Li Fei-Fei

Audio-linguistic Embeddings for Spoken Sentences

2019

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence level. …

Visualizing and Understanding Recurrent Networks

2015 · arXiv (Cornell University)

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data. …

OpenTag

2018

Extraction of missing attribute values is to find values describing an attribute of interest from a free text input. Most past related work on extraction of missing attribute values work with a closed world assumption …