Large Dataset and Language Model Fun-Tuning for Humor Recognition

Blinov, Vladislav; Bolotova-Baranova, Valeriia; Braslavski, Pavel

doi:10.18653/v1/p19-1394

Cited by 40 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al (2015) scraped puns from the Pun of the Day website 1 and negative examples from various news websites. There is also work on the curation of non-English humor datasets (Zhang et al, 2019;Blinov et al, 2019). Hasan et al (2019) developed UR-FUNNY, a multimodal humor dataset that involves text, audio and video information extracted from TED talks.…”

Section: Related Workmentioning

confidence: 99%

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Xie¹,

Li²,

Pu³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Humor recognition has been widely studied as a text classification problem using data-driven approaches. However, most existing work does not examine the actual joke mechanism to understand humor. We break down any joke into two distinct components: the set-up and the punchline, and further explore the special relationship between them. Inspired by the incongruity theory of humor, we model the setup as the part developing semantic uncertainty, and the punchline disrupting audience expectations. With increasingly powerful language models, we were able to feed the set-up along with the punchline into the GPT-2 language model, and calculate the uncertainty and surprisal values of the jokes. By conducting experiments on the SemEval 2021 Task 7 dataset, we found that these two features have better capabilities of telling jokes from non-jokes, compared with existing baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Xie¹,

Li²,

Pu³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…In this section, we briefly describe other work in this area. In this approach (Blinov et al, 2019), the authors have used universal language model fine-tuning method for humour recognition. Convolutional neural networks (CNN) have also been used for this task by (Chen and Soo, 2018) whereas (Weller and Seppi, 2019) used transformers to classify humour.…”

Section: Related Workmentioning

confidence: 99%

IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining

Raha

Upadhyay²,

Mamidi

et al. 2021

Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)

View full text Add to dashboard Cite

This paper describes our approach (IIITH) for SemEval-2021 Task 5: HaHackathon: Detecting and Rating Humor and Offense. Our results focus on two major objectives: (i) Effect of task adaptive pretraining on the performance of transformer based models (ii) How does lexical and hurtlex features help in quantifying humour and offense. In this paper, we provide a detailed description of our approach along with comparisions mentioned above.

show abstract

“…Owing to the subjective nature of humor, there have been recent efforts in collecting datasets for humor; Blinov et al, (2019) collected a dataset of jokes and funny dialogues in Russian from various online resources, and complemented them carefully with unfunny texts with similar lexical properties. They developed a fine-tuned language model for text classification with a significant gain over baseline methods.…”

Section: Related Workmentioning

confidence: 99%

“Judge me by my size (noun), do you?” YodaLib: A Demographic-Aware Humor Generation Framework

Banea

Hossain

Mihalcea

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

The subjective nature of humor makes computerized humor generation a challenging task. We propose an automatic humor generation framework for filling the blanks in Mad Libs R stories, while accounting for the demographic backgrounds of the desired audience. We collect a dataset consisting of such stories, which are filled in and judged by carefully selected workers on Amazon Mechanical Turk. We build upon the BERT platform to predict location-biased word fillings in incomplete sentences, and we fine-tune BERT to classify location-specific humor in a sentence. We leverage these components to produce YODALIB, a fully-automated Mad Libs style humor generation framework, which selects and ranks appropriate candidate words and sentences in order to generate a coherent and funny story tailored to certain demographics. Our experimental results indicate that YODALIB outperforms a previous semi-automated approach proposed for this task, while also surpassing human annotators in both qualitative and quantitative analyses.

show abstract

Large Dataset and Language Model Fun-Tuning for Humor Recognition

Cited by 40 publications

References 16 publications

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

IIITH at SemEval-2021 Task 7: Leveraging transformer-based humourous and offensive text detection architectures using lexical and hurtlex features and task adaptive pretraining

“Judge me by my size (noun), do you?” YodaLib: A Demographic-Aware Humor Generation Framework

Contact Info

Product

Resources

About