Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Allen Schmaltz"'
Autor:
Allen Schmaltz
Publikováno v:
Computational Linguistics, Vol 47, Iss 4, Pp 729-773 (2021)
AbstractWe propose a new, more actionable view of neural network interpretability and data analysis by leveraging the remarkable matching effectiveness of representations derived from deep networks, guided by an approach for class-conditional feature
Externí odkaz:
https://doaj.org/article/8a110c2972ac434893b7707757d30c43
Publikováno v:
Political Analysis. 28:65-86
Ecological inference (EI) is the process of learning about individual behavior from aggregate data. We study a partially identified linear contextual effects model for EI and describe how to estimate the district level parameter averaging over many p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::399e4d871f3899c71119ff6d72baac88
https://doi.org/10.1017/pan.2019.19
https://doi.org/10.1017/pan.2019.19
Autor:
Allen Schmaltz, Andrew L. Beam
Publikováno v:
Spine J
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a02cf97124b4f501f1ad6bff2784ac92
https://europepmc.org/articles/PMC7904953/
https://europepmc.org/articles/PMC7904953/
Autor:
Allen Schmaltz
Publikováno v:
EthNLP@NAACL-HLT
In this position paper, we propose that the community consider encouraging researchers to include two riders, a “Lay Summary” and an “AI Safety Disclosure”, as part of future NLP papers published in ACL forums that present user-facing systems
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8a7b63dd4e5370d7d01870fca921e1b6
https://doi.org/10.18653/v1/w18-0801
https://doi.org/10.18653/v1/w18-0801
Publikováno v:
EMNLP
In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::365dc073b78aed31bc04bf030d4c3a63
http://arxiv.org/abs/1707.09067
http://arxiv.org/abs/1707.09067
Publikováno v:
EMNLP
Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence. We find that, in fact, an n-gram language model with a simple heuristic gives strong results on this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::735e74ce21219a2aa8525393bd3517b1
https://doi.org/10.18653/v1/d16-1255
https://doi.org/10.18653/v1/d16-1255
Publikováno v:
BEA@NAACL-HLT
We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016. The attention-based encoder-decoder models can be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b6b6bd26e8fa2df71147b352f52263ef
https://doi.org/10.18653/v1/w16-0528
https://doi.org/10.18653/v1/w16-0528