Search Results for author:
Found 18 papers, 8 papers with code
Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models
Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time.
Re-examining Routing Networks for Multi-task Learning
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.
Limitations of Autoregressive Models and Their Alternatives
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.
Distributed Gradient Methods for Nonconvex Optimization: Local and Global Convergence Guarantees
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
Personalized Language Model for Query Auto-Completion
Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types.
Community Member Retrieval on Social Media using Textual Information
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.
Real-Time Prediction of the Duration of Distribution System Outages
This paper addresses the problem of predicting duration of unplanned power outages, using historical outage records to train a series of neural network predictors.
Low-Rank RNN Adaptation for Context-Aware Language Modeling
A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions.
Improving Context Aware Language Models
Increased adaptability of RNN language models leads to improved predictions that benefit many applications.
Match-Tensor: a Deep Relevance Model for Search
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.
Hierarchical Character-Word Models for Language Identification
Social media messages' brevity and unconventional spelling pose a challenge to language identification.
Domain Adaptation of Recurrent Neural Networks for Natural Language Understanding
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.
Talking to the crowd: What do people react to in online discussions?
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.
What Your Username Says About You
Experimental results on the two tasks demonstrate the effectiveness of the proposed morphological features compared to a character n-gram baseline.
Leveraging Twitter for Low-Resource Conversational Speech Language Modeling
In applications involving conversational speech, data sparsity is a limiting factor in building a better language model.
