Machine Translation System Combination with Flexible Word Ordering (2009)
Kenneth Heafield, Greg Hanneman, Alon Lavie
We describe a synthetic method for combining machine translations produced by different systems given the same input. One-best outputs are explicitly aligned to remove duplicate words. Hypotheses...
An Improved Statistical Transfer System for French–English Machine Translation (2009)
Greg Hanneman, Vamshi Ambati, Jonathan H. Clark, Alok Parlikar, Alon Lavie
This paper presents the Carnegie Mellon University statistical transfer MT system submitted to the 2009 WMT shared task in French-to-English translation. We describe a syntax-based approach that...
This paper describes our submissions to the machine translation evaluation shared task in ACL WMT-08. Our primary submission is the Meteor metric tuned for optimizing correlation with human rankings...
Stat-XFER: A General Search-based Syntax-driven Framework for Machine Translation (2009)
Abstract. The CMU Statistical Transfer Framework (Stat-XFER) is a general framework for developing search-based syntax-driven machine translation (MT) systems. The framework consists of an underlying...
Statistical Transfer Systems for French–English and German–English Machine Translation (2009)
Greg Hanneman, Edmund Huber, Abhaya Agarwal, Vamshi Ambati, Alok Parlikar, Erik Peterson, ...
We apply the Stat-XFER statistical transfer machine translation framework to the task of translating from French and German into English. We introduce statistical methods within our framework that...
ParaMor and Morpho Challenge 2008 (2009)
Christian Monson, Jaime Carbonell, Alon Lavie, Lori Levin
ParaMor, our unsupervised morphology induction system performed well at Morpho Challenge 2008. When ParaMor's morphological analyses, which specialize at identifying inflectional morphology, are...
This paper describes our submissions to the machine translation evaluation shared task in ACL WMT-08. Our primary submission is the Meteor metric tuned for optimizing correlation with human rankings...
Christian Monson, Ariadna Font Llitjós, Vamshi Ambati, Lori Levin, Alon Lavie, Alison Alvarez, ...
Producing machine translation (MT) for the many minority languages in the world is a serious challenge. Minority languages typically have few resources for building MT systems. For many minor...
ParaMor: Finding Paradigms across Morphology (2009)
Christian Monson, Jaime Carbonell, Alon Lavie, Lori Levin
Our algorithm, ParaMor, fared well in Morpho Challenge 2007 (Kurimo et al., 2007), a peer operated competition pitting against one another algorithms designed to discover the morphological structure...
Occurrence Based Statistics in Machine Translation (2008)
As MT approaches demand longer context for better translation quality, the limitations of current language modeling techniques become explicit. The computational inability to model the likelihood of...
A Multi-Perspective Evaluation of the NESPOLE! Speech-to-Speech Translation System (2008)
Lavie, Alon, Metze, Florian, Cattoni, Roldano, Constantini, Erica
The NESPOLE! speech-to-speech translation system (2008)
Metze, Florian, McDonough, John, Soltau, Hagen, Langley, Chad, Lavie, Alon, Schultz, Tanja, ...
Speechalator: two-way speech-to-speech translation on a consumer PDA (2008)
Waibel, Alex, Badran, Ahmed, Black, Alan W., Frederking, Robert, Gates, Donna, Lavie, Alon, ...
Speechalator: Two-way Speech-to-Speech Translation in your Hand (2008)
Waibel, Alex, Badran, Ahmed, Black, Alan W., Frederking, Robert, Gates, Donna, Lavie, Alon, ...
BLANC 1: Learning Evaluation Metrics for MT (2008)
Lucian Vlad Lita, Monica Rogati, Alon Lavie
We introduce BLANC, a family of dynamic, trainable evaluation metrics for machine translation. Flexible, parametrized models can be learned from past data and automatically optimized to correlate...
System Description JANUS Multi-lingual Translation of Spontaneous Speech in a Limited Domain (2008)
Alon Lavie, Lori Levin, Alex Waibel, Donna Gates, Marsal Gavalda, Laura Mayfield
ParaMor: Minimally Supervised Induction of Paradigm Structure and Morphological Analysis (2008)
Christian Monson, Jaime Carbonell, Alon Lavie, Lori Levin
Paradigms provide an inherent organizational structure to natural language morphology. ParaMor, our minimally supervised morphology induction algorithm, retrusses the word forms of raw text corpora...
ParaMor: Finding Paradigms across Morphology (2008)
Christian Monson, Jaime Carbonell, Alon Lavie, Lori Levin
Our algorithm, ParaMor, fared well in Morpho Challenge 2007 (Kurimo et al., 2007), a peer operated competition pitting against one another algorithms designed to discover the morphological structure...
Introduction: The Need for Speech-to-Speech Translation (2008)
Jaime Carbonell, Alon Lavie, Lori Levin, Alan Black
Humanitarian aid missions, whether emergency famine relief, establishment of medical clinics, or missions in conjunction with peace-keeping operations, require on-demand communication with the...
Experiments with a Noun-Phrase driven Statistical Machine Translation System (2008)
Sanjika Hewavitharana, Alon Lavie, Stephan Vogel
This paper presents a noun phrase driven two-level statistical machine translation system. Noun phrases (NPs) are used as the unit of decomposition to build a two level hierarchy of phrases. English...
Pre-processing of Bilingual Corpora for Mandarin-English EBMT (2008)
Ying Zhang, Ralf Brown, Robert Frederking, Alon Lavie
Pre-processing of bilingual corpora plays an important role in Example-Based Machine Translation (EBMT) and Statistical-Based Machine Translation (SBMT). For our Mandarin-English EBMT system,...
Building NLP Systems for Two Resource-Scarce Indigenous Languages: (2008)
Christian Monson, Ariadna Font Llitjós, Roberto Aranovich, Lori Levin, Ralf Brown, Eric Peterson, ...
By adopting a “first-things-first ” approach we overcome a number of challenges inherent in developing NLP Systems for resourcescarce languages. By first gathering the necessary corpora and...
Carolyn Penstein Rose, Alon Lavie
Large practical NLP applications require robust analysis components that can e#ectively handle input that is disfluent or extra-grammatical. The e#ectiveness and e#ciency of any robust parser are a...
Data Collection and Language Technologies for Mapudungun (2008)
Lori Levin Rodolfo, Jaime Carbonell, Ralf Brown, Alon Lavie, Eliseo Cañulef, Carolina Huenchullan
Mapudungun is spoken by over 900,000 people (Mapuche) in Chile and Argentina. Thanks to an active bilingual and multicultural education program, Mapuche children are now being taught to be literate...
Evaluating an Agglutinative Segmentation Model for ParaMor. The Tenth Meeting (2008)
Christian Monson, Alon Lavie, Jaime Carbonell, Lori Levin
This paper describes and evaluates a modification to the segmentation model used in the unsupervised morphology induction system, ParaMor. Our improved segmentation model permits multiple morpheme...
