Unsupervised Enrichment of Persona-grounded Dialog with Background Stories

Bodhisattwa Prasad Majumder, Taylor Berg-Kirkpatrick, Julian McAuley, Harsh Jhamtani
<span title="">2021</span> <i title="Association for Computational Linguistics"> Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) </i> &nbsp; <span class="release-stage">unpublished</span>
Humans often refer to personal narratives, life experiences, and events to make a conversation more engaging and rich. While personagrounded dialog models are able to generate responses that follow a given persona, they often miss out on stating detailed experiences or events related to a persona, often leaving conversations shallow and dull. In this work, we equip dialog models with 'background stories' related to a persona by leveraging fictional narratives from existing story datasets (e.g.
more &raquo; ... OC-Stories). Since current dialog datasets do not contain such narratives as responses, we perform an unsupervised adaptation of a retrieved story for generating a dialog response using a gradient-based rewriting technique. Our proposed method encourages the generated response to be fluent (i.e., highly likely) with the dialog history, minimally different from the retrieved story to preserve event ordering and consistent with the original persona. We demonstrate that our method can generate responses that are more diverse, and are rated more engaging and human-like by human evaluators, compared to outputs from existing dialog models.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.acl-short.74">doi:10.18653/v1/2021.acl-short.74</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4umvve6jibhkznmsdtq7vi6kay">fatcat:4umvve6jibhkznmsdtq7vi6kay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210726025608/https://aclanthology.org/2021.acl-short.74.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f1/37/f1373ad1521ab00e2b71e9def02dad569b10af14.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.acl-short.74"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>