative Language in Narratives

CardiffNLP-Metaphor at SemEval-2022 Task 2: Targeted Fine-tuning of Transformer-based Language Models for Idiomaticity Detection

It's not Rocket Science : Interpreting Figurative Language in Narratives

Contact Info

Product

Resources

About