Papers by Michael Kranzlein
Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite high accuracy, modern neural networks can still suffer from severe miscalibration. |
| Approach: | They propose to use tag frequency grouping to measure calibration error in different frequency bands to reduce error. |
| Outcome: | The proposed techniques reduce calibration error across the marginal distribution for two existing sequence taggers. |
CuRIAM: Corpus Re Interpretation and Metalanguage in U.S. Supreme Court Opinions (2024.lrec-main)
Copied to clipboard
| Challenge: | judicial opinions use language to comment on or draw attention to other language . a recent case involving a federal anti-discrimination law requires that justices determine the meaning of just one word or phrase in a specific context. |
| Approach: | They identify 9 categories prominent in metalinguistic discussions, including key terms, definitions, and different kinds of sources. |
| Outcome: | The results show that the annotated concepts are well-defined and frequent, and that they differ between majority, concurring, and dissenting opinions. |