Underreporting of errors in NLG output, and what to do about it
We observe a severe under-reporting of the different kinds of errors that Natural Language
Generation systems make. This is a problem, because mistakes are an important indicator of …
Generation systems make. This is a problem, because mistakes are an important indicator of …
CS-Shapley: class-wise Shapley values for data valuation in classification
Data valuation, or the valuation of individual datum contributions, has seen growing interest
in machine learning due to its demonstrable efficacy for tasks such as noisy label detection. …
in machine learning due to its demonstrable efficacy for tasks such as noisy label detection. …
“This is a Problem, Don't You Agree?” Framing and Bias in Human Evaluation for Natural Language Generation
Despite recent efforts reviewing current human evaluation practices for natural language
generation (NLG) research, the lack of reported question wording and potential for framing …
generation (NLG) research, the lack of reported question wording and potential for framing …
Data selection for fine-tuning large language models using transferred shapley values
Although Shapley values have been shown to be highly effective for identifying harmful training
instances, dataset size and model complexity constraints limit the ability to apply Shapley…
instances, dataset size and model complexity constraints limit the ability to apply Shapley…
Barriers and enabling factors for error analysis in NLG research
…, S Mahamood, S Schoch… - Northern …, 2023 - napier-repository.worktribe.com
Earlier research has shown that few studies in Natural Language Generation (NLG)
evaluate their system outputs using an error analysis, despite known limitations of automatic …
evaluate their system outputs using an error analysis, despite known limitations of automatic …
[HTML][HTML] Hepatitis A virus incidence rates and biomarker dynamics for plasma donors, United States
S Schoch, M Wälti, M Schemmerer… - Emerging Infectious …, 2021 - ncbi.nlm.nih.gov
The United States is currently affected by widespread hepatitis A virus (HAV) outbreaks. We
investigated HAV incidence rates among source plasma donors in the United States since …
investigated HAV incidence rates among source plasma donors in the United States since …
Contextualizing variation in text style transfer datasets
Text style transfer involves rewriting the content of a source sentence in a target style. Despite
there being a number of style tasks with available data, there has been limited systematic …
there being a number of style tasks with available data, there has been limited systematic …
Mergers and Acquisitions in the Data Economy
DS Schoch - Available at SSRN 3686247, 2020 - papers.ssrn.com
In research, public, and policy debate, there is increasing interest in data intensive firms like
Google, Facebook, and Amazon. As business models of data firms are often characterized …
Google, Facebook, and Amazon. As business models of data firms are often characterized …
[HTML][HTML] Ask and you shall receive?: A LibAnswers FAQ usability study
S Schoch, A VerMeulen - Weave: Journal of …, 2022 - journals.publishing.umich.edu
St. Mary’s College of Maryland (SMCM) has an enrollment of approximately 1,500 students.
As a rural school, the majority of students live on campus. At the time of this study, the …
As a rural school, the majority of students live on campus. At the time of this study, the …
MIT CAACB Risk Assessment Case Study: Assessing virus cross-contamination risk between two simultaneous processes in an open biomanufacturing facility
…, S Parriott, GK Raju, C Scallan, S Schoch… - PDA Journal of …, 2023 - journal.pda.org
Some members of MIT's Consortium on Adventitious Agent Contamination in Biomanufacturing
(CAACB) previously published content on the “Quality Risk Management in the Context …
(CAACB) previously published content on the “Quality Risk Management in the Context …