Applying Automatically Generated Semantic Knowledge A Case Study in Machine Translation (2009)
Nitin Madnani, Philip Resnik, Bonnie Dorr, Richard Schwartz
In this paper, we discuss how we apply automatically generated semantic knowledge to benefit statistical machine translation (SMT). Currently, almost all statistical machine translation systems rely...
Nitin Madnani, Philip Resnik, Bonnie J. Dorr, Richard Schwartz
Most state-of-the-art statistical machine translation systems use log-linear models, which are defined in terms of hypothesis features and weights for those features. It is standard to tune the...
Language and Translation Model Adaptation using Comparable Corpora (2009)
Matthew Snover, Bonnie Dorr, Richard Schwartz
Traditionally, statistical machine translation systems have relied on parallel bi-lingual data to train a translation model. While bi-lingual parallel data are expensive to generate, monolingual data...
Improved Word-Level System Combination for Machine Translation (2009)
Spyros Matsoukas, Richard Schwartz
Recently, confusion network decoding has been applied in machine translation system combination. Due to errors in the hypothesis alignment, decoding may result in ungrammatical combination outputs....
Quasiperiodic Motion for the Pentagram Map (2009)
Ovsienko, Valentin, Schwartz, Richard, Tabachnikov, Serge
The pentagram map is a projectively natural iteration defined on polygons, and also on a generalized notion of a polygon which we call {\it twisted polygons}. In this note we describe our recent work...
Quasiperiodic Motion for the Pentagram Map (2009)
Ovsienko, Valentin, Schwartz, Richard, Tabachnikov, Serge
The pentagram map is a projectively natural iteration defined on polygons, and also on a generalized notion of a polygon which we call {\it twisted polygons\/}. In this note we describe our recent...
Quasiperiodic Motion for the Pentagram Map (2009)
Ovsienko, Valentin, Schwartz, Richard, Tabachnikov, Serge
The pentagram map is a projectively natural iteration defined on polygons, and also on a generalized notion of a polygon which we call {\it twisted polygons\/}. In this note we describe our recent...
1.1. The Named Entity Task (2008)
Daniel M. Bikel, Richard Schwartz, Ralph M. Weischedel
Abstract. In this paper, we present IdentiFinder™, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities. We have evaluated the model in English...
ON-LINE CURSIVE HANDWRITING RECOGNITION USING SPEECH RECOGNITION METHODS (2008)
Thad Starnert, John Makhoul, Richard Schwartz, George Chou
A hidden Markov model (HMM) based continuous speech recognition system is applied to on-line cursive handwrit-ing recognition. The base system is unmodified except for using handwriting feature...
ADAPTATION TO NEW MICROPHONES USING TIED-MIXTURE NORMALIZATION (2008)
Anastasios Anastasakost, Francis Kubala, John Makhoul, Richard Schwartz
In this paper, we present several approaches designed to increase the robustness of BYBLOS, the BBN continuous speech recogni-tion system. We address the problem of increased degradation in •...
The Pentagram map: a discrete integrable system (2008)
Ovsienko, Valentin, Schwartz, Richard, Tabachnikov, Serge
The pentagram map is a projectively natural iteration defined on polygons, and also on objects we call twisted polygons (a twisted polygon is a map from Z into the projective plane that is periodic...
OPTIMAL ESTIMATION OF REJECTION THRESHOLDS FOR TOPIC SPOTTING (2008)
Krishna Subramanian, Rohit Prasad, Prem Natarajan, Richard Schwartz
In many applications of topic spotting technology, especially those that require a human review of in-topic documents, a low false alarm rate is a key requirement. Topic spotting techniques typically...
Techniques, and Tools. Addison-Wesley, 1986. (2008)
Steven P. Abney, Carol Tenny, Alfred V. Aho, Daniel M. Bikel, Scott Miller, ...
[2] Steven Abney. Partial parsing via finite-state cascades. In Proceedings
Pomona College, Swarthmore College, (2008)
Katrin Kirchhoff, Jeff Bilmes, Sourin Das, Nicolae Duta, Melissa Egan, Gang Ji, ...
of Defense, � SRI Although Arabic is currently one of the most widely spoken languages in the world, there has been relatively little speech recognition research on Arabic compared to other...
