SemEval-2020 Task 7: Assessing Humor in Edited News Headlines

Hossain, Nabil; Krumm, John; Gamon, Michael; Kautz, Henry

doi:10.18653/v1/2020.semeval-1.98

Cited by 58 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of the system, the organizers used different strategies and metrics for the Sub-tasks 1 and 2 (Hossain et al, 2020). For the Sub-task 1, Root Mean Square (RMSE), RMSE@10, RMSE@20 and RMSE@30 were applied to estimate the performance of a system.…”

Section: Evaluation Resultsmentioning

confidence: 99%

“…However detecting humor in news headlines from which one word is chosen to be replaced by another word to make the micro-edited sentences look funny is quite challenging. To address the challenges of humor detection in edited news headlines, (Hossain et al, 2020) proposed detection of funniness level in dataset named as Humicroedit 1 , Task 7 at SemEval-2020. They focus on two related subtasks.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

kdehumor at semeval-2020 task 7: a neural network model for detecting funniness in dataset humicroedit

Miraj¹,

Aono²

2021

Preprint

View full text Add to dashboard Cite

This paper describes our contribution to SemEval-2020 Task 7: Assessing Humor in Edited News Headlines. Here we present a method based on a deep neural network. In recent years, quite some attention has been devoted to humor production and perception. Our team KdeHumor employs recurrent neural network models including Bi-Directional LSTMs (BiLSTMs). Moreover, we utilize the state-of-the-art pre-trained sentence embedding techniques. We analyze the performance of our method and demonstrate the contribution of each component of our architecture.

show abstract

Section: Evaluation Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

kdehumor at semeval-2020 task 7: a neural network model for detecting funniness in dataset humicroedit

Miraj¹,

Aono²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, most of the existing related approaches attempts to utilize the traditional neural network models to detect the humour from tweets. However, Hossain et al [20] presented a slightly different type of challenge, namely, an attempt to investigate how small edits can turn a text from non-funny to funny. For this purpose, we have built a robust model, named IBEN (Integrating BERT and other Embeddings with Neural Network).…”

Section: Related Workmentioning

confidence: 99%

“…To validate the effectiveness of our proposed framework for humour detection, we made use of a dataset used in the SemEval-2020 Task 7 [20]. In this section, we would like to point out some interesting facts about the used data.…”

Section: Data Processingmentioning

confidence: 99%

Integrating Extracted Information from Bert and Multiple Embedding Methods with the Deep Neural Network for Humour Detection

Miraj¹,

Aono²

2021

IJNLC

View full text Add to dashboard Cite

Humour detection from sentences has been an interesting and challenging task in the last few years. In attempts to highlight humour detection, most research was conducted using traditional approaches of embedding, e.g., Word2Vec or Glove. Recently BERT sentence embedding has also been used for this task. In this paper, we propose a framework for humour detection in short texts taken from news headlines. Our proposed framework (IBEN) attempts to extract information from written text via the use of different layers of BERT. After several trials, weights were assigned to different layers of the BERT model. The extracted information was then sent to a Bi-GRU neural network as an embedding matrix. We utilized the properties of some external embedding models. A multi-kernel convolution in our neural network was also employed to extract higher-level sentence representations. This framework performed very well on the task of humour detection.

show abstract

“…Previous tasks on humor-grading consist of datasets comprising of originally humorous texts (Potash et al, 2017;Chiruzzo et al, 2019). SemEval-2020 Task-7 (Hossain et al, 2020a) focuses on short-edits based humor-grading. The dataset used for this shared-task was introduced by Hossain et al (2019).…”

Section: Introductionmentioning

confidence: 99%

LRG at SemEval-2020 Task 7: Assessing the Ability of BERT and Derivative Models to Perform Short-Edits based Humor Grading

Mahurkar¹,

Patil²

2020

Preprint

View full text Add to dashboard Cite

In this paper, we assess the ability of BERT and its derivative models (RoBERTa, DistilBERT, and ALBERT) for short-edits based humor grading. We test these models for humor grading and classification tasks on the Humicroedit and the FunLines dataset. We perform extensive experiments with these models to test their language modeling and generalization abilities via zero-shot inference and cross-dataset inference based approaches. Further, we also inspect the role of self-attention layers in humor-grading by performing a qualitative analysis over the self-attention weights from the final layer of the trained BERT model. Our experiments show that all the pre-trained BERT derivative models show significant generalization capabilities for humor-grading related tasks.

show abstract

SemEval-2020 Task 7: Assessing Humor in Edited News Headlines

Cited by 58 publications

References 38 publications

kdehumor at semeval-2020 task 7: a neural network model for detecting funniness in dataset humicroedit

kdehumor at semeval-2020 task 7: a neural network model for detecting funniness in dataset humicroedit

Integrating Extracted Information from Bert and Multiple Embedding Methods with the Deep Neural Network for Humour Detection

LRG at SemEval-2020 Task 7: Assessing the Ability of BERT and Derivative Models to Perform Short-Edits based Humor Grading

Contact Info

Product

Resources

About