Publications (4)
Uncertainty Quantification for Named Entity Recognition via Full-Sequence and Subsequence Conformal Prediction
Matthew Singer, Srijan Sengupta, Karl Pazdernik
Named Entity Recognition (NER) serves as a foundational component in many natural language processing (NLP) pipelines. However, current NER models typically output a single predict…
Beam-controlled spectral-selective architecture with planar polydimethylsiloxane/metal-films for all-day radiative cooling
Lyu Zhou, Haomin Song, Jianwei Liang +9
Radiative cooling is a passive cooling strategy with zero consumption of electricity. Although this technology can work well during optimal atmospheric conditions at nighttime, it…
Graded nanocomposite metamaterials for a double-sided radiative cooling architecture with a record breaking cooling power density
Lyu Zhou, Haomin Song, Nan Zhang +6
As an emerging electricity-free cooling technology, radiative cooling employs outer space as the heat sink. With this, a sky-facing thermal emitter is usually required. Due to the…
Word Embeddings as Statistical Estimators
Neil Dey, Matthew Singer, Jonathan P. Williams +1
Word embeddings are a fundamental tool in natural language processing. Currently, word embedding methods are evaluated on the basis of empirical performance on benchmark data sets,…