Header for SPIE use A Robust, Language-Independent OCR System (2008)
Zhidong Lu, Issam Bazzi, Andras Kornai, John Makhoul, Premkumar Natarajan, Richard Schwartz
We present a language-independent optical character recognition (OCR) system that is capable, in principle, of recognizing printed text from most of the world’s languages. For each new language or...
A Robust, Language-Independent OCR System (2007)
Zhidong Lu, Issam Bazzi, Andras Kornai, John Makhoul, Premkumar Natarajan, Richard Schwartz
We present a language-independent optical character recognition (OCR) system that is capable, in principle, of recognizing printed text from most of the world's languages. For each new language...
BBN Systems and Technologies (2007)
Ralph Weischedel, Richard Schwartz, Jeff Palmucci, Marie Meteer T, Lance Ramshaw
From spring 1990 through fall 1991, we performed a battery of small experiments to test the effectiveness of supplementing knowledge-based techniques with probabilistic models. This paper reports our...
Running head: What's in a Name (2007)
Daniel M. Bikel, Richard Schwartz, Ralph M. Weischedel
Abstract. In this paper, we present IdentiFinder^TM, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities. We have evaluated the model in English...
Frederick Walls, Hubert Jin, Sreenivasa Sista, Richard Schwartz, Fawcett St
We propose a system for the Topic Detection and Tracking (TDT) detection task concerned with the unsupervised grouping of news stories according to topic. We use an incremental k-means algorithm for...
Use of Minimal Lexical Conceptual Structures for Single-Document Summarization (2007)
Dorr, Bonnie J., Habash, Nizar Y., Monz, Christof, Schwartz, Richard
This reports provides an overview of the findings and software that have evolved from the Use of Minimal Lexical Conceptual Structures for Single-Document Summarization project over the last six...
Adaptation to New Microphones Using Tied-Mixture Normalization (2007)
Anastasakos, Anastasios, Kubala, Francis, Makhoul, John, Schwartz, Richard
In this paper, we present several approaches designed to increase the robustness of BYBLOS, the BBN continuous speech recognition system. We address the problem of increased degradation in...
Efficient, High-Performance Algorithms for N-Best Search (2007)
Schwartz, Richard, Austin, Steve
We present two efficient search algorithms for real-time spoken language systems. The first called the Word-Dependent N-Best algorithm is an improved algorithm for finding the top N sentence...
Nguyen, Long, Schwartz, Richard, Zhao, Ying, Zavaliagkos, George
We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was little or no decrease...
Comparative Experiments on Large Vocabulary Speech Recognition (2007)
Schwartz, Richard, Anastasakos, Tasos, Kubala, Francis, Makhoul, John, Nguyen, Long, Zavaliagkos, George
This paper describes several key experiments in large vocabulary speech recognition. We demonstrate that, counter to our intuitions, given a fixed amount of training speech, the number of training...
Miller, Scott, Crystal, Michael, Fox, Heidi, Ramshaw, Lance, Schwartz, Richard, Stone, Rebecca, ...
For MUC-7, BBN has for the first time fielded a fully-trained system for NE, TE, and TR; results are all the output of statistical language models trained on annotated data, rather than programs...
Improved HMM Models for High Performance Speech Recognition (2007)
Austin, Steve, Barry, Chris, Chow, Yen-Lu, Derr, Alan, Kimball, Owen, Kubala, Francis, ...
In this paper we report on the various techniques that we implemented in order to improve the basic speech recognition performance of the BYBLOS system. Some of these methods are new, while others...
BBN BYBLOS and HARC February 1992 ATIS Benchmark Results (2007)
Kubala, Francis, Barry, Chris, Bates, Madeleine, Bobrow, Robert, Fung, Pascale, Ingria, Robert, ...
We present results from the February `92 evaluation on the ATIS travel planning domain for HARC, the BBN spoken language system (SLS). In addition, we discuss in detail the individual performance of...
Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2007)
Dorr, Bonnie, Zajic, David, Schwartz, Richard
This paper presents Hedge Trimmer a HEaDline GEneration system that creates a headline for a newspaper story using linguistically-motivated heuristics to guide the choice of a potential headline. We...
