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...
Online Large-Margin Training of Syntactic and Structural Translation Features (2009)
David Chiang, Yuval Marton, Philip Resnik
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimize. Building on the...
Using Paraphrases for Parameter Tuning in Statistical Machine Translation (2009)
Nitin Madnani, Necip Fazil Ayan, Philip Resnik, Bonnie J. Dorr
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...
Soft Syntactic Constraints for Hierarchical Phrased-Based Translation (2009)
In adding syntax to statistical MT, there is a tradeoff between taking advantage of linguistic analysis, versus allowing the model to exploit linguistically unmotivated mappings learned from parallel...
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...
TOR, TORMD: Distributional Profiles of Concepts for Unsupervised Word Sense Disambiguation (2009)
Saif Mohammad, Graeme Hirst, Philip Resnik
Words in the context of a target word have long been used as features by supervised word-sense classifiers. Mohammad and Hirst (2006a) proposed a way to determine the strength of association between...
Exploring Cross-Language Communication for Children via a Word Guessing Game (2009)
Evan Golub, Allison Druin, Anita Komlodi, Philip Resnik, Jenny Preece, Jerry Fails, ...
Techniques and tools exist to allow children to create and share stories. However, challenges can arise when attempting to share stories across languages and cultures. In this paper we explore a...
Nitin Madnani, Necip Fazil Ayan, Philip Resnik, Bonnie J. Dorr
• Future Work ref1 ref2 refn
Advisor Prof, Philip Resnik, Advisor Prof, Kemal Oflazer
Natural language processing; in particular statistical modeling and methods, resource acquisition and transfer using parallel corpora, machine translation. Information retrieval.
A Generative Probabilistic OCR Model (2008)
In this paper, we present a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process from generation of the true word sequence to the noisy output of an...
Using Paraphrases for Parameter Tuning in Statistical Machine Translation (2008)
Nitin Madnani, Necip Fazil Ayan, Philip Resnik, Bonnie J. Dorr
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...
Clara Cabezas, Indrajit Bhattacharya, Philip Resnik
For SENSEVAL-3, the University of Maryland (UMD) team focused on two primary issues: the portability of sense disambigation across languages, and the exploitation of real-world bilingual text as a...
ABSTRACT Title of Dissertation: WORD SENSE DISAMBIGUATION WITHIN A MULTILINGUAL FRAMEWORK (2008)
Mona Talat Diab, Doctor Of Philosophy, Dissertation Professor, Philip Resnik
Word Sense Disambiguation (WSD) is the process of resolving the meaning of a word unambiguously in a given natural language context. Within the scope of this thesis, it is the process of marking text...
Treebanks: Building and using parsed corpora (review) (2008)
Language - Volume 83, Number 4, December 2007
Genomic Entity Recognition at TREC (2008)
Dina Demner-fushman, Philip Resnik, Douglas W. Oard
The University of Maryland has been as active participant in TREC, NTCIR and CLEF for many years, both as participants and as a track coordinator. In this position paper we argue for genomic entity...
Caren Rosenblatt, Tapas Kanungo, Philip Resnik, Song Mao, Doe-wan Kim, Qigong Zheng
proves ideal for evaluating OCR techniques. As global online access to information becomes more common, the technology of multilingual optical character recognition (OCR) increases in importance as a...
Timothy Hawes, Jimmy Lin, Philip Resnik
This paper explores computational models of multi-party discourse, using transcripts from U.S. Supreme Court oral arguments. The turn-taking behavior of participants is treated as a supervised...
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Timothy Hawes, Jimmy Lin, Philip Resnik
This paper explores computational models of multi-party discourse, using transcripts from U.S. Supreme Court oral arguments. The turn-taking behavior of participants is treated as a supervised...
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Computational approaches to language processing arose during a time of bitter debate in the linguistics community that pitted the generative theory of grammar [Cho57] versus more quantitative and...
The Balancing, The Balancing Act, Judith L. Klavans, Philip Resnik, Diana Mccarthy, Diana Mccarthy
o approaches may have been viewed as contradictory by many researchers, yet the claim to the contrary does not seem very controversial at the current time. Exploration into the type of symbolic and...
