Deep learning of audio and language features for humor prediction

Dario Bertero, Pascale Fung

Research output: Chapter in Book/Conference Proceeding/ReportConference Paper published in a bookpeer-review

Abstract

We propose a comparison between various supervised machine learning methods to predict and detect humor in dialogues. We retrieve our humorous dialogues from a very popular TV sitcom: "The Big Bang Theory". We build a corpus where punchlines are annotated using the canned laughter embedded in the audio track. Our comparative study involves a linear-chain Conditional Random Field over a Recurrent Neural Network and a Convolutional Neural Network. Using a combination of word-level and audio frame-level features, the CNN outperforms the other methods, obtaining the best F-score of 68.5% over 66.5% by CRF and 52.9% by RNN. Our work is a starting point to developing more effective machine learning and neural network models on the humor prediction task, as well as developing machines capable in understanding humor in general.

Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016
EditorsNicoletta Calzolari, Khalid Choukri, Helene Mazo, Asuncion Moreno, Thierry Declerck, Sara Goggi, Marko Grobelnik, Jan Odijk, Stelios Piperidis, Bente Maegaard, Joseph Mariani
PublisherEuropean Language Resources Association (ELRA)
Pages496-501
Number of pages6
ISBN (Electronic)9782951740891
Publication statusPublished - 2016
Event10th International Conference on Language Resources and Evaluation, LREC 2016 - Portoroz, Slovenia
Duration: 23 May 201628 May 2016

Publication series

NameProceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016

Conference

Conference10th International Conference on Language Resources and Evaluation, LREC 2016
Country/TerritorySlovenia
CityPortoroz
Period23/05/1628/05/16

Keywords

  • Humor prediction
  • Neural networks
  • TV-sitcoms

Fingerprint

Dive into the research topics of 'Deep learning of audio and language features for humor prediction'. Together they form a unique fingerprint.

Cite this