2.2k citations
- Massachusetts Institute of TechnologyUS303 papers
- Harvard UniversityUS23 papers
- MIT Lincoln LaboratoryUS17 papers
- IIT@MITUS16 papers
- Stanford UniversityUS16 papers
- Intel (United States)US13 papers
- Microsoft (United States)US12 papers
- University of California, BerkeleyUS12 papers
- University of WashingtonUS12 papers
- Carnegie Mellon UniversityUS11 papers
- Google (United States)US11 papers
- Massachusetts General HospitalUS11 papers
8 papers · 2 filters
Implementing a Portable Clinical NLP System with a Common Data Model - a Lisp Perspective
Yuan Luo, Peter Szolovits
This paper presents a Lisp architecture for a portable NLP system, termed LAPNLP, for processing clinical notes. LAPNLP integrates multiple standard, customized and in-house develo…
Towards Unsupervised Speech-to-Text Translation
Yu-An Chung, Wei-Hung Weng, Schrasing Tong +1
We present a framework for building speech-to-text translation (ST) systems using only monolingual speech and text corpora, in other words, speech utterances from a source language…
Multi-Source Domain Adaptation with Mixture of Experts
Jiang Guo, Darsh J Shah, Regina Barzilay
We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example a…
Deriving Machine Attention from Human Rationales
Yujia Bao, Shiyu Chang, Mo Yu +1
Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectiv…
On Training Recurrent Networks with Truncated Backpropagation Through Time in Speech Recognition
Hao Tang, James Glass
Recurrent neural networks have been the dominant models for many speech and language processing tasks. However, we understand little about the behavior and the class of functions r…
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition
Hao Tang, Wei-Ning Hsu, Francois Grondin +1
Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on ta…