Alon Lavie, Dorcas Wallace, Taro Watanabe, Monika Woszczyna
For several years we have been conducting Accuracy Based Evaluations (ABE) of the JANUS speech-to-speech MT system (Gates et al., 1997) which measure quality and fidelity of translation. Recently we...
Published in "Proceedings of ICASSP-97" (2007)
Alon Lavie, Alex Waibel, Lori Levin, Michael Finke, Donna Gates, ...
This paper describes JANUS-III, our most recent version of the JANUS speech-to-speech translation system. We present an overview of the system and focus on how system design facilitates speech...
Alon Lavie, Alon Lavie, Lori Levin, Lori Levin, Alex Waibel, Alex Waibel, ...
Janus is a multi-lingual speech translation system currently operating in the domain of meeting scheduling. Translating spontaneous speech requires a high degree of robustness to overcome the...
Robust Parsing of Noise Contaminated and Extra-grammatical Input: A Grammar Focused Approach (2007)
This thesis tackles the problem of parsing noise contaminated input by identifying and parsing the maximal subset of the input string that is found to be grammatical. I develop a parser that is based...
The GLR * Parser The GLR Parsing Algorithm The Generalized LR Parser, developed by Tomita (2007)
GLR * is a recently developed robust version of the Generalized LR Parser [Tomita, 1986], that can parse almost any input sentence by ignoring unrecognizable parts of the sentence. On a given input...
Pre-processing of Bilingual Corpora for Mandarin-English EBMT (2007)
Ying Zhang, Ralf Brown, Robert Frederking, Alon Lavie
Pre-processing of bilingual corpora plays an important role in Example-Based Machine Translation (EBMT) and Statistical-Based Machine Translation (SBMT). For our Mandarin-English EBMT system,...
Puming Zhan, Klaus Ries, Marsal Gavalda, Donna Gates, Alon Lavie, Alex Waibel
JANUS-II is a research system for investigating various issues in speech-to-speech translations and has been implemented for speech-to-speech translations on many languages [1]. In this paper, we...
Robust Analysis Of Spoken Input Combining Statistical And (2007)
Roldano Cattoni, Marcello Federico, Alon Lavie
The work presented in this paper concerns the analysis of automatic transcription of spoken input into an interlingua formalism for a speech-to-speech machine translation system. This process is...
Benjamin Han, Alon Lavie, A Toy Grammar
# This paper describes UKernel version 1.91.
Alon Lavie, Florian Metze, Fabio Pianesi
This paper describes how we tackled these issues and evaluates their e#ect on system performance and usability. We focus on three main issues: (1) a study on the usage and utility of multi-modality...
Expanding the domain of a multi-lingual speech-to-speech translation system. (2007)
Lavie, Alon, Levin, Lori, Zhan, Puming, Taboada, Maite, Gates, Donna, Lapata, Mirella, ...
Janus III: speech-to-speech translation in multiple languages. (2007)
Lavie, Alon, Waibel, Alex, Levin, Lori, Finke, Michael, Gates, Donna, Gavalda, Marsal, ...
Multi-lingual translation of spontaneously spoken language in a limited domain. (2007)
Lavie, Alon, Gates, Donna, Gavalda, Marsal, Mayfield, Laura, Waibel, Alex, Levin, Lori
Dialogue processing in a conversational speech translation system. (2007)
Lavie, Alon, Levin, Lori, Qu, Yan, Waibel, Alex, Gates, Donna, Gavalda, Marsal, ...
Translation of conversational speech with Janus-II. (2007)
Lavie, Alon, Waibel, Alex, Levin, Lori, Gates, Donna, Gavalda, Marsal, Zeppenfeld, Torsten, ...
Janus II: towards spontaneous Spanish speech recognition. (2007)
Zhan, Puming, Ries, Klaus, Gavalda, Marsal, Gates, Donna, Lavie, Alon, Waibel, Alex
End-to-end evaluation in JANUS: a speech-to-speech translation system. (2007)
Gates, Donna, Lavie, Alon, Levin, Lori, Waibel, Alex, Gavalda, Marsal, Mayfield, Laura, ...
Cross Lingual and Semantic Retrieval for Cultural Heritage Appreciation (2007)
Szpektor, Idan, Dagan, Ido, Lavie, Alon, Shacham, Danny, Winter, Shuly
We describe a system which enhances the experience of museum visits by providing users with language-technology-based information retrieval capabilities. The system consists of a cross-lingual search...
High-accuracy annotation and parsing of CHILDES transcripts (2007)
Corpora of child language are essential for psycholinguistic research. Linguistic annotation of the corpora provides researchers with better means for exploring the development of grammatical...
High-accuracy annotation and parsing of CHILDES transcripts (2007)
Corpora of child language are essential for psycholinguistic research. Linguistic annotation of the corpora provides researchers with better means for exploring the development of grammatical...
Improving a Transfer-Based MT System with Automatic Refinements (2007)
Ariadna Font Llitjós, Jaime Carbonell, Alon Lavie
In this paper, we describe an Automatic Rule Refiner that, given online post-editing information, traces errors back to problematic translation rules and proposes concrete fixes to such rules....
High-accuracy annotation and parsing of CHILDES transcripts (2007)
Corpora of child language are essential for psycholinguistic research. Linguistic annotation of the corpora provides researchers with better means for exploring the development of grammatical...
Apply several MT engines to each input in parallel Create a combined translation from the individual translations Goal is to combine strengths, and avoid weaknesses. Along all dimensions: domain...
Dimensions of MT Evaluation (2007)
– MT systems are becoming wide-spread, embedded in more complex systems • How well do they work in practice? • Are they reliable enough? – MT is a technology still in research stages • How...
Distributed S2S Translation over the (2007)
Alon Lavie, Lori Levin, Work Chad Langley, Kay Peterson, Kornel Laskowski
UJF-CLIPS, AETHRA, APT-Trentino Builds on successful collaboration within C-STAR Improved limited-domain speech translation Experiment with multimodality and with MEMT Showcase-1: Travel and Tourism...
Parser combination by reparsing (2006)
We present a novel parser combination scheme that works by reparsing input sentences once they have already been parsed by several different parsers. We apply this idea to dependency and constituent...
Multi-engine Machine Translation Guided by Explicit Word Matching (2005)
Shyamsundar Jayaraman, Alon Lavie
Abstract. We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to produce a synthetic...
A Framework for Interactive and Automatic Refinement of Transfer-based (2005)
Ariadna Font Llitjós, Jaime G Carbonell, Alon Lavie
Abstract. Most current Machine Translation (MT) systems do not improve with feedback from post-editors beyond the addition of corrected translations to parallel training data (for statistical and...
METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments (2005)
Satanjeev Banerjee, Alon Lavie
We describe METEOR, an automatic metric for machine translation evaluation that is based on a generalize concept of unigram match ing between the machine pro uce translation an h uman-pro uce...
