1 code implementation • NAACL 2022 • Qinyuan Ye, Madian Khabsa, Mike Lewis, Sinong Wang, Xiang Ren, Aaron Jaech
Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time.
no code implementations • 1 Jan 2021 • Limeng Cui, Aaron Jaech
We re-examine Routing Networks, an approach to multi-task learning that uses reinforcement learning to decide parameter sharing with the goal of maximizing knowledge transfer between related tasks while avoiding task interference.
no code implementations • NAACL 2021 • Chu-Cheng Lin, Aaron Jaech, Xin Li, Matthew R. Gormley, Jason Eisner
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.
no code implementations • 23 Mar 2020 • Brian Swenson, Soummya Kar, H. Vincent Poor, José M. F. Moura, Aaron Jaech
We discuss local minima convergence guarantees and explore the simple but critical role of the stable-manifold theorem in analyzing saddle-point avoidance.
Optimization and Control
4 code implementations • ACL 2018 • Aaron Jaech, Mari Ostendorf
Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types.
1 code implementation • NAACL 2018 • Aaron Jaech, Shobhit Hathi, Mari Ostendorf
This paper addresses the problem of community membership detection using only text features in a scenario where a small number of positive labeled examples defines the community.
no code implementations • 3 Apr 2018 • Aaron Jaech, Baosen Zhang, Mari Ostendorf, Daniel S. Kirschen
This paper addresses the problem of predicting duration of unplanned power outages, using historical outage records to train a series of neural network predictors.
1 code implementation • TACL 2018 • Aaron Jaech, Mari Ostendorf
A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions.
1 code implementation • 21 Apr 2017 • Aaron Jaech, Mari Ostendorf
Increased adaptability of RNN language models leads to improved predictions that benefit many applications.
1 code implementation • 26 Jan 2017 • Aaron Jaech, Hetunandan Kamisetty, Eric Ringger, Charlie Clarke
The architecture of the Match-Tensor model simultaneously accounts for both local relevance matching and global topicality signals allowing for a rich interplay between them when computing the relevance of a document to a query.
1 code implementation • WS 2016 • Aaron Jaech, George Mulcaire, Shobhit Hathi, Mari Ostendorf, Noah A. Smith
Social media messages' brevity and unconventional spelling pose a challenge to language identification.
no code implementations • 1 Apr 2016 • Aaron Jaech, Larry Heck, Mari Ostendorf
The goal of this paper is to use multi-task learning to efficiently scale slot filling models for natural language understanding to handle multiple target tasks or domains.
no code implementations • EMNLP 2015 • Aaron Jaech, Victoria Zayats, Hao Fang, Mari Ostendorf, Hannaneh Hajishirzi
This paper addresses the question of how language use affects community reaction to comments in online discussion forums, and the relative importance of the message vs. the messenger.
1 code implementation • EMNLP 2015 • Aaron Jaech, Mari Ostendorf
Experimental results on the two tasks demonstrate the effectiveness of the proposed morphological features compared to a character n-gram baseline.
no code implementations • 9 Apr 2015 • Aaron Jaech, Mari Ostendorf
In applications involving conversational speech, data sparsity is a limiting factor in building a better language model.