6 citations · 6 across the 1 of their papers we have counts for
3 papers
cs.CL2020
Unsupervised Evaluation for Question Answering with Transformers
Lukas Muttenthaler, Isabelle Augenstein, Johannes Bjerva
It is challenging to automatically evaluate the answer of a QA model at inference time. Although many models provide confidence scores, and simple heuristics can go a long way towa…
cs.CL2020
Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
Lukas Muttenthaler
Understanding subjectivity demands reasoning skills beyond the realm of common knowledge. It requires a machine learning model to process sentiment and to perform opinion mining. I…
cs.CL2020★ 6 cited
Human brain activity for machine attention
Lukas Muttenthaler, Nora Hollenstein, Maria Barrett
Cognitively inspired NLP leverages human-derived data to teach machines about language processing mechanisms. Recently, neural networks have been augmented with behavioral data to…