Multi-candidate reduction: Sentence compression as a tool for document summarization tasks (2007)
David Zajic, Bonnie J. Dorr, Jimmy Lin, Richard Schwartz
This article examines the application of two single-document sentence compression techniques to the problem of multi-document summarization—a “parse-and-trim ” approach and a statistical...
Headline Generation for Written and Broadcast News (2006)
Zajic, David, Dorr, Bonnie, Schwartz, Richard
This technical report is an overview of work done on Headline Generation for written and broadcast news. The report covers HMM Hedge, a statistical approach based on the noisy channel model, Hedge...
Search Algorithms for Software-Only Real-Time Recognition with Very Large Vocabularies (2006)
Nguyen, Long, Schwartz, Richard, Kubala, Francis, Placeway, Paul
This paper deals with search algorithms for real-time speech recognition. We argue that software-only speech recognition has several critical advantages over using special or parallel hardware. We...
Speaker Adaptation Using Multiple Reference Speakers (2006)
Kubala, Francis, Schwartz, Richard, Barry, Chris
We introduce a new technique for using the speech of multiple reference speakers as a basis for speaker adaptation in large vocabulary continuous speech recognition. In contrast to other methods that...
Toward a Real-Time Spoken Language System Using Commercial Hardware (2006)
Austin, Steve, Peterson, Pat, Placeway, Paul, Schwartz, Richard, Vandergrift, Jeff
We describe the methods and hardware that we are using to produce a real-tune demonstration of an integrated Spoken Language System. We describe algorithms that greatly reduce the computation needed...
A study of translation edit rate with targeted human annotation (2006)
Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, John Makhoul
We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments....
A study of translation error rate with targeted human annotation (2006)
Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, Ralph Weischedel
We define a new, intuitive measure for evaluating machine translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments....
A Study of Translation Error Rate with Targeted Human Annotation (2006)
Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, Ralph Weischedel
We define a new, intuitive measure for evaluating machine translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments....
RADC Reliability Notebook, Volume I. (2005)
Mazzilli, Fred, Mathis, John, Schwartz, Richard, Shapiro, Samuel
RADC Reliability Notebook, Volume I, is an updating of the RADC Reliability Notebook which was first published in 1958 and which had been revised several times up until the Fall of 1966. There are...
A Methodology for Extrinsic Evaluation of Text Summarization: Does ROUGE Correlate? (2005)
Bonnie Dorr, Christof Monz, Stacy President, Richard Schwartz, David Zajic
This paper demonstrates the usefulness of summaries in an extrinsic task of relevance judgment based on a new method for measuring agreement, Relevance-Prediction, which compares subjects '...
Headline generation for written and broadcast news, lamp-tr-120, cs-tr-4698 (2005)
David Zajic, Bonnie Dorr, Richard Schwartz
This technical report is an overview of work done on Headline Generation for written and broadcast news. The report covers HMM Hedge, a statistical approach based on the noisy channel model, Hedge...
Environmentalism and democracy in Hungary and Latvia [electronic resource] / (2004)
Steger, Tamara Shevaun., Schwartz, Richard.
Thesis (PH.D.) -- Syracuse University, 2004.
Extrinsic Evaluation of Automatic Metrics for Summarization (2004)
Bonnie Dorr, Christof Monz, Douglas Oard, Stacy President, David Zajic, Richard Schwartz
This paper describes extrinsic-task evaluation of summarization. We show that it is possible to save time using summaries for relevance assessment without adversely impacting the degree of accuracy...
Using N-best Lists for Named Entity Recognition from Chinese Speech (2004)
Lufeng Zhai, Pascale Fung, Richard Schwartz, Marine Carpuat, Dekai Wu
We present the first known result for named entity recognition (NER) in realistic largevocabulary spoken Chinese. We establish this result by applying a maximum entropy model, currently the single...
A Lexically-Driven Algorithm for Disfluency Detection (2004)
Matthew Snover, Bonnie Dorr, Richard Schwartz
This paper describes a transformationbased learning approach to disfluency detection in speech transcripts using primarily lexical features. Our method produces comparable results to two other...
