Taxonomy of risks posed by language models

Autor: Laura Weidinger, Jonathan Uesato, Maribeth Rauh, Conor Griffin, Po-Sen Huang, John Mellor, Amelia Glaese, Myra Cheng, Borja Balle, Atoosa Kasirzadeh, Courtney Biles, Sasha Brown, Zac Kenton, Will Hawkins, Tom Stepleton, Abeba Birhane, Lisa Anne Hendricks, Laura Rimell, William Isaac, Julia Haas, Sean Legassick, Geoffrey Irving, Iason Gabriel

Publikováno v: Weidinger, L, Uesato, J, Rauh, M, Griffin, C, Huang, P, Mellor, J, Glaese, A, Cheng, M, Balle, B, Kasirzadeh, A, Biles, C, Brown, S, Kenton, Z, Hawkins, W, Stepleton, T, Birhane, A, Hendricks, L A, Rimell, L, Isaac, W, Haas, J, Legassick, S, Irving, G & Gabriel, I 2022, Taxonomy of risks posed by language models . in FAccT '22 : 2022 ACM Conference on Fairness, Accountability, and Transparency . pp. 214-229 . https://doi.org/10.1145/3531146.3533088

Responsible innovation on large-scale Language Models (LMs) requires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxonomy of ethical and social risks associated with LMs. We identi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7cf0fa54923f2f0a0d4d9b8a02d0cc6
https://hdl.handle.net/20.500.11820/50548a53-8cb0-4140-8857-9ebbd3311866

Pretraining the Noisy Channel Model for Task-Oriented Dialogue

Autor: Laura Rimell, Lei Yu, Phil Blunsom, Qi Liu

Direct decoding for task-oriented dialogue is known to suffer from the explaining-away effect, manifested in models that prefer short and generic responses. Here we argue for the use of Bayes' theorem to factorize the dialogue task into two models, t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6c1dc24f1c6884e8e7c882e99b0ba81
http://arxiv.org/abs/2103.10518

Neural Generative Rhetorical Structure Parsing

Autor: Laura Rimell, Andreas Vlachos, Amandla Mabona, Stephen Clark

Publikováno v: EMNLP/IJCNLP (1)

Rhetorical structure trees have been shown to be useful for several document-level tasks including summarization and document classification. Previous approaches to RST parsing have used discriminative models; however, these are less sample efficient

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b88bc7da52872bb2062bdd3c6786e9e
https://doi.org/10.18653/v1/d19-1233

Acquisition and evaluation of verb subcategorization resources for biomedicine

Autor: Anna Korhonen, Karin Verspoor, Thomas Lippincott, Laura Rimell, Helen L. Johnson

Publikováno v: Journal of Biomedical Informatics. 46(2):228-237

Background: Biomedical natural language processing (NLP) applications that have access to detailed resources about the linguistic characteristics of biomedical language demonstrate improved performance on tasks such as relation extraction and syntact

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3db868a04cdf33be3bfcf22e33f3dcf

Predicting the Direction of Derivation in English Conversion

Autor: Laura Rimell, Alexis Palmer, Max Kisselew, Sebastian Padó

Publikováno v: SIGMORPHON

Conversion is a word formation operation that changes the grammatical category of a word in the absence of overt morphology. Conversion is extremely productive in English (e.g., tunnel, talk). This paper investigates whether distributional informatio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0f028ad96de699fd08a4e5cced946abd
https://doi.org/10.18653/v1/w16-2015