A Classifier-Based Parser with Linear Run-Time Complexity (2005)
We present a classifier-based parser that produces constituent trees in linear time.
BLANC: Learning Evaluation Metrics for MT (2005)
Lucian Vlad Lita, Monica Rogati, Alon Lavie
We introduce BLANC, a family of dynamic, trainable evaluation metrics for machine translation. Flexible, parametrized models can be learned from past data and automatically optimized to correlate...
Automatic Measurement of Syntactic Development in Child Language (2005)
Kenji Sagae And, Kenji Sagae, Alon Lavie
To facilitate the use of syntactic information in the study of child language acquisition, a coding scheme for Grammatical Relations (GRs) in transcripts of parent-child dialogs has been proposed by...
Multi-Engine Machine Translation Guided by Explicit Word Matching (2005)
Shyamsundar Jayaraman, Alon Lavie
We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to produce a synthetic combination...
Using Collocations to Assess MT Quality (2005)
Conventional metrics for Machine Translation evaluation have focused on using n-gram similarity between a reference translation and a system translation as an indication of the system quality. A...
METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments (2005)
Satanjeev Banerjee, Alon Lavie
We describe METEOR, an automatic metric for machine translation evaluation that is based on a generalize concept of unigram match ing between th e mach inepro uce translation an h uman-pro uce...
Multi-Engine Machine Translation Guided by Explicit Word Matching (2005)
Shyamsundar Jayaraman, Alon Lavie
We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to produce a synthetic combination...
Multilingual Named Entity Extraction and Translation from Text and Speech (2005)
Fei Huang, Alon Lavie, Tanja Schultz, Kevin Knight (usc/isi, C○ Fei Huang
I want to thank this age, the age of globalization, especially its posi-tive effect on China. When I was 10 years old, I could not imagine I would visit another country tens of thousands of miles...
A Framework for Interactive and Automatic Refinement of Transfer-based (2005)
Ariadna Font Llitjós, Jaime G Carbonell, Alon Lavie
Abstract. Most current Machine Translation (MT) systems do not improve with feedback from post-editors beyond the addition of corrected translations to parallel training data (for statistical and...
Blanc: Learning evaluation metrics for mt (2005)
Lucian Vlad Lita, Monica Rogati, Alon Lavie
We introduce BLANC, a family of dynamic, trainable evaluation metrics for machine translation. Flexible, parametrized models can be learned from past data and automatically optimized to correlate...
Automatic measurement of syntactic development in child language (2005)
To facilitate the use of syntactic information in the study of child language acquisition, a coding scheme for Grammatical Relations (GRs) in transcripts of parent-child dialogs has been proposed by...
Multi-engine Machine Translation Guided by Explicit Word Matching (2005)
Shyamsundar Jayaraman, Alon Lavie
We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to produce a synthetic combination...
Why Machine Translation (2005)
Alon Lavie, Jaime Carbonell, Lori Levin, Bob Frederking, Erik Peterson, Christian Monson, ...
• Automatic rule refinement
METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments (2005)
Meteor is an automatic metric for Machine Translation evaluation which has been demonstrated to have high levels of correlation with human judgments of translation quality, significantly...
Multi-Engine Machine Translation Guided by Explicit Word Matching (2005)
Shyamsundar Jayaraman, Alon Lavie
We describe a new approach for synthetically combining the output of several different Machine Translation (MT) engines operating on the same input. The goal is to produce a synthetic combination...
Unsupervised Induction of Natural Language Morphology Inflection Classes (2004)
Christian Monson, Alon Lavie, Jaime Carbonell, Lori Levin
We propose a novel language-independent framework for inducing a collection of morphological inflection classes from a monolingual corpus of full form words. Our approach involves two main stages. In...
Adding Syntactic Annotations to Transcripts of Parent-Child Dialogs (2004)
Kenji Sagae, Brian MacWhinney, Alon Lavie
We describe an annotation scheme for syntactic information in the CHILDES database (MacWhinney, 2000), which contains several megabytes of transcribed dialogs between parents and children. The...
Rapid Prototyping of a Transfer-based Hebrew-to-English Machine Translation System (2004)
Alon Lavie, Erik Peterson, Katharina Probst, Shuly Wintner, Yaniv Eytani
We describe the rapid development of a preliminary Hebrew-to-English Machine Translation system under a transfer-based framework specifically designed for rapid MT prototyping for languages with...
The Significance of Recall in Automatic Metrics for MT Evaluation (2004)
Alon Lavie, Kenji Sagae, Shyamsundar Jayaraman
Recent research has shown that a balanced harmonic mean (F1 measure) of unigram precision and recall outperforms the widely used BLEU and NIST metrics for Machine Translation evaluation in terms of...
Behavior Research Methods, Instruments, Computers (2004)
Explaining The Enigma, Kenji Sagae, Brian Macwhinney, Alon Lavie
this article, we describe our efforts in using state-of-the-art natural language analysis technolo113 Copyright 2004 Psychonomic Society, Inc. This work was supported by a grant from the National...
Data Collection and Analysis of Mapudungun Morphology for Spelling Correction (2004)
Christian Monson, Lori Levin, Rodolfo Vega, Ralf Brown, Ariadna Font Llitjos, Alon Lavie, ...
This paper describes part of a three year collaboration between Carnegie Mellon University's Language Technologies Institute, the Programa de Educacin Intercultural Bilinge of the Chilean...
A Structurally Diverse Minimal Corpus for Eliciting Structural Mappings between Languages (2004)
We describe an approach to creating a small but diverse corpus in English that can be used to elicit information about any target language. The focus of the corpus is on structural information. The...
A Framework for Resolution of Time in Natural (2004)
Language Benjamin Han, Benjamin Han, Alon Lavie
this article we set out to address these requirements by proposing a constraint-based framework for resolution of temporal information in NL. In particular, we focus our effort in putting forward a...
A Trainable Transfer-based Machine Translation Approach (2004)
For Languages With, Alon Lavie, Katharina Probst, Erik Peterson, Stephan Vogel, Lori Levin, ...
We describe a Machine Translation (MT) approach that is specifically designed to enable rapid development of MT for languages with limited amounts of online resources. Our approach assumes the...
Unsupervised Induction of Natural Language Morphology Inflection Classes (2004)
Christian Monson, Alon Lavie, Jaime Carbonell, Lori Levin
We propose a novel language-independent framework for inducing a collection of morphological inflection classes from a monolingual corpus of full form words. Our approach involves two main stages. In...
Trainable Transfer-based Machine Translation Approach for Languages with Limited Resources (2004)
Alon Lavie, Katharina Probst, Erik Peterson, Stephan Vogel, Lori Levin, Ariadna Font-llitjos, ...