RT-S: Surface rich transcription scoring, methodology, and initial results (2004)
Matthew Snover, Richard Schwartz, Bonnie Dorr, John Makhoul
In this paper we present a methodoly for the scoring of punctuation annotated texts, as well as a preliminary system to perform the task. We modify SCLITE’s scoring methodology to support scoring...
Keeping Circulation Services Relevant: Implementing a New Campus Book Retrieval Service (2003)
Dieterle, Ulrike, Dixon, Edie, Grow, Dineen, Koranda, MaryJo, Lewis, Anna, Mulvey, Sharon, ...
As e-books and e-journals become more prevalent many libraries are seeing use of their physical collections decline. At the same time patrons are requesting more comprehensive library services,...
Keeping Circulation Services Relevant: Implementing a New Campus Book Retrieval Service (2003)
Dieterle, Ulrike, Dixon, Edie, Grow, Dineen, Koranda, MaryJo, Lewis, Anna, Mulvey, Sharon, ...
As e-books and e-journals become more prevalent many libraries are seeing use of their physical collections decline. At the same time patrons are requesting more comprehensive library services,...
Speech Compression and Synthesis. (2002)
Berouti,Michael, Cosell,Lynn, Klovstad,John, Makhoul,John, Schwartz,Richard
This report describes our work for the past year on speech compression and synthesis. We implemented a real-time variable-frame-rate LPC vocoder operating at an average rate of 2000 bits/s. We also...
Speech Compression and Synthesis. (2002)
Berouti,Michael, Makoul,John, Schwartz,Richard, Sorensen,John
This report concludes our work for the past two years on speech compression and synthesis. A real-time variable-frame-rate LPC vocoder was implemented operating at an average rate of 2000 bits/s. We...
Research on Narrowband Communications. (2002)
Makhoul,John, Roukos,Salim, Krasner,Micheal, Schwartz,Richard, Sorensen,John
This document reports on work toward a very low rate vocoder. We model speech as a Markov Chain of spectral templates for the unsupervised learning approach to very low rate vocoding. This quarter...
Research on Narrowband Communications. (2002)
Makhoul,John, Krasner,Michael, Roukos,Salim, Schwartz,Richard, Sorensen,John
We report on research toward a very-low-rate vocoder. This quarter we continued investigation in three areas. The first area of research is multi-speaker synthesis: speech synthesis from the...
Research on Narrowband Communications. (2002)
Makhoul,John, Roukos,Salim, Schwartz,Richard
This document reports on work toward a very low rate vocoder. We model speech as a Markov Chain of spectral templates for the unsupervised learning approach to very low rate vocoding. This quarter we...
Research on Narrowband Communications. (2002)
Makhoul,John, Roukos,Salim, Schwartz,Richard
We report on research toward a very-low-rate vocoder. This quarter we continued investigation in two areas: the phonetic vocoder and an unsupervised method for vocoding. We introduced phoneme pair...
Research on Narrowband Communications. (2002)
Roucos,Salim, Schwartz,Richard, Makhoul,John
This report describes the methods used to implement a very-low-rate (VLR) vocoder that transmits speech with a bit rate in the range of 100 to 200 b/s. The primary goal of this two-year project was...
Research in Speech Understanding. (2002)
Schwartz,Richard, Makhoul,John, Roucos,Salim, Huggins,A. W. F.
This annual report describes the work performed during the first year of a two-year effort to develop improved techniques for acoustic-phonetic recognition, with eventual application to automatic...
Development of Real-Time Speech Recognition. (2002)
Krasner,Michael A., Schwartz,Richard, Kimball,Owen, Cosell,Lynn
This phase developed parallel processing techniques appropriate for real time speech recognition and demonstrated the feasibility of achieving real time recognition on the BBN Butterfly Parallel...
Unsupervised Topic Discovery (2001)
Richard Schwartz, Sreenivasa Sista, Timothy Leek
This white paper describes a new problem, which is to determine a set of topics or subjects automatically from a corpus. The result is a large number of topics, each with meaningful names. Each of...
