From text to talk- ACL 2022 NLP position paper -acl2022nlp
Mark Ding
Make a clip
CC BY 3.0 · Mark Ding
Up to 60 seconds, at most the picture size of the copy it is cut from. The clip carries the title, the credit, the licence and a link back here. It is made in this browser, and nothing is sent to this site.
Or send the moment itself: https://invisiblenetwork.ai/watch/archive/commons/123726163?play=1&t=0
Parts
About
Preview and pre-recorded presentation accompanying the ACL 2022 paper "From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology" by Mark Dingemanse and Andreas Liesenfeld, Radboud University.
ACL Anthology link: https://aclanthology.org/2022.acl-long.385/ Preprint, code & materials: https://osf.io/m43zh/
In case you consider reusing or remixing this material, we release it under a Creative Commons Attribution Non-Commercial license: https://creativecommons.org/licenses/by-nc/4.0/ For attribution, we ask that you (1) cite the paper including a link to the DOI of its most definitive version and (2) link to the visual preview. The most update attribution information is:
Dingemanse, M., & Liesenfeld, A. (2022). From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 5614–5633. Dublin: Association for Computational Linguistics. doi: 10.18653/v1/2022.acl-long.385
Human-made No record of this work says a model made it. What this means.