Search Results for author:
Found 7 papers, 4 papers with code
Optimally Controllable Perceptual Lossy Compression
We prove that arbitrary points of the D-P tradeoff bound can be achieved by a simple linear interpolation between the outputs of a minimum MSE decoder and a specifically constructed perfect perceptual decoder.
Optimal Transport for Unsupervised Denoising Learning
Toward answering this question, this work proposes a criterion for unsupervised denoising learning based on the optimal transport theory.
On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder.
Mention Extraction and Linking for SQL Query Generation
On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots.
FASTMATCH: Accelerating the Inference of BERT-based Text Matching
Recently, pre-trained language models such as BERT have shown state-of-the-art accuracies in text matching.
SQL Generation via Machine Reading Comprehension
Text-to-SQL systems offers natural language interfaces to databases, which can automatically generates SQL queries given natural language questions.