Speechalator: Two-way Speech-to-Speech Translation in your Hand. (2003)
Waibel, Alex, Badran, Ahmed, Black, Alan W., Frederking, Robert, Gates, Donna, Lavie, Alon, ...
Speechalator: two-way speech-to-speech translation on a consumer PDA. (2003)
Waibel, Alex, Badran, Ahmed, Black, Alan W., Frederking, Robert, Gates, Donna, Lavie, Alon, ...
We investigate an aspect of the relationship between parsing and corpus-based methods in NLP that has received relatively little attention: coverage augmentation in rule-based parsers. In the...
Experiments with a Hindi-to-English Transfer-based MT System under a Miserly Data Scenario (2003)
Alon Lavie, Stephan Vogel, Lori Levin, Erik Peterson, Katharina Probst, Ariadna Font, ...
We describe an experiment designed to evaluate the capabilities of our trainable transfer-based (Xfer) machine translation approach, as applied to the task of Hindi-to-English translation, and...
We investigate an aspect of the relationship between parsing and corpus-based methods in NLP that has received relatively little attention: coverage augmentation in rule-based parsers. In the...
Speechalator: two-way speech-to-speech translation on a consumer PDA (2003)
Alex Waibel, Ahmed Badran, Alan W Black, Robert Frederking, Donna Gates, Alon Lavie, ...
This demonstration involves two-way automatic speechto-speech translation on a consumer off-the-shelf PDA. This work was done as part of the DARPA-funded Babylon project, investigating better...
Speechalator: two-way speech-to-speech translation on a consumer PDA (2003)
Alex Waibel, Ahmed Badran, Alan W Black, Robert Frederking, Alon Lavie, Lori Levin, ...
This paper describes a working two-way speech-to-speech translation system that runs in near real-time on a consumer handheld computer. It can translate from English to Arabic and Arabic to English...
Domain Specific Speech Acts for Spoken Language Translation (2003)
Lori Levin, Chad Langley, Alon Lavie, Donna Gates, Dorcas Wallace, Kay Peterson
We describe a coding scheme for machine translation of spoken taskoriented dialogue. The coding scheme covers two levels of speaker intention − domain independent speech acts and domain dependent...
Speechalator: Two-Way Speech-To-Speech Translation In Your Hand (2003)
Alex Waibel Ahmed, Ahmed Badran, Alan W Black, Robert Frederking, Donna Gates, Alon Lavie, ...
This demonstration involves two-way automatic speechto -speech translation on a consumer off-the-shelf PDA. This work was done as part of the DARPA-funded Babylon project, investigating better...
Domain Specific Speech Acts for Spoken Language Translation (2003)
Lori Levin Chad, Lori Levin, Chad Langley, Alon Lavie, Donna Gates, Dorcas Wallace, ...
We describe a coding scheme for machine translation of spoken task-oriented dialogue.
Parsing Domain Actions With Phrase-Level (2003)
Grammars And Memory-Based, Chad Langley, Alon Lavie
In this paper, we describe an approach to analysis for spoken language translation that combines phrase-level grammar-based parsing and automatic domain action classification. The job of the analyzer...
Speechalator: two-way speech-to-speech translation on a consumer PDA (2003)
Alex Waibel, Ahmed Badran, Alan W Black, Robert Frederking, Alon Lavie, Lori Levin, ...
This paper describes a working two-way speech-to-speech translation system that runs in near real-time on a consumer handheld computer. It can translate from English to Arabic and Arabic to English...
Experiments with a Hindi-to-English Transfer-based MT System under a Miserly Data Scenario (2003)
Alon Lavie, Stephan Vogel, Lori Levin, Erik Peterson, Katharina Probst, Ariadna Font, ...
We describe an experiment designed to evaluate the capabilities of our trainable transfer-based (Xfer) machine translation approach, as applied to the task of Hindi-to-English translation, and...
A Multi-Perspective Evaluation of the NESPOLE! Speech-to-Speech Translation System. (2002)
Lavie, Alon, Metze, Florian, Cattoni, Roldano, Constantini, Erica
The NESPOLE! speech-to-speech translation system. (2002)
Metze, Florian, McDonough, John, Soltau, Hagen, Langley, Chad, Lavie, Alon, Schultz, Tanja, ...
Lavie, Alon, Metze, Florian, Pianesi, Fabio, Burger, Susanne, Gates, Donna, Levin, Lori, ...
Over the past year, we have developed a fully functional showcase of the NESPOLE! system within the domain of travel and tourism, and have significantly improved system performance and usability...
The NESPOLE! Speech to Speech Translation System (2002)
Metze, Florian, Mcdonough, John, Soltau, Hagen, Waibel, Alex, Lavie, Alon, Burger, Susanne, ...
The main goal of NESPOLE! is to advance the state-of-the-art of speech-to-speech translation in realistic scenarios and involving naive users. The first showcase presented in this demonstration...
A Multi-Perspective evaluation of the NESPOLE! Speech-to-Speech Translation System (2002)
Lavie, Alon, Metze, Florian, Cattoni, Roldano, Costantini, Erica, Burger, Susanne, Gates, Donna, ...
Performance and usability of realworld speech-to-speech translation systems, like the one developed within the NESPOLE! project, are affected by several aspects that go beyong the pure translation...
Lavie, Alon, Metze, Florian, Pianesi, Fabio, Burger, Susanne, Gates, Donna, Levin, Lori, ...
Over the past year, we have developed a fully functional showcase of the NESPOLE! system within the domain of travel and tourism, and have significantly improved system performance and usability...
The NESPOLE! Speech to Speech Translation System (2002)
Metze, Florian, Mcdonough, John, Soltau, Hagen, Waibel, Alex, Lavie, Alon, Burger, Susanne, ...
The main goal of NESPOLE! is to advance the state-of-the-art of speech-to-speech translation in realistic scenarios and involving naive users. The first showcase presented in this demonstration...
A Multi-Perspective evaluation of the NESPOLE! Speech-to-Speech Translation System (2002)
Lavie, Alon, Metze, Florian, Cattoni, Roldano, Costantini, Erica, Burger, Susanne, Gates, Donna, ...
Performance and usability of realworld speech-to-speech translation systems, like the one developed within the NESPOLE! project, are affected by several aspects that go beyong the pure translation...
Spoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers (2002)
Chad Langley, Alon Lavie, Lori Levin, Dorcas Wallace, Donna Gates, Kay Peterson
In this paper, we describe a novel approach to spoken language analysis for translation, which uses a combination of grammar-based phrase-level parsing and automatic classification. The job of the...
Data Collection and Language Technologies for Mapudungun (2002)
Lori Levin, Rodolfo Vega, Jaime Carbonell, Ralf Brown, Alon Lavie, Eliseo Cañulef Y, ...
Mapudungun is spoken by over 900,000 people (Mapuche) in Chile and Argentina. Thanks to an active bilingual and multicultural education program, Mapuche children are now being taught to be literate...