Douglas W. Oard, Dina Demner-fushman, Samuel Gustman, William J. Byrne, Dagobert Soergel, Bonnie Dorr, ...
Abstract. The MALACH project seeks to help users find information in a vast multilingual collections of untranscribed oral history interviews. This paper introduces the goals of the project and...
1198 A Rule-Based Approach to Prepositional Phrase Attachment Disambiguation (2007)
brill~goldilocks.lcs.mit.edu I:n this paper, we describe a new corpus-based ap-proach to prepositional phrase attachment disam-biguation, and present results colnparing peffo> mange of this...
At 4:13 A.M. Eastern Standard Time on (2007)
Douglas W. Oard, David Doermann, Bonnie Dorr, Daqing He, Philip Resnik, Amy Weinberg, ...
Jean Vronis (editor, Technology Series, Edited Nancy Ide, Jean Vronis, Philip Resnik
One can't help but be fascinated by two sentences in parallel translation, the selfsame meaning diffused, distributed, diverging across alternative expressions. In his Le Ton beau de Marot: In...
Genomic Entity Recognition at TREC (2007)
Dina Demner-fushman, Philip Resnik, Douglas W. Oard
The University of Maryland has been as active participant in TREC, NTCIR and CLEF for many years, both as participants and as a track coordinator. In
Lexical Resource Integration Across the Syntax-Semantics Interface (2007)
Green, Rebecca, Pearl, Lisa, Door, Bonnie J., Resnik, Philip
This paper examines extending a database of English verbs, grouped into syntactico-semantic classes, with WordNet senses. Probabilistic associations between theta-grids and WordNet verb frames,...
Word-level Alignment for Multilingual Resource Acquisition (2007)
Lopez, Adam, Nossal, Michael, Hwa, Rebecca, Resnik, Philip
We present a simple, one-pass word alignment algorithm for parallel text. Our algorithm utilizes synchronous parsing and takes advantage of existing syntactic annotations. In our experiments the...
Cabezas, Clara, Dorr, Bonnie, Resnik, Philip
We describe here our construction of lexical resources, tool creation, building of an aligned parallel corpus, and an approach to automatic treebank creation, which we have been developing using...
Improved Cross-Language Retrieval using Backoff Translation (2007)
Resnik, Philip, Oard, Douglas, Levow, Gina
The limited coverage of available translation lexicons can pose a serious challenge in some cross-language information retrieval applications. We present two techniques for combining evidence from...
Rapidly Retargetable Interactive Translingual Retrieval (2007)
Levow, Gina-Anne, Oard, Douglas W., Resnik, Philip
This paper describes a system for rapidly retargetable interactive translingual retrieval. Basic functionality can be achieved for a new document language in a single day, and further improvements...
Bibliography Published Papers by Dragomir R. Radev References (2007)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, Bruce Croft, ...
[5] Suresh Bhavnani, Karen Drabenstott, and Dragomir Radev. Towards a unified framework of IR tasks and strategies. In 2001 ASIST Annual
Using WSD Techniques for Lexical Selection in Statistical Machine Translation (2006)
Cabezas, Clara, Resnik, Philip
In current state of the art statistical MT systems, word choice in the target language is governed implicitly by a combination of "phrase" selection and language modeling. In contrast, the state of...
Measuring Verb Similarity (2006)
The way we model semantic similarity is closely tied to our understanding of linguistic representations. We present several models of semantic similarity, based on differing rep- resentational...
Evaluating Translational Correspondence Using Annotation Projection (2006)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy, Kolak, Okan
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependence. Underlying these models is an assumption about the...
The Bible, Truth, and Multilingual OCR Evaluation (2006)
Kanungo, Tapas, Resnik, Philip
Multilingual OCR has emerged as an important information technology, thanks to the increasing need for cross-language information access. While many research groups and companies have developed OCR...
The Linguist’s Search Engine: an overview (2005)
The Linguist’s Search Engine (LSE) was designed to provide an intuitive, easy-touse interface that enables language researchers to seek linguistically interesting examples on the Web, based on...