Named entity extraction from noisy input: speech and OCR (2000)
David Miller, Scan Boisen, Richard Schwartz, Rebecca Stone, Ralph Weischedel
In this paper, we analyze the performance of name finding in the context of a variety of automatic speech recognition (ASR) systems and in the context of one optical character recognition (OCR)...
Topic Detection in broadcast news (1999)
Frederick Walls, Hubert Jin, Sreenivasa Sista, Richard Schwartz
We propose a system for the Topic Detection and Tracking (TDT) detection task concerned with the unsupervised grouping of news stories according to topic. We use an incremental k-means algorithm for...
The BBN crosslingual topic detection and tracking system (1999)
Tim Leek, Hubert Jin, Sreenivasa Sista, Richard Schwartz
This was the first year that the TDT program included a required crosslingual test: English and Mandarin. Most of our work, therefore, was to adapt our tracking and detection systems to work on a...
Topic Detection in broadcast news (1999)
Frederick Walls, Hubert Jin, Sreenivasa Sista, Richard Schwartz
We propose a system for the Topic Detection and Tracking (TDT) detection task concerned with the unsupervised grouping of news stories according to topic. We use an incremental k-means algorithm for...
Named entity extraction from broadcast news (1999)
David Miller, Richard Schwartz, Ralph Weischedel, Rebecca Stone
In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present...
Named entity extraction from broadcast news (1999)
David Miller, Richard Schwartz, Ralph Weischedel, Rebecca Stone
In this paper, we contrast the two tasks of named entity extraction from speech and text both qualitatively and quantitatively in the context of the DARPA 1998 Hub4e-IE evaluation. We will present...
Performance measures for information extraction (1999)
John Makhoul, Francis Kubala, Richard Schwartz, Ralph Weischedel
While precision and recall have served the information extraction community well as two separate measures of system performance, we show that the F-measure, the weighted harmonic mean of precision...
The 1998 BBN Byblos 10x Real Time System (1999)
Jason Davenport, Long Nguyen, Spyros Matsoukas, Richard Schwartz, John Makhoul
In this paper we describe the BBN Byblos 10x real time system used for the 1998 Hub-4 English tests. Given our state of the art primary system [1] running at 230 times real time (230 xRT) we show...
Performance measures for information extraction (1999)
John Makhoul, Francis Kubala, Richard Schwartz, Ralph Weischedel
While precision and recall have served the information extraction community well as two separate measures of system performance, we show that the F-measure, the weighted harmonic mean of precision...
Combining Multiple Knowledge Sources for Speech Recognition. (1998)
Schwartz, Richard, Makhoul, John
This annual report summarizes the work on using multiple knowledge sources in a speech recognition system. Included is research in search strategies, statistical language modeling and phonological...
Toward Real-Time Continuous Speech Recognition. (1998)
Schwartz, Richard, Kimball, Owen
This final report describes research on real-time speech recognition. The authors developed, under other DARPA-funded contracts, a system for continuous speech recognition. BYBLOS, the BBN Continuous...
Extrinsic Evaluation of Automatic Metrics for Summarization (1998)
Dorr, Bonnie, Monz, Christof, Oard, Douglas, President, Stacy, Zajic, David, Schwartz, Richard
This paper describes extrinsic-task evaluation of summarization. We show that it is possible to save time using summaries for relevance assessment without adversely impacting the degree of accuracy...
Nymble: a High-Performance Learning Name-finder (1998)
Bikel, Daniel M., Miller, Scott, Schwartz, Richard, Weischedel, Ralph
This paper presents a statistical, learned approach to finding names and other non-recursive entities in text (as per the MUC-6 definition of the NE task), using a variant of the standard hidden...
The 1997 BBN BYBLOS system applied to Broadcast News transcription (1998)
Francis Kubala, Jason Davenport, Hubert Jin, Daben Liu, Tim Leek, Spyros Matsoukas, ...
In this paper, we describe the BBN Byblos system used for the 1997 DARPA Hub-4 Broadcast News evaluation and discuss numerous improvements made to the system in 1997. We focused our effort entirely...
Named entity extraction from speech (1998)
Francis Kubala, Richard Schwartz, Rebecca Stone, Ralph Weischedel
We report results using a hidden Markov model to extract information from broadcast news. IdentiFinder ™ was trained on the broadcast news corpus and tested on both the 1996 HUB-4 development test...
