An Information-Theoretic Quantification of Discrimination with Exempt Features

Autor: Anupam Datta, Pulkit Grover, Piotr Mardziel, Praveen Venkatesh, Sanghamitra Dutta

Publikováno v: AAAI

The needs of a business (e.g., hiring) may require the use of certain features that are critical in a way that any discrimination arising due to them should be exempted. In this work, we propose a novel information-theoretic decomposition of the tota

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::970cdb2ca2ae6f692b8b5efcb7cd9b04
https://doi.org/10.1609/aaai.v34i04.5794

Quantitative Equational Reasoning

Autor: Calderón Trilla, Michael Hicks, José Manuel, Ian Sweet, Stephen Magill, Piotr Mardziel

Publikováno v: Bacci, G, Mardare, R, Panangaden, P & Plotkin, G D 2020, Quantitative Equational Reasoning . in G Barthe, J-P Katoen & A Silva (eds), Foundations of Probabilistic Programming . Cambridge University Press, pp. 333-360 . https://doi.org/10.1017/9781108770750.011

Equational logic has been a central theme in mathematical reasoning and in reasoning about programs. We introduce a quantitative analogue of equational reasoning that allows one to reason about approximate equality. The equality symbol is annotated w

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d2e3f1263540d6bac865b29347d894a0
https://vbn.aau.dk/da/publications/dcd33553-7b69-4222-a4b7-16ea6a9b45f1

Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models

Autor: Matt Fredrikson, Anupam Datta, Kaiji Lu, Klas Leino, Piotr Mardziel

Publikováno v: ACL

LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs learn structural features of natural languages such as subject-verb number

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51e8819a9814a723f9f2736bfbd50054
https://doi.org/10.18653/v1/2020.acl-main.430

Gender Bias in Neural Natural Language Processing

Autor: Fangjing Wu, Anupam Datta, Kaiji Lu, Piotr Mardziel, Preetam Amancharla

Publikováno v: Logic, Language, and Security ISBN: 9783030620769
Logic, Language, and Security

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::abbb3f0116448241f06907b165e4d350
https://doi.org/10.1007/978-3-030-62077-6_14

Evaluating Design Tradeoffs in Numeric Static Analysis for Java

Autor: Piotr Mardziel, Michael Hicks, Jeffrey S. Foster, Andrew Ruef, Shiyi Wei

Publikováno v: Programming Languages and Systems ISBN: 9783319898834
ESOP

Numeric static analysis for Java has a broad range of potentially useful applications, including array bounds checking and resource usage estimation. However, designing a scalable numeric static analysis for real-world Java programs presents a multit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3e7f94b3527c4341791913872de0a371
https://doi.org/10.1007/978-3-319-89884-1_23