Publications
-
Exploiting Information Extraction Annotations for Document Retrieval in Distillation Tasks
In this paper, we present our approach for using information extraction annotations to augment document retrieval for distillation. We take advantage of the fact that some of the distillation queries…
-
Integrating MAP, Marginals, and Unsupervised Language Model Adaptation
We investigate the integration of various language model adaptation approaches for a cross-genre adaptation task to improve Mandarin ASR system performance on a recently introduced new genre, broadcast conversation (BC).
-
Co-training Using Prosodic and Lexical Information for Sentence Segmentation
We investigate the application of the co-training learning algorithm on the sentence boundary classification problem by using lexical and prosodic information. Co-training is a semisupervised machine learning algorithm that uses…
-
The SRI/OGI 2006 Spoken Term Detection System
This paper describes the system developed jointly at SRI and OGI for participation in the 2006 NIST Spoken Term Detection (STD) evaluation.
-
A Smoothing Kernel for Spatially Related Features and Its Application to Speaker Verification
Most commonly used kernels are invariant to permutations of the feature vector components. We will consider one such case, where the features are spatially related and show a way to…
-
Leveraging graph locality via abstraction
The use of abstraction to speedup problem solving is ubiquitous in AI, especially in the field of heuristic search where abstraction has proven a crucial technique for creating highly accurate…
-
Regression testing for grammar-based systems
This paper describes best practices in two closely related regression testing frameworks used in grammar-based systems: MedSLT, a spoken language translation system based on the Regulus platform, and a search…
-
An LFG Chinese grammar for machine use
This paper describes the Chinese grammar developed at PARC, including its three basic components: the tokenizer and tagger, lexicon and syntactic rules.
-
PARC’s Bridge question answering system
This paper describes a system designed to robustly map from natural language sentences to logical, abstract knowledge representations (the Bridge system).
-
Overlay mechanisms for multi-level deep processing applications
This paper discusses some engineering tools that are used in the XLE grammar development platform to allow for domain specialization.
-
Results from Levels 2/3 Fusion Implementations: Issues, Challenges, Retrospectives and Perspectives for the Future an Annotated Perspective
This paper is a retrospective annotated view of the invited panel discussion organized by Ivan Kadar (first author), supported by John Salerno, in order to provide both a historical perspective…
-
A Preference Model for Over-Constrained Meeting Requests
We develop a preference model designed to capture user scheduling preferences for overconstrained meeting requests between multiple people, and a methodology for preference elicitation to initially populate this model.