Rapid Adaptive Development of Semantic Analysis Grammars (2002)
Alicia Tribble, Alon Lavie, Lori Levin
In this paper we describe a process for rapid development of semantic analysis grammars for Interlingual Machine Translation. The technique applies to existing systems and can be used to extend...
Balancing expressiveness and simplicity in an interlingua for task based dialogue (2002)
Lori Levin, Donna Gates, Dorcas Wallace, Kay Peterson, Alon Lavie
In this paper we compare two interlingua representations for speech translation. The basis of this paper is a distributional analysis of the C-star II and Nespole databases tagged with interlingua...
Spoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers (2002)
Chad Langley, Alon Lavie, Lori Levin, Dorcas Wallace, Donna Gates, Kay Peterson
In this paper, we describe a novel approach to spoken language analysis for translation, which uses a combination of grammar-based phrase-level parsing and automatic classification. The job of the...
A multi-perspective evaluation of the NESPOLE! speech-to-speech translation system (2002)
Performance and usability of realworld speech-to-speech translation systems, like the one developed within the Nespole! project, are affected by several aspects that go beyond the pure translation...
A multi-perspective evaluation of the NESPOLE! speech-to-speech translation system (2002)
Alon Lavie, Florian Metze, Roldano Cattoni
Performance and usability of realworld speech-to-speech translation systems, like the one developed within the NESPOnE! project, are affected by several aspects that go beyond the pure translation...
A multi-perspective evaluation of the NESPOLE! speech-to-speech translation system (2002)
Performance and usability of realworld speech-to-speech translation systems, like the one developed within the Nespole! project, are affected by several aspects that go beyond the pure translation...
Data Collection and Language Technologies for Mapudungun (2002)
Lori Levin, Rodolfo Vega, Jaime Carbonell, Ralf Brown, Alon Lavie, Eliseo Canulef, ...
Mapudungun is spoken by over 900,000 people (Mapuche) in Chile and Argentina. Thanks to an active bilingual and multicultural education program, Mapuche children are now being taught to be literate...
Balancing Expressiveness and Simplicity (2002)
In An Interlingua, Lori Levin, Donna Gates, Dorcas Wallace, Kay Peterson, Alon Lavie
In this paper we compare two interlingua representations for speech translation.
Domain portability in speech-to-speech translation (2001)
Alon Lavie, Lori Levin, Tanja Schultz, Chad Langley, Benjamin Han, Alicia Tribble
Speech-to-speech translation has made significant advances over the past decade, with several high-visibility projects (C-STAR, Verbmobil, the Spoken Language Translator, and others) significantly...
Katharina Probst, Ralf Brown, Jaime Carbonell, Alon Lavie, Lori Levin, Erik Peterson
NICE is a machine translation project for low-density languages. We are building a tool that will elicit a controlled corpus from a bilingual speaker who is not an expert in linguistics. The corpus...
Parsing the CHILDES database: Methodology and lessons learned (2001)
Kenji Sagae, Alon Lavie, Brian Macwhinney
This paper discusses the process of parsing adult utterances directed to a child, in an effort to produce a syntactically annotated corpus of the verbal input to a human language learner. In parsing...
Katharina Probst, Ralf Brown, Jaime Carbonell, Alon Lavie, Lori Levin, Erik Peterson
NICE is a machine translation project for low-density languages. We are building a tool that will elicit a controlled corpus from a bilingual speaker who is not an expert in linguistics. The corpus...
Increasing the coherence of spoken dialogue summaries by cross-speaker information linking (2001)
This paper addresses the question of how to increase local coherence in summaries of multiparty conversations. Due to the interactive nature of dialogues, local regions of coherence often stretch...
Alon Lavie, Alex Waibel, Fabio Pianesi, Gianni Lazzari, Paolo Coletti, Loredana Taddei, ...
NESPOLE!
Domain portability in speech-to-speech translation (2001)
Alon Lavie, Lori Levin, Tanja Schultz, Chad Langley, Benjamin Han, Alicia Tribble, ...
Speech-to-speech translation has made significant advancesover the past decade, with several high-visibility projects (C-STAR, Verbmobil, the Spoken Language Translator, and others) significantly
Domain portability in speech-to-speech translation (2001)
Alon Lavie, Lori Levin, Tanja Schultz, Chad Langley, Benjamin Han, Alicia Tribble
Speech-to-speech translation has made significant advances over the past decade, with several high-visibility projects (C-STAR, Verbmobil, the Spoken Language Translator, and others) significantly...
Design and Implementation of Controlled Elicitation for Machine Translation of (2001)
Katharina Probst, Ralf Brown, Jaime Carbonell, Alon Lavie, Lori Levin, ...
NICE is a machine translation project for low-density languages. We are building a tool that will elicit a controlled corpus from a bilingual speaker who is not an expert in linguistics. The corpus...
Architecture and Design Considerations in NESPOLE!: (2001)
Speech Translation System, Alon Lavie, Alex Waibel
this paper we describe the design considerations behind the architecture that we have developed for the NESPOLE! speech translation system in the scenario described above. In order to make the...
Architecture and Design Considerations in NESPOLE!: (2001)
Speech Translation System, Alon Lavie, Alex Waibel
this paper we describe the design considerations behind the architecture that we have developed for the NESPOLE! speech translation system in the scenario described above. In order to make the...
Domain portability in speech-to-speech translation (2001)
Alon Lavie, Lori Levin, Tanja Schultz, Chad Langley, Benjamin Han, Alicia Tribble
Speech-to-speech translation has made significant advances over the past decade, with several high-visibility projects (C-STAR, Verbmobil, the Spoken Language Translator, and others) significantly...
Optimal ambiguity packing in context-free parsers with interleaved unification (2000)
Alon Lavie, Carolyn Penstein Rose
Ambiguity packing is a well known technique for enhancing the efficiency of context-free parsers. However, in the case of unification-augmented context-free parsers where parsing is interleaved with...
Optimal ambiguity packing in context-free parsers with interleaved uni (2000)
Alon Lavie, Carolyn Penstein Ros'e
Ambiguity packing is a well known technique for enhancing the efficiency of context-free parsers. However, in the case of unification-augmented context-free parsers where parsing is interleaved with...
Shallow discourse genre annotation in callhome spanish (2000)
Klaus Ries, Lori Levin, Liza Valle, Alon Lavie, Alex Waibel
www.is.cs.cmu.edu friesjlsljalaviejahwgcs.cmu.edu
Shallow discourse genre annotation in CallHome Spanish (2000)
Klaus Ries Lori, Klaus Ries, Lori Levin, Liza Valle, Alon Lavie, Alex Waibel, ...
The classification of speech genre is not yet an established task in language technologies. However we believe that it is a task that will become fairly important as large amounts of audio (and...
