Domain Controlled Title Generation with Human Evaluation

EasyChair Preprint 4825

Abstract

We study automatic title generation and present a method for generating domain-controlled titles
for scientific articles. A good title allows you to get the attention that your research deserves. A title can be
interpreted as a high-compression description of a document containing information on the implemented
process. For domain-controlled titles, we used the pre-trained text-to-text transformer model and the additional
token technique. Title tokens are sampled from a local distribution (which is a subset of global vocabulary) of
the domain-specific vocabulary and not global vocabulary, thereby generating a catchy title and closely linking
it to its corresponding abstract. Generated titles looked realistic, convincing, and very close to the ground truth.
We have performed automated evaluation and human evaluation to make a comparison between human and
machine-generated titles. The titles produced were considered acceptable in human evaluation, thus we
concluded that our research proposes a promising method for domain-controlled title generation.

Keyphrases: Summarization Technique, Text-to-Text Transformer, automatic title generation, domain-control, human evaluation

@booklet{EasyChair:4825,
  author    = {Abdul Waheed and Muskan Goyal and Nimisha Mittal and Deepak Gupta},
  title     = {Domain Controlled Title Generation with Human Evaluation},
  howpublished = {EasyChair Preprint 4825},
  year      = {EasyChair, 2020}}