Named entity extraction from speech (1998)
Francis Kubala, Richard Schwartz, Rebecca Stone, Ralph Weischedel
We report results using a hidden Markov model to extract information from broadcast news. IdentiFinder^TM was trained on the broadcast news corpus and tested on both the 1996 HUB-4 development test...
The 1997 BBN BYBLOS system applied to Broadcast News transcription (1998)
Francis Kubala, Jason Davenport, Hubert Jin, Daben Liu, Tim Leek, Spyros Matsoukas, ...
In this paper, we describe the BBN Byblos system used for the 1997 DARPA Hub-4 Broadcast News evaluation and discuss numerous improvements made to the system in 1997. We focused our e ort entirely...
Fast robust inverse transform SAT and multi-stage adaptation (1998)
Hubert Jin, Spyros Matsoukas, Richard Schwartz, Francis Kubala
We present a new method of Speaker Adapted Training (SAT) that is more robust, faster, and results in lower error rate than the previous methods. The method, called Inverse Transform SAT (ITSAT) is...
What size test set gives good error rate estimates (1998)
Isabelle Guyon, John Makhoul, Richard Schwartz
We address the problem of determining what size test set guarantees statistically significant results in a character recognition task, as a function of the expected error rate. We provide a...
Scott Miller, Michael Crystal, Heidi Fox, Lance Ramshaw, Richard Schwartz, Rebecca Stone, ...
For MUC-7, BBN has for the first time fielded a fully-trained system for NE, TE, and TR; results are all the output of statistical language models trained on annotated data, rather than programs...
Scott Miller, Michael Crystal, Heidi Fox, Lance Ramshaw, Richard Schwartz, Rebecca Stone, ...
All of BBN's research under the TIPSTER III program has focused on doing extraction by applying statistical models trained on annotated data, rather than by using programs that execute...
Efficient 2-Pass N-Best Decoder (1997)
Long Nguyen, Richard Schwartz, Fawcett St
In this paper, we describe the new BBN BYBLOS efficient 2-Pass N-Best decoder used for the 1996 Hub-4 Benchmark Tests. The decoder uses a quick fastmatch to determine the likely word endings. Then in...
Nymble: a High-Performance Learning Name-finder (1997)
Daniel M. Bikel, Scott Miller, Richard Schwartz, Ralph Weischedel
This paper presents a statistical, learned approach to finding names and other nonrecursive entities in text (as per the MUC-6 definition of the NE task), using a variant of the standard hidden...
Modeling Those F-Conditions - Or Not (1997)
Richard Schwartz, Hubert Jin, Francis Kubala, Spyros Matsoukas
After several disappointing preliminary attempts to make condition-speci#c models, we decided that it would be more advantageous to spend our time just trying to improve the core recognition system...
Modeling Those F-Conditions -- Or Not (1997)
Richard Schwartz, Hubert Jin, Francis Kubala, Yspyros Matsoukas
After several disappointing preliminary attempts to make condition-specific models, we decided that it would be more advantageous to spend our time just trying to improve the core recognition system...
Efficient 2-Pass N-Best Decoder (1997)
In this paper, we describe the new BBN BYBLOS e#cient 2-Pass N-Best decoder used for the 1996 Hub-4 Benchmark Tests. The decoder uses a quick fastmatch to determine the likely word endings. Then in...
A fully statistical approach to natural language interfaces (1996)
Scott Miller, David Stallard, Robert Bobrow, Richard Schwartz
We present a natural language interface system which is based entirely on trained statistical models. The system consists of three stages of processing: parsing, semantic interpretation, and...
Language understanding using hidden understanding models (1996)
Richard Schwartz, Scott Miller, David Stallard, John Makhoul
We describe the �rst sentence understanding system that is completely based on learned methods both for understanding individual sentences, and determinig their meaning in the context of preceding...
A compact model for speaker-adaptive training (1996)
Ytasos Anastasakos, John Mcdonough, Richard Schwartz, John Makhoul
In this work we formulate a novel approach to estimating the parameters of continuous density HMMs for speaker-independent (SI) continuous speech recognition. It is motivated by the fact that...