The Algebraic Structure of Attributed Type Signatures (2000)
Gerald B. Penn, Alon Lavie, Arunas L. Liulevicius, William Morrison
Feature structures are related to frames in artificial intelligence and to record structures in many programming languages. They are widely used as a data structure for natural language processing...
Lessons Learned from a Task-Based Evaluation (2000)
Lori Levin, Boris Bartlog, Ariadna Font Llitjos, Donna Gates, Alon Lavie, ...
For several years we have been conducting Accuracy Based Evaluations (ABE) of the JANUS speech-to-speech MT system (Gates et al., 1997) which measure quality and fidelity of translation. Recently we...
Lessons Learned from a Task-Based Evaluation (2000)
Lori Levin, Boris Bartlog, Ariadna Font Llitjos, Donna Gates, Alon Lavie, ...
For several years we have been conducting Accuracy Based Evaluations (ABE) of the JANUS speech-to-speech MT system (Gates et al., 1997) which measure quality and fidelity of translation. Recently we...
Lessons Learned from a Task-Based Evaluation (2000)
Lori Levin, Boris Bartlog, Ariadna Font Llitjos, Donna Gates, Alon Lavie, ...
For several years we have been conducting Accuracy Based Evaluations (ABE) of the JANUS speech-to-speech MT system (Gates et al., 1997) which measure quality and fidelity of translation. Recently we...
Lesson Learned from a Task-Based Evaluation of Speech-to-Speech Machine Translation (2000)
Lori Levin, Boris Bartlog, Ariadna Font Llitjos, Donna Gates, Alon Lavie, Dorcas Wallace, ...
For several years we have been conducting Accuracy Based Evaluations (ABE) of the JANUS speech-to-speech MT system (Gates et al., 1997) which measure quality and fidelity of translation. Recently we...
Shallow discourse genre annotation in callhome spanish (2000)
Klaus Ries, Lori Levin, Liza Valle, Alon Lavie, Alex Waibel, Interactive System Labs
¤ ries¥lsl¥alavie¥ahw¦ www.is.cs.cmu.edu § cs.cmu.edu
Optimal Ambiguity Packing In Context-Free Parsers With Interleaved Unification (2000)
Alon Lavie, Carolyn Penstein Rose
Ambiguity packing is a well known technique for enhancing the e#ciency of context-free parsers. However, in the case of unification-augmented context-free parsers where parsing is interleaved with...
Evaluation of a Practical Interlingua for Task-Oriented Dialogue (2000)
Lori Levin, Donna Gates, Alon Lavie, Fabio Pianesi, Dorcas Wallace, Taro Watanabe, ...
IF (Interchange Format), the interlingua used by the C-STAR consortium, is a speech-act based interlingua for task-oriented dialogue. IF was designed as a practical interlingua that could strike a...
Tagging of speech acts and dialogue games in Spanish CallHome (1999)
Lori Levin, Klaus Ries, Ann Thym-gobbel, Alon Lavie
The Clarity project is devoted to automatic de-tection and classification of discourse structures in casual, non-task-oriented conversation using shal-low, corpus-based methods of analysis. For the...
The Janus-III Translation System: Speech-to-Speech Translation in Multiple Domains (1999)
Lori Levin, Alon Lavie, Monika Woszczyna, Donna Gates, Marsal Gavalda, Detlef Koll, ...
. The Janus-III translation system translates spoken languages in limited domains. The current research focus is on is expanding beyond tasks involving a single semantic domain. The system combines...
A Modular Approach to Spoken Language Translation for Large Domains (1998)
Monika Woszczyna Matthew, Alon Lavie, Lori Levin, Alex Waibel
. The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1) an interlingua approach that allows the efficient addition of new languages, 2) the use of...
Clarity: Inferring Discourse Structure From Speech (1998)
Michael Finke Maria, Maria Lapata, Alon Lavie, Lori Levin, Laura Mayfield Tomokiyo, Thomas Polzin, ...
The goal of the CLARITY project is to explore the use of discourse structure in the understanding of conversational speech. Within project CLARITY we aim to develop automatic classifiers for three...
Tagging of Speech Acts and Dialogue Games in Spanish Call Home (1998)
Lori Levin, Klaus Ries, Ann Thymé-Gobbel, Alon Lavie
The Clarity project is devoted to automatic detection and classification of discourse structures in casual, non-task-oriented conversation using shallow, corpus-based methods of analysis. For the...
A Domain Independent Approach for Efficiently Interpreting Extragrammatical Utterances (1998)
Carolyn Penstein Rose, Alon Lavie
In this paper we address the issue of efficiently and effectively handling the problem of extragrammaticality in a large-scale spontaneous spoken language system. We propose and argue in favor of...
A Modular Approach to Spoken Language Translation for Large Domains (1998)
Monika Woszczyna Matthew, Alon Lavie, Lori Levin, Alex Waibel
. The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1) an interlingua approach that allows the efficient addition of new languages, 2) the use of...
A Modular Approach to Spoken Language Translation for Large Domains (1998)
Monika Woszczyna, Matthew Broadhead, Donna Gates, Marsal Gavaldá, Alon Lavie, Lori Levin, ...
. The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1) an interlingua approach that allows the efficient addition of new languages, 2) the use of...
A Discourse Coding Scheme For Conversational Spanish (1998)
Lori Levin, Ann Thyme-gobbel, Alon Lavie, Klaus Ries, Klaus Zechner
This paper describes a 3-level manual discourse coding scheme that we have devised for manual tagging of the CallHome Spanish (CHS) and CallFriend Spanish (CFS) databases used in the CLARITY project....
Clarity: Inferring Discourse Structure from Speech (1998)
Michael Finke, Maria Lapata, Alon Lavie, Lori Levin, Laura Mayfield Tomokiyo, Thomas Polzin, ...
The goal of the CLARITY project is to explore the use of discourse structure in the understanding of conversational speech. Within project CLARITY we aim to develop automatic classifiers for three...
A Modular Approach to Spoken Language Translation for Large Domains (1998)
Monika Woszczyna, Alon Lavie, Lori Levin, Alex Waibel
. The MT engine of the Janus speech-to-speech translation system is designed around four main principles: 1) an interlingua approach that allows the efficient addition of new languages, 2) the use of...
Clarity: Inferring discourse structure from speech (1998)
Inferring Discourse Structure, Michael Finke, Maria Lapata, Alon Lavie, Lori Levin, Laura Mayfield Tomokiyo, ...
The goal of the CLARITY project is to explore the use of discourse structure in the understanding of conversational speech. Within project CLARITY we aim to develop automatic classifiers for three...
A Discourse Coding Scheme For Conversational Spanish (1998)
Lori Levin Ann, Ann Thymé-gobbel, Alon Lavie, Klaus Ries, Klaus Zechner
This paper describes a 3-level manual discourse coding scheme that we have devised for manual tagging of the CallHome Spanish (CHS) and CallFriend Spanish (CFS) databases used in the CLARITY project....
