Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Arabshahi, Forough"'
Publikováno v:
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:11360-11397, 2023
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpretable models require extensiv
Externí odkaz:
http://arxiv.org/abs/2307.05350
We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explain
Externí odkaz:
http://arxiv.org/abs/2302.10289
Autor:
Singla, Sumedha, Murali, Nihal, Arabshahi, Forough, Triantafyllou, Sofia, Batmanghelich, Kayhan
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie clos
Externí odkaz:
http://arxiv.org/abs/2210.12196
Autor:
Sethi, Pooja, Savenkov, Denis, Arabshahi, Forough, Goetz, Jack, Tolliver, Micaela, Scheffer, Nicolas, Kabul, Ilknur, Liu, Yue, Aly, Ahmed
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work, we present a system called AutoNLU, which we designed to scale the N
Externí odkaz:
http://arxiv.org/abs/2110.06384
One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users' commands, a task trivial for humans due to their common sense. In this paper, we propose a zero-shot commonsense reasoning syste
Externí odkaz:
http://arxiv.org/abs/2109.08544
Autor:
Arabshahi, Forough, Lee, Jennifer, Gawarecki, Mikayla, Mazaitis, Kathryn, Azaria, Amos, Mitchell, Tom
In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the comman
Externí odkaz:
http://arxiv.org/abs/2006.10022
We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tree Stack Memory Units (Tree-SM
Externí odkaz:
http://arxiv.org/abs/1911.01545
Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain utterance,
Externí odkaz:
http://arxiv.org/abs/1910.12197
Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, especially on problems and programs with high complexity or on large domai
Externí odkaz:
http://arxiv.org/abs/1801.04342
In this paper, we propose guaranteed spectral methods for learning a broad range of topic models, which generalize the popular Latent Dirichlet Allocation (LDA). We overcome the limitation of LDA to incorporate arbitrary topic correlations, by assumi
Externí odkaz:
http://arxiv.org/abs/1605.09080