Transcribing radio news (1996)
Francis Kubala, Tasos Anastasakos, Hubert Jin, Long Nguyen, Richard Schwartz
We have recently extended the capabilities of BBN's large vocabulary discrete-utterance speech recognition system �BY-BLOS � to operate on raw audio recordings of radio news programming. The...
On-line cursive handwriting recognition using speech recognition methods (1994)
John Makhoul, Thad Starner, Richard Schwartz, George Chou
The BYBLOS continuous speech recognition system is applied to on-line cursive handwriting recognition. By exploiting similarities between on-line cursive handwriting and continuous speech...
Statistical language processing using hidden understanding models (1994)
Scott Miller, Richard Schwartz
This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models derives from...
On-Line Cursive Handwriting Recognition Using Speech Recognition Methods (1994)
Thad Starner, John Makhoul, Richard Schwartz, George Chou
A hidden Markov model (HMM) based continuous speech recognition system is applied to on-line cursive handwriting recognition. The base system is unmodified except for using handwriting feature...
Long Nguyen, Richard Schwartz, Ying Zhao, George Zavaliagkos T
We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was little or no decrease...
The BBN/HARC spoken language understanding system (1993)
Madeleine Bates, Robert Bobrow, Pascale Fung, Robert Ingria, Francis Kubala, John Makhoul, ...
We describe the design and performance of a complete spoken language understanding system currently under development at BBN. The system, dubbed HARC (Hear And Respond to Con-tinuous speech),...
The estimation of powerful language models from small and large corpora (1993)
Paul Placeway, Richard Schwartz, Pascale Fung, Long Nguyen
This paper deals with the estimation of powerful sta-tistical language models using a technique that scales from very small to very large amounts of domain-dependent data. We begin with an improved...
We consider the pentagram map on the space of plane convex pentagons obtained by drawing a pentagon's diagonals, recovering unpublished results of Conway and proving new ones. We generalize this to a...
POST: Using probabilities in language processing (1991)
Marie Meteer, Richard Schwartz, Ralph Weischedel
We report here on our experiments with POST (Part of Speech Tagger) to address problems of ambiguity and of understanding unknown words. Part of speech tagging, per se, is a well understood problem....
Preparation of islets of Langerhans from the hamster pancreas (1988)
Rosenberg, Lawrence, Schwartz, Richard, Dafoe, Donald C., Clarke, Susan, Turcotte, Jeremiah G., Vinik, Aaron I.
We describe a method for the preparation of viable islets from the pancreas of normal 8-week-old female Syrian golden hamster, based on the injection of the pancreatic duct with collagenase and on...
Thesis - Wisconsin.
HIDDEN UNDERSTANDING MODELS OF NATURAL LANGUAGE
Scott Miller, Robert Bobrow, Robert Ingria, Richard Schwartz
Coping with Ambiguity and Unknown Words through Probabilistic Models
Ralph Weischedel, Richard Schwartz, Jeff Palmucci, Marie Meteer, Lance Ramshaw
Nymble: a High-Performance Learning Name-finder
Daniel M. Bikel, Scott Miller, Richard Schwartz, Ralph Weischedel
A Fully Statistical Approach to Natural Language Interfaces
Scott Miller, David Stallard, Robert Bobrow, Richard Schwartz
Named Entity Extraction from Noisy Input: Speech and OCR
David Miller, Sean Boisen, Richard Schwartz, Rebecca Stone, Ralph Weischedel
Dunne, Michael W., Khurana, Chandra, Mohs, Adriano Arguedas, Rodriguez, Adib, Arrieta, Antonio, McLinn, Samuel, ...
Children with acute otitis media underwent tympanocentesis and were given a single dose of 30 mg of azithromycin/kg of body weight. At day 28, the overall clinical cure rate was 206 of 242 (85%)....
Dunne, Michael W., Khurana, Chandra, Mohs, Adriano Arguedas, Rodriguez, Adib, Arrieta, Antonio, McLinn, Samuel, ...
Children with acute otitis media underwent tympanocentesis and were given a single dose of 30 mg of azithromycin/kg of body weight. At day 28, the overall clinical cure rate was 206 of 242 (85%)....