paper-with-me

홈 › Papers

Who's to say what's funny? A computer using Language Models and Deep Learning, That's Who!

2017-05-29 · Xinru Yan, Ted Pedersen

Humor is a defining characteristic of human beings. Our goal is to develop methods that automatically detect humorous statements and rank them on a continuous scale. In this paper we report on results using a Language Model approach, and outline our plans for using methods from Deep Learning.

📄 PDF Abstract BibTeX arXiv:1705.10272

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Neural Joking Machine : Humorous image captioning

2018-05-30 · Kota Yoshida, Munetaka Minoguchi, Kenichiro Wani, Akio Nakamura 외

What is an effective expression that draws laughter from human beings? In the present paper, in order to consider this question from an academic standpoint, we generate an image caption that draws a "laugh" by a computer…

Image Captioning

FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild

2024-01-08 · Zhi-Song Liu, Robin Courant, Vicky Kalogeiton

Automatically understanding funny moments (i.e., the moments that make people laugh) when watching comedy is challenging, as they relate to various features, such as body language, dialogues and culture. In this paper, w…

Language ModellingLarge Language ModelScene UnderstandingSpeech-to-Text

Filling the Blanks (hint: plural noun) for Mad Libs Humor

2017-09-01 · EMNLP 2017 9 · Nabil Hossain, John Krumm, V, Lucy erwende 외

Computerized generation of humor is a notoriously difficult AI problem. We develop an algorithm called Libitum that helps humans generate humor in a Mad Lib, which is a popular fill-in-the-blank game. The algorithm is ba…

"President Vows to Cut <Taxes> Hair": Dataset and Analysis of Creative Text Editing for Humorous Headlines

2019-06-01 · Nabil Hossain, John Krumm, Michael Gamon

We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor. Our publicly available data consists of regular English news headlines paired with versions of the same headlines…

``President Vows to Cut \textlessTaxes\textgreater Hair'': Dataset and Analysis of Creative Text Editing for Humorous Headlines

2019-06-01 · NAACL 2019 6 · Nabil Hossain, John Krumm, Michael Gamon

We introduce, release, and analyze a new dataset, called Humicroedit, for research in computational humor. Our publicly available data consists of regular English news headlines paired with versions of the same headlines…