Search Results for author:
Found 11 papers, 8 papers with code
Learning to Plan for Language Modeling from Unlabeled Data
By training to predict the next token in an unlabeled corpus, large language models learn to perform many tasks without any labeled data.
Triple-Encoders: Representations That Fire Together, Wire Together
Search-based dialog models typically re-encode the dialog history at every turn, incurring high cost.
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition
In particular, multi-head HyperConformer achieves comparable or higher recognition performance while being more efficient than Conformer in terms of inference speed, memory, parameter count, and available training data.
BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
In this paper, we present a novel formulation of Combinatorial Optimization Problems (COPs) as Markov Decision Processes (MDPs) that effectively leverages common symmetries of COPs to improve out-of-distribution robustness.
Combinatorial Optimization
Out-of-Distribution Generalization
HyperMixer: An MLP-based Low Cost Alternative to Transformers
We find that existing architectures such as MLPMixer, which achieves token mixing through a static MLP applied to each feature independently, are too detached from the inductive biases required for natural language understanding.
Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation
We address this issue by extending their method to Bag-of-Vectors Autoencoders (BoV-AEs), which encode the text into a variable-size bag of vectors that grows with the size of the text, as in attention-based models.
Plug and Play Autoencoders for Conditional Text Generation
Text autoencoders are commonly used for conditional generation tasks such as style transfer.
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning
The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration.
Multi-Modal Adversarial Autoencoders for Recommendations of Citations and Subject Labels
We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: citation recommendation and subject label recommendation.
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
In order to address this shortcoming, we propose a learning algorithm for the Continuous Matrix Space Model, which we call Continual Multiplication of Words (CMOW).
Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
For the first time, we offer a systematic comparison of classification approaches to investigate how far semantic annotations can be conducted using just the metadata of the documents such as titles published as labels on the Linked Open Data cloud.
