In many NLP applications that involve interpreting sentences within a rich context -- for instance, information retrieval systems or dialogue systems -- it is desirable to be able to preserve the sentence in a form that can be readily understood without context, for later reuse -- a process known as ``decontextualization''. While previous work demonstrated that generative Seq2Seq models could effectively perform decontextualization after being fine-tuned on a specific dataset, this approach requires expensive human annotations and may not transfer to other domains. We propose a few-shot method of decontextualization using a large language model, and present preliminary results showing that this method achieves viable performance on multiple domains using only a small set of examples.
@article{arxiv.2310.06254,
title = {Get the gist? Using large language models for few-shot decontextualization},
author = {Benjamin Kane and Lenhart Schubert},
journal= {arXiv preprint arXiv:2310.06254},
year = {2023}
}