Brian Roark (Google Research) – Good-Turing Estimation from Uncertain Data for Semi-Supervised Language Model Adaptation

[video]

Abstract

We present a new algorithm for efficiently training n-gram language models on uncertain data, and illustrate its use for semi-supervised language model adaptation. We compute the probability that an n-gram occurs k times in the sample of uncertain data, and use the resulting histograms to derive a generalized Katz back-off model. We compare three approaches to semi-supervised adaptation of language models for speech recognition of selected YouTube video categories: (1) using just the one-best output from the baseline speech recognizer or (2) using samples from lattices with standard algorithms versus (3) using full lattices with our new algorithm. Unlike the other methods, our new algorithm provides models that yield solid improvements over the baseline on the full test set, and, further, achieves these gains without hurting performance on any of the set of video categories. We show that categories with the most data yielded the largest gains. The algorithm has been released as part of the OpenGRM n-gram library. Time permitting, we will also present some thoughts about training FST-based n-gram language models in a distributed setting.

Bio

Brian Roark is a computational linguist working on various topics in natural language processing. His research interests include: syntactic parsing of text and speech; language modeling for automatic speech recognition and other applications; supervised and unsupervised learning of language and parsing models; text entry, accessibility and augmentative & alternative communication (AAC).

Before joining Google, he was a faculty member for 9 years in the Center for Spoken Language Understanding (CSLU) at Oregon Health & Science University (OHSU) – part of what used to be the Oregon Graduate Institute (OGI). Before that, he was in the Speech Algorithms Department at AT&T Labs – Research from 2001–2004. He received his PhD in the Department of Cognitive and Linguistic Sciences at Brown University in 2001.

Center for Language and Speech Processing