Clarity: Inferring discourse structure from speech (1998)
Michael Finke, Maria Lapata, Alon Lavie, Lori Levin, Laura Mayfield Tomokiyo, Thomas Polzin, ...
The goal of the CLARITY project is to explore the use of discourse structure in the understanding of conversational speech. Within project CLARITY we aim to develop automatic classifiers for three...
A discourse coding scheme for conversational spanish (1998)
Lori Levin, Ann Thymé-gobbel, Alon Lavie, Klaus Ries, Klaus Zechner
This paper describes a 3-level manual discourse coding scheme that we have devised for manual tagging of the CallHome Spanish (CHS) and CallFriend Spanish (CFS) databases used in the CLARITY project....
An Efficient Distribution of Labor in a Two Stage Robust Interpretation Process (1997)
Rose', Carolyn Penstien, Lavie, Alon
Although Minimum Distance Parsing (MDP) offers a theoretically attractive solution to the problem of extragrammaticality, it is often computationally infeasible in large scale practical applications....
Expanding the domain of a multi-lingual speech-to-speech translation system. (1997)
Lavie, Alon, Levin, Lori, Zhan, Puming, Taboada, Maite, Gates, Donna, Lapata, Mirella, ...
Janus III: speech-to-speech translation in multiple languages. (1997)
Lavie, Alon, Waibel, Alex, Levin, Lori, Finke, Michael, Gates, Donna, Gavalda, Marsal, ...
Multi-lingual translation of spontaneously spoken language in a limited domain. (1997)
Lavie, Alon, Gates, Donna, Gavalda, Marsal, Mayfield, Laura, Waibel, Alex, Levin, Lori
Dialogue processing in a conversational speech translation system. (1997)
Lavie, Alon, Levin, Lori, Qu, Yan, Waibel, Alex, Gates, Donna, Gavalda, Marsal, ...
Translation of conversational speech with Janus-II. (1997)
Lavie, Alon, Waibel, Alex, Levin, Lori, Gates, Donna, Gavalda, Marsal, Zeppenfeld, Torsten, ...
Janus II: towards spontaneous Spanish speech recognition. (1997)
Zhan, Puming, Ries, Klaus, Gavalda, Marsal, Gates, Donna, Lavie, Alon, Waibel, Alex
Expanding the Domain of a Multi-lingual Speech-to-Speech Translation System (1997)
Alon Lavie, Lori Levin, Puming Zhan, Maite Taboada, Donna Gates, Mirella Lapata, ...
JANUS is a multi-lingual speech-to-speech translation system, which has been designed to translate sponta-neous spoken language in a limited domain. In this paper, we describe our recent preliminary...
An Efficient Distribution of Labor in a Two Stage Robust Interpretation Process (1997)
Carolyn Penstein Ros'e, Alon Lavie
Although Minimum Distance Parsing (MDP) offers a theoretically attractive solution to the problem of extragrammaticality, it is often computationally infeasible in large scale practical applications....
JANUS - A System for Translation of Conversational Speech (1997)
Alex Waibel, Alon Lavie, Lori Levin
Janus is a large scale system for interactive spoken language translation that has been developed at Carnegie Mellon University and the University of Karlsruhe in the course of the last seven years....
Janus-III: Speech-To-Speech Translation In Multiple Languages (1997)
Alon Lavie, Alex Waibel, Lori Levin, Michael Finke, Donna Gates, Marsal Gavaldà, ...
This paper describes JANUS-III, our most recent version of the JANUS speech-to-speech translation system. We present an overview of the system and focus on how system design facilitates speech...
Expanding the Domain of a Multi-lingual Speech-to-Speech Translation System (1997)
Alon Lavie, Lori Levin, Puming Zhan, Maite Taboada, Donna Gates, Mirella Lapata, ...
JANUS is a multi-lingual speech-to-speech translation system, which has been designed to translate spontaneous spoken language in a limited domain. In this paper, we describe our recent preliminary...
Discourse Information for Disambiguation: The Phoenix Approach in JANUS (1997)
Maite Taboada, Lori Levin, Alex Waibel, Nancy Green, Alon Lavie
this paper, I will use the convention of assigning female gender to the speaker or initiator of the conversation, and male to the hearer
An Efficient Distribution of Labor in a Two Stage Robust Interpretation Process (1997)
Carolyn Penstein Rose, Alon Lavie
Although Minimum Distance Parsing (MDP) offers a theoretically attractive solution to the problem of extragrammaticality, it is often computationally infeasible in large scale practical applications....
GLR :--a robust grammar-focused parser for spontaneously spoken language /--Alon Lavie. (1996)
"May 1996."
End-to-end evaluation in JANUS: a speech-to-speech translation system. (1996)
Gates, Donna, Lavie, Alon, Levin, Lori, Waibel, Alex, Gavalda, Marsal, Mayfield, Laura, ...
Multi-lingual translation of spontaneously spoken language in a limited domain (1996)
Alon Lavie, Donna Gates, Marsal Gavaldh, Laura Mayfield, Alex Waibel, Lori Levin
JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous con-versation in a limited domain. In an attempt to...
Dialogue Processing in a Conversational Speech Translation System (1996)
Alon Lavie, Lori Levin, Yan Qu, Alex Waibel, Donna Gates, Marsal Gavaldà, ...
Attempts at discourse processing of spontaneously spoken dialogue face several difficulties: multiple hypotheses that result from the parser’s attempts to make sense of the output from the speech...
Janus-ii: Towards spontaneous spanish speech recognition (1996)
Puming Zhan, Klaus Ries, Marsal Gavalda, Donna Gates, Alon Lavie, Alex Waibel
JANUS-II is a research system for investigating various issues in speech-to-speech translations and has been implemented for speech-to-speech translations on many languages #1#. In this paper, we...
Translation of conversational speech with JANUS-II (1996)
Alon Lavie, Alex Waibel, Lori Levin, Donna Gates, Marsal Gavaldà, Puming Zhan, ...
In this paper we investigate the possibility of translating continuous spoken conversations in a cross-talk environment. This is a task known to be difficult for human translators due to several...
Minimizing Cumulative Error in Discourse Context (1996)
Yan Qu, Barbara Di Eugenio, Alon Lavie, Lori Levin, Carolyn P. Rose
Abstract. Cumulative error limits the usefulness of context in applications utilizing contextual information. It is especially a problem in spontaneous speech systems where unexpected input,...
Multi-lingual Translation of Spontaneously Spoken Language in a Limited Domain (1996)
Alon Lavie, Donna Gates, Marsal Gavaldà, Laura Mayfield, Alex Waibel, ...
JANUS is a multi-lingual speech-tospeech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In an attempt to...
