An official website of the United States government
- Home
- Search Results
- Page 1 of 1
Search for: All records
-
Total Resources3
- Resource Type
-
0002000001000000
- More
- Availability
-
30
- Author / Contributor
- Filter by Author / Creator
-
-
Das, Anubrata (3)
-
Kovatchev, Venelin (2)
-
Lease, Matthew (2)
-
Li, Junyi Jessy (2)
-
Burke, Robin (1)
-
Chatterjee, Trina (1)
-
Chen, Jifan (1)
-
Choi, Eunsol (1)
-
Chronis, Gabriella (1)
-
Diaz, Fernando (1)
-
Ekstrand, Michael D. (1)
-
Erk, Katrin (1)
-
Govindarajan, Venkata S (1)
-
Gupta, Chitrank (1)
-
Mahowald, Kyle (1)
-
Wu, Yating (1)
-
#Tyler Phillips, Kenneth E. (0)
-
#Willis, Ciara (0)
-
& Abreu-Ramos, E. D. (0)
-
& Abramson, C. I. (0)
-
- Filter by Editor
-
-
& Spizer, S. M. (0)
-
& . Spizer, S. (0)
-
& Ahn, J. (0)
-
& Bateiha, S. (0)
-
& Bosch, N. (0)
-
& Brennan K. (0)
-
& Brennan, K. (0)
-
& Chen, B. (0)
-
& Chen, Bodong (0)
-
& Drown, S. (0)
-
& Ferretti, F. (0)
-
& Higgins, A. (0)
-
& J. Peters (0)
-
& Kali, Y. (0)
-
& Ruiz-Arias, P.M. (0)
-
& S. Spitzer (0)
-
& Sahin. I. (0)
-
& Spitzer, S. (0)
-
& Spitzer, S.M. (0)
-
(submitted - in Review for IEEE ICASSP-2024) (0)
-
-
Have feedback or suggestions for a way to improve these results?
!
Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
-
Das, Anubrata; Gupta, Chitrank; Kovatchev, Venelin; Lease, Matthew; Li, Junyi Jessy (, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics)We present ProtoTEx, a novel white-box NLP classification architecture based on prototype networks (Li et al., 2018). ProtoTEx faithfully explains model decisions based on prototype tensors that encode latent clusters of training examples. At inference time, classification decisions are based on the distances between the input text and the prototype tensors, explained via the training examples most similar to the most influential prototypes. We also describe a novel interleaved training algorithm that effectively handles classes characterized by ProtoTEx indicative features. On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERTlarge with the added benefit of providing faithful explanations. A user study also shows that prototype-based explanations help non-experts to better recognize propaganda in online news.more » « less
-
Kovatchev, Venelin; Chatterjee, Trina; Govindarajan, Venkata S; Chen, Jifan; Choi, Eunsol; Chronis, Gabriella; Das, Anubrata; Erk, Katrin; Lease, Matthew; Li, Junyi Jessy; et al (, Proceedings of DADC Workshop)