The Linguist’s Search Engine: an overview (2005)
The Linguist’s Search Engine (LSE) was designed to provide an intuitive, easy-touse interface that enables language researchers to seek linguistically interesting examples on the Web, based on...
2005. A Paraphrase-Based Approach to Machine Translation Evaluation (2005)
Grazia Russo-lassner, Jimmy Lin, Philip Resnik
We propose a novel approach to automatic machine translation evaluation based on paraphrase identification. The quality of machine-generated output can be viewed as the extent to which the conveyed...
Philip Resnik, Aaron Elkiss, Ellen Lau, Heather Taylor
The whisper of “does that sound ok to you? ” is a familiar sound to most linguists: we often hear it in the audience when a presenter supports a theoretical point using a judgment of...
The hiero machine translation system: Extensions, evaluation, and analysis (2005)
David Chiang, Adam Lopez, Nitin Madnani, Christof Monz, Philip Resnik, Michael Subotin
Hierarchical organization is a well known property of language, and yet the notion of hierarchical structure has been largely absent from the best performing machine translation systems in recent...
Improved HMM Alignment Models for Languages with Scarce Resources (2005)
We introduce improvements to statistical word alignment based on the Hidden Markov Model. One improvement incorporates syntactic knowledge. Results on the workshop data show that alignment...
Philip Resnik, Aaron Elkiss, Ellen Lau, Heather Taylor
The whisper of “does that sound ok to you? ” is a familiar sound to most linguists: we often hear it in the audience when a presenter supports a theoretical point using a judgment of...
Bootstrapping Parsers via Syntactic Projection across Parallel Texts (2005)
Rebecca Hwa, Philip Resnik, Amy Weinberg, Clara Cabezas, Okan Kolak
Broad coverage, high quality parsers are available for only a handful of languages. A prerequisite for developing broad coverage parsers for more languages is the annotation of text with the desired...
The hiero machine translation system: Extensions, evaluation, and analysis (2005)
David Chiang, Adam Lopez, Nitin Madnani, Christof Monz, Philip Resnik, Michael Subotin
Hierarchical organization is a well known property of language, and yet the notion of hierarchical structure has been largely absent from the best performing machine translation systems in recent...
Pattern visualization for machine translation output (2005)
We describe a method for identifying systematic patterns in translation data using part-ofspeech tag sequences. We incorporate this analysis into a diagnostic tool intended for developers of machine...
Inducing Frame Semantic Verb Classes from WordNet and LDOCE (2004)
Rebecca Green, Bonnie J. Dorr, Philip Resnik
This paper presents SemFrame, a system that induces frame semantic verb classes from WordNet and LDOCE. Semantic frames are thought to have significant potential in resolving the paraphrase problem...
Exploiting Hidden Meanings Using Bilingual Text (2004)
The last decade has taught computational linguists that high performance on broad-coverage natural language processing tasks is best obtained using supervised learning techniques, which require...
THE LINGUIST'S SEARCH ENGINE: GETTING STARTED GUIDE (2003)
The World Wide Web can be viewed as a naturally occurring resource that embodies the rich and dynamic nature of language, a data repository of unparalleled size and diversity. However, current Web...
THE LINGUIST'S SEARCH ENGINE: GETTING STARTED GUIDE (2003)
The World Wide Web can be viewed as a naturally occurring resource that embodies the rich and dynamic nature of language, a data repository of unparalleled size and diversity. However, current Web...
Evaluating Translational Correspondence using Annotation Projection (2003)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy, Kolak, Okan
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependencies. Underlying these models is an assumption about the...
Evaluating Translational Correspondence using Annotation Projection (2003)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy, Kolak, Okan
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependencies. Underlying these models is an assumption about the...
Making miracles: Interactive translingual search for cebuano and hindi (2003)
Daqing He, Douglas W. Oard, Jianqiang Wang, Jun Luo, Dina Demner-fushman, Kareem Darwish, ...
Searching is inherently a user-centered process; people pose the questions for which machines seek answers, and ultimately people judge the degree to which retrieved documents meet their needs. Rapid...
Making miracles: Interactive translingual search for cebuano and hindi (2003)
Daqing He, Douglas W. Oard, Jianqiang Wang, Jun Luo, Kareem Darwish, Philip Resnik, ...