End-to-end Evaluation in JANUS: a Speech-to-speech Translation System (1996)
Donna Gates, Alon Lavie, Lori Levin, Alex Waibel, Marsal Gavaldà, Laura Mayfield, ...
. JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneousconversation in a limited domain. In this paper we...
JANUS-II: Towards Spontaneous Spanish Speech Recognition (1996)
Puming Zhan, Klaus Ries, Marsal Gavalda, Donna Gates, Alon Lavie, Alex Waibel
JANUS-II is a research system for investigating various issues in speech-to-speech translations and has been implemented for speech-to-speech translations on many languages [1]. In this paper, we...
Translation of Conversational Speech with JANUS-II (1996)
Alon Lavie, Alex Waibel, Lori Levin, Donna Gates, Marsal Gavalda, Torsten Zeppenfeld, ...
In this paper we investigate the possibility of translating continuous spoken conversations in a cross-talk environment. This is a task known to be difficult for human translators due to several...
Minimizing Cumulative Error in Discourse Context (1996)
Yan Qu, Barbara Di Eugenio, Alon Lavie, Lori Levin, Carolyn P. Ros'e
. Cumulative error limits the usefulness of context in applications utilizing contextual information. It is especially a problem in spontaneous speech systems where unexpected input, out-of-domain...
End-to-end Evaluation in JANUS: a Speech-to-speech Translation System (1996)
Donna Gates, Alon Lavie, Lori Levin, Marsal Gavaldà, Alex Waibel, ...
. JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In this paper we...
JANUS-II: Towards Spontaneous Spanish Speech Recognition (1996)
Puming Zhan, Klaus Ries, Marsal Gavalda, Donna Gates, Alon Lavie, Alex Waibel
JANUS-II is a research system for investigating various issues in speech-to-speech translations and has been implemented for speech-to-speech translations on many languages [1]. In this paper, we...
Dialogue Processing in a Conversational Speech Translation System (1996)
Alon Lavie, Lori Levin, Yan Qu, Alex Waibel, Donna Gates, ...
Attempts at discourse processing of spontaneously spoken dialogue face several difficulties: multiple hypotheses that result from the parser's attempts to make sense of the output from the...
Minimizing Cumulative Error in Discourse Context (1996)
Yan Qu, Barbara Di Eugenio, Alon Lavie, Lori Levin, Carolyn P. Rose
. Cumulative error limits the usefulness of context in applications utilizing contextual information. It is especially a problem in spontaneous speech systems where unexpected input, out-of-domain...
Input Segmentation of Spontaneous Speech in JANUS: a Speech-to-speech Translation System (1996)
. JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In this paper we...
GLR* - A Robust Parser For Spontaneously Spoken Language (1996)
This paper describes GLR*, a parsing system based on Tomita's Generalized LR parsing algorithm, that was designed to be robust to two particular types of extra-grammaticality: noise in the...
GLR*: A Robust Grammar-Focused Parser for Spontaneously Spoken Language (1996)
The analysis of spoken language is widely considered to be a more challenging task than the analysis of written text. All of the difficulties of written language can generally be found in spoken...
GLR*: A Robust Grammar-Focused Parser for Spontaneously Spoken Language (1996)
Alon Lavie, Alex Waibel, Edward Gibson Mit
analysis of written text. All of the difficulties of written language can generally be found in spoken language as well. Parsing spontaneous speech must, however, also deal with problems such as...
In Proc. of ECAI-96 Wrkshp on Dial. Proc. of SL Sys. (1996)
Minimizing Cumulative Error, Yan Qu, Barbara Di Eugenio, Alon Lavie, Lori Levin, Carolyn P. Rosé
Cumulative error limits the usefulness of context in applications utilizing contextual information. It is especially a problem in spontaneous speech systems where unexpected input, out-of-domain...
Using Context in Machine Translation of Spoken Language (1995)
Lori Levin Oren, Oren Glickman, Yan Qu, Alon Lavie, Carolyn P. Ros'e
: We report on techniques for using discourse context to reduce ambiguity and improve translation accuracy in a multi-lingual (Spanish, German, and English) spoken language translation system. The...
Using Context in Machine Translation of Spoken Language (1995)
Lori Levin, Oren Glickman, Yan Qu, Alon Lavie, Carolyn P. Ros'e
: We report on techniques for using discourse context to reduce ambiguity and improve translation accuracy in a multi-lingual (Spanish, German, and English) spoken language translation system. The...
Using Context in Machine Translation of Spoken Language (1995)
Lori Levin, Oren Glickman, Yan Qu, Alon Lavie, Carolyn P. Ros'e
: We report on techniques for using discourse context to reduce ambiguity and improve translation accuracy in a multi-lingual (Spanish, German, and English) spoken language translation system. The...
An Integrated Heuristic Scheme for Partial Parse Evaluation (1994)
GLR* is a recently developed robust version of the Generalized LR Parser, that can parse almost ANY input sentence by ignoring unrecognizable parts of the sentence. On a given input sentence, the...
An Integrated Heuristic Scheme for Partial Parse Evaluation (1994)
GLR* is a recently developed robust version of the Generalized LR Parser [ Tomita, 1986 ] , that can parse almost any input sentence by ignoring unrecognizable parts of the sentence. On a given input...
Recognizing Substrings of LR(k) Languages in Linear Time (1994)
LR parsing techniques have long been studied as efficient and powerful methods for processing context free languages. A linear time algorithm for recognizing languages representable by LR(k) grammars...
Recognizing Substrings of LR(k) Languages in Linear Time (1994)
LR parsing techniques have long been studied as efficient and powerful methods for processing context free languages. A linear time algorithm for recognizing languages representable by LR(k) grammars...
Efficient Generalized LR Parsing of Word Lattices (1993)
A word lattice is an efficient representation of a large set of possible sentence candidates, of which only a few are grammaticaland thus parsable. Word lattices are a common output of some speech...
GLR* -- An Efficient Noise-skipping Parsing Algorithm For Context Free Grammars (1993)
Alon Lavie And, Alon Lavie, Masaru Tomita
This chapter describes GLR*, a parser that can parse any input sentence by ignoring unrecognizable parts of the sentence. Using an efficient algorithm, the parser is capable of finding and parsing a...
GLR* - An Efficient Noise-skipping Parsing Algorithm For Context Free Grammars (1993)
This paper describes GLR*, a parser that can parse any input sentence by ignoring unrecognizable parts of the sentence. In case the standard parsing procedure fails to parse an input sentence, the...
GLR* - An Efficient Noise-skipping Parsing Algorithm For Context Free Grammars (1993)
This chapter describes GLR*, a parser that can parse any input sentence by ignoring unrecognizable parts of the sentence. Using an efficient algorithm, the parser is capable of finding and parsing a...
Carolyn Penstein Rosé, Alon Lavie
Large practical NLP applications require robust analysis components that can effectively handle input that is disfluent or extra-grammatical. The effectiveness and efficiency of any robust parser are...