Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Sean Welleck"'
Autor:
Peter West, Chandra Bhagavatula, Jack Hessel, Jena Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi
The common practice for training commonsense models has gone from-human-to-corpus-to-machine: humans author commonsense knowledge graphs in order to train commonsense models. In this work, we investigate an alternative, from-machine-to-corpus-to-mach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fbedaaf170593a37cb2b165cc753070e
Despite its wide use, recent studies have revealed unexpected and undesirable properties of neural autoregressive sequence models trained with maximum likelihood, such as an unreasonably high affinity to short sequences after training and to infinite
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f75e271431c2530953d82e7a131f51a6
Publikováno v:
EMNLP (1)
Despite strong performance on a variety of tasks, neural sequence models trained with maximum likelihood have been shown to exhibit issues such as length bias and degenerate repetition. We study the related issue of receiving infinite-length sequence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f90a716e88887ab2e3f0d4a142ebec9b
http://arxiv.org/abs/2002.02492
http://arxiv.org/abs/2002.02492
Autor:
Kyunghyun Cho, Stephen Roller, Sean Welleck, Margaret Li, Ilia Kulikov, Y-Lan Boureau, Jason Weston
Publikováno v:
ACL
Generative dialogue models currently suffer from a number of problems which standard maximum likelihood training does not address. They tend to produce generations that (i) rely too much on copying from the context, (ii) contain repetitions within ut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7e2bed0d5d0aea03cda3cd6c4fce45a
https://doi.org/10.18653/v1/2020.acl-main.428
https://doi.org/10.18653/v1/2020.acl-main.428
Autor:
Kyunghyun Cho, Sean Welleck
Publikováno v:
RANLP
We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and easy-first parsi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ba863edc04c040dd4042be4c8d6b49c
https://doi.org/10.26615/978-954-452-056-4_153
https://doi.org/10.26615/978-954-452-056-4_153
Autor:
Sean Welleck
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319306704
ECIR
ECIR
Adequate evaluation of an information retrieval system to estimate future performance is a crucial task. Area under the ROC curve (AUC) is widely used to evaluate the generalization of a retrieval system. However, the objective function optimized in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3914a01a5dbaa3752547c7b52b1480f
https://doi.org/10.1007/978-3-319-30671-1_12
https://doi.org/10.1007/978-3-319-30671-1_12