That’s What She Said_ Humor Identification with Word Embeddings and Recurrent Neural Networks

Ashish Kayastha, Alexander Redei

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Humor identification is an interesting problem in natural language that has previously been tackled with handcrafted features and traditional classifiers. We take on a famous double entendre identification problem—the “That’s What She Said” (TWSS) joke—using a powerful class of models for Natural Language Processing (NLP): Word Embeddings and Recurrent Neural Networks (RNNs). We investigated the benefits of these models by discriminating their performance on three train/test sets, each having a different class balance. Our best model achieves a precision of 93.7% and a recall of 96.5% on a class balanced train/test set (generated from web data) using GloVe embeddings paired with Gated Recurrent Unit (GRU). More importantly, the model maintains stellar performance with a precision of 89.2% and a recall of 84.7% on a class imbalanced train/test set. These results are remarkable compared to the previous state-of-the-art approach, based on feature engineering that only manages to achieve a precision of 71.4% and a recall of less than 20%.

Original languageEnglish
Title of host publicationAdvances in Information and Communication - Proceedings of the 2022 Future of Information and Communication Conference, FICC
EditorsKohei Arai
PublisherSpringer Science and Business Media Deutschland GmbH
Pages209-221
Number of pages13
ISBN (Print)9783030980146
DOIs
StatePublished - 2022
EventFuture of Information and Communication Conference, FICC 2022 - Virtual, Online
Duration: Mar 3 2022Mar 4 2022

Publication series

NameLecture Notes in Networks and Systems
Volume439 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceFuture of Information and Communication Conference, FICC 2022
CityVirtual, Online
Period03/3/2203/4/22

Keywords

  • Computational humor
  • Computational linguistics
  • Deep learning
  • Natural language processing
  • Recurrent Neural Networks
  • That’s What She Said

Fingerprint

Dive into the research topics of 'That’s What She Said_ Humor Identification with Word Embeddings and Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this