Searching is inherently a user-centered process; people pose the questions for which machines seek answers, and ultimately people judge the degree to which retrieved documents meet their needs. Rapid...
The web as a parallel corpus (2003)
Parallel corpora have become an essential resource for work in multilingual natural language processing. In this report, we describe our work using the STRAND system for mining parallel text on the...
A Generative Probabilistic OCR Model for NLP Applications (2003)
Okan Kolak, Willian Byrne, Philip Resnik
In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of...
The web as a parallel corpus (2003)
Parallel corpora have become an essential resource for work in multilingual natural language processing. In this article, we report on our work using the STRAND system for mining parallel text on the...
The Linguist’s Search Engine: Getting started guide (2003)
Philip Resnik, Philip Resnik, Aaron Elkiss, Aaron Elkiss
The World Wide Web can be viewed as a naturally occurring resource that embodies the rich and dynamic nature of language, a data repository of unparalleled size and diversity. However, current Web...
Making miracles: Interactive translingual search for cebuano and hindi (2003)
Daqing He, Douglas W. Oard, Jianqiang Wang, Jun Luo, Dina Demner-fushman, Kareem Darwish, ...
Searching is inherently a user-centered process; people pose the questions for which machines seek answers, and ultimately people judge the degree to which retrieved documents meet their needs. Rapid...
The Web as a Parallel Corpus (2002)
Resnik, Philip, Smith, Noah A.
Also UMIACS-TR-2002-61. Also LAMP-TR-089
The Web as a Parallel Corpus (2002)
Resnik, Philip, Smith, Noah A.
Also UMIACS-TR-2002-61. Also LAMP-TR-089
Breaking the Resource Bottleneck for Multilingual Parsing (2002)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy
We propose a framework that enables the acquisition of annotation-heavy resources such as syntactic dependency tree corpora for low-resource languages by importing linguistic annotations from...
Breaking the Resource Bottleneck for Multilingual Parsing (2002)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy
We propose a framework that enables the acquisition of annotation-heavy resources such as syntactic dependency tree corpora for low-resource languages by importing linguistic annotations from...
An Unsupervised Method for Word Sense Tagging Using Parallel Corpora (2002)
We present an unsupervised method for word sense disambiguation that exploits translation correspondences in parallel corpora. The technique takes advantage of the fact that crosslanguage...
Word-Level Alignment For Multilingual Resource Acquisition (2002)
Adam Lopez, Michael Nossal, Rebecca Hwa, Philip Resnik
We present a simple, one-pass word alignment algorithm for parallel text. Our algorithm utilizes synchronous parsing and takes advantage of existing syntactic annotations. In our experiments the...
Word-Level Alignment For Multilingual Resource Acquisition (2002)
Adam Lopez, Michael Nossal, Rebecca Hwa, Philip Resnik
We present a simple, one-pass word alignment algorithm for parallel text. Our algorithm utilizes synchronous parsing and takes advantage of existing syntactic annotations. In our experiments the...
Evaluating Translational Correspondence using Annotation Projection (2002)
Rebecca Hwa, Philip Resnik, Amy Weinberg, Okan Kolak
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependencies. Underlying these models is an assumption about the...
An Unsupervised Method for Word Sense Tagging Using Parallel Corpora (2002)
We present an unsupervised method for word sense disambiguation that exploits translation correspondences in parallel corpora. The technique takes advantage of the fact that crosslanguage...
Evaluating Translational Correspondence using Annotation Projection (2002)
Rebecca Hwa, Philip Resnik, Amy Weinberg, Okan Kolak
Recently, statistical machine translation models have begun to take advantage of higher level linguistic structures such as syntactic dependencies. Underlying these models is an assumption about the...
Breaking the Resource Bottleneck for Multilingual Parsing (2002)
Rebecca Hwa, Philip Resnik, Amy Weinberg
We propose a framework that enables the acquisition of annotation-heavy resources such as syntactic dependency tree corpora for low-resource languages by importing linguistic annotations from...
Breaking the Resource Bottleneck for Multilingual Parsing (2002)
Rebecca Hwa, Philip Resnik, Amy Weinberg
We propose a framework that enables the acquisition of annotation-heavy resources such as syntactic dependency tree corpora for low-resource languages by importing linguistic annotations from...
Lexical Resource Integration across the Syntax-Semantics Interface (2001)
Green, Rebecca, Pearl, Lisa, Dorr, Bonnie J., Resnik, Philip
This paper examines extending a database of English verbs, grouped into syntactico-semantic classes, with WordNet senses. Probabilistic associations between theta-grids and WordNet verb frames,...
Mapping Lexical Entries in a Verbs Database to WordNet Senses (2001)
Green, Rebecca, Pearl, Lisa, Dorr, Bonnie J., Resnik, Philip
This paper describes automatic techniques for mapping 9611 entries in a database of English verbs to WordNet senses. The verbs were initially grouped into 491 classes based on syntactic categories....
Lexical Resource Integration across the Syntax-Semantics Interface (2001)
Green, Rebecca, Pearl, Lisa, Dorr, Bonnie J., Resnik, Philip
This paper examines extending a database of English verbs, grouped into syntactico-semantic classes, with WordNet senses. Probabilistic associations between theta-grids and WordNet verb frames,...
Mapping Lexical Entries in a Verbs Database to WordNet Senses (2001)
Green, Rebecca, Pearl, Lisa, Dorr, Bonnie J., Resnik, Philip
This paper describes automatic techniques for mapping 9611 entries in a database of English verbs to WordNet senses. The verbs were initially grouped into 491 classes based on syntactic categories....
Improved cross-language retrieval using backoff translation (2001)
Philip Resnik, Douglas Oard, Gina Levow
The limited coverage of available translation lexicons can pose a serious challenge in some cross-language information retrieval applications. We present two techniques for combining evidence from...
Mapping lexical entries in verbs database to WordNet senses (2001)
Rebecca Green, Lisa Pearl, Bonnie J. Dorr, Philip Resnik
This paper describes automatic techniques for mapping 9611 entries in a database of English verbs to Word-Net senses. The verbs were initially grouped into 491 classes based on syntactic features....
Improved cross-language retrieval using backoff translation (2001)
The limited coverage of available translation lexicons can posea serious challenge in some cross-language information retrieval applications. We present two techniques for combining evidence from...
Mapping lexical entries in verbs database to WordNet senses (2001)
Rebecca Green, Lisa Pearl, Bonnie J. Dorr, Philip Resnik
This paper describes automatic techniques for mapping 9611 entries in a database of English verbs to WordNet senses. The verbs were initially grouped into 491 classes based on syntactic categories....
Clara Cabezas, Bonnie Dorr, Philip Resnik
Abstract: We describe here our construction of lexical resources, tool creation, building of an aligned parallel corpus, and an approach to automatic treebank creation that we have been developing...
Rapidly Retargetable Interactive Translingual Retrieval (2001)
Douglas W. Oard, Philip Resnik, Clara I. Cabezas
This paper describes a system for rapidly retargetable interactive translingual retrieval.
Tagger Evaluation Given Hierarchical Tag Sets (2000)
Melamed, I. Dan, Resnik, Philip
We present methods for evaluating human and automatic taggers that extend current practice in three ways. First, we show how to evaluate taggers that assign multiple tags to each test instance, even...
Measuring Verb Similarity (2000)
The way we model semantic similarity is closely tied to our understanding of linguistic representations. We present several models of semantic similarity, based on differing representational...
Measuring Verb Similarity (2000)
The way we model semantic similarity is closely tied to our understanding of linguistic representations. We present several models of semantic similarity, based on differing representational...
Measuring Verb Similarity (2000)
The way we model semantic similarity is closely tied to our understanding of linguistic representations. We present several models of semantic similarity, based on differing representational...
Mining the Web for Bilingual Text (1999)
STRAND (Resnik, 1998) is a language-independent system for automatic discovery of text in parallel translation on the World Wide Web. This paper extends the prelim-inary STRAND results by adding...
The Bible, truth, and multilingual OCR evaluation (1999)
Tapas Kanungo, Tapas Kanungo, Philip Resnik, Philip Resnik
Multilingual OCR has emerged as an important information technology, thanks to the increasing need for cross-language information access. While many research groups and companies have developed OCR...
Mining the Web for Bilingual Text (1999)
STRAND (Resnik, 1998) is a language-independent system for automatic discovery of text in parallel translation on the World Wide Web. This paper extends the preliminary STRAND results by adding...
This article presents a measure of semantic similarityinanis-a taxonomy based on the notion of shared information content. Experimental evaluation against a benchmark set of human similarity...
This article presents a measure of semantic similarity in an is-a taxonomy based on the notion of shared information content. Experimental evaluation against a benchmark set of human similarity...
The Bible, Truth, and Multilingual OCR Evaluation (1999)
Multilingual OCR has emerged as an important information technology, thanks to the increasing need for crosslanguage information access. While many research groups and companies have developed OCR...
This paper presents a measure of semantic similarity in an is-a taxonomy based on the notion of shared information content. Experimental evaluation against a benchmark set of human similarity...
Access to Multiple Underlying Systems in Janus. (1998)
The job of the back-end of any natural language interface is to translate a logical description of what the user wants (a request) into an efficient plan for fulfilling that request. Typically the...
Breaking the Resource Bottleneck for Multilingual Parsing (1998)
Hwa, Rebecca, Resnik, Philip, Weinberg, Amy
We propose a framework that enables the acquisition of annotation-heavy resources such as syntactic dependency tree corpora for low-resource languages by importing linguistic annotations from...
A Paraphrase-Based Approach to Machine Translation Evaluation (1998)
Russo-Lassner, Grazia, Lin, Jimmy, Resnik, Philip
We propose a novel approach to automatic machine translation evaluation based on paraphrase identification. The quality of machine-generated output can be viewed as the extent to which the conveyed...
Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual Text (1998)
Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic...
Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual Text (1998)
Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic...
Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual Text (1998)
Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic...
Parallel strands: A preliminary investigation into mining the web for bilingual text (1998)
Abstract. Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genreand domain-specificity, licensing restrictions, and the...
Resnik and Yarowsky (1997) made a set of observations about the state of the art in automatic word sense disambiguation and, motivated by those observations, offered several specific proposals...
Creating a Parallel Corpus from the "Book of 2000 Tongues" (1998)
Philip Resnik, Mari Broman Olsen, Mona Diab
This paper reports on a project to annotate biblical texts in order to create an aligned multilingual Bible corpus for linguistic research, particularly computational linguistics, including...
Creating a Parallel Corpus from the "Book of 2000 Tongues" (1998)
Philip Resnik, Mari Broman Olsen, Mona Diab
This paper reports on a project to annotate biblical texts in order to create an aligned multilingual Bible corpus for linguistic research, particularly computational linguistics, including...
The Bible, Truth, and Multilingual OCR Evaluation (1998)
Tapas Kanungo, Tapas Kanungo, Tapas Kanungo, Philip Resnik, Philip Resnik, Philip Resnik
this paper we propose to use the Bible as a dataset for comparing OCR accuracy across languages. Besides being available in a wide range of languages, Bible translations are closely parallel in...
Evaluating Multilingual Gisting of Web Pages (1997)
We describe a prototype system for multilingual gisting of Web pages, and present an evaluation methodology based on the notion of gisting as decision support. This evaluation paradigm is...
Semi-Automatic Acquisition of Domain-Specific Translation Lexicons (1997)
Resnik, Philip, Melamed, I. Dan
We investigate the utility of an algorithm for translation lexicon acquisition (SABLE), used previously on a very large corpus to acquire general translation lexicons, when that algorithm is applied...
Evaluating Multilingual Gisting of Web Pages (1997)
We describe a prototype system for multilingual gisting of Web pages, and present an evaluation methodology based on the notion of gisting as decision support. This evaluation paradigm is...
Evaluating Multilingual Gisting of Web Pages (1997)
We describe a prototype system for multilingual gisting of Web pages, and present an evaluation methodology based on the notion of gisting as decision support. This evaluation paradigm is...
A perspective on word sense disambiguation methods and their evaluation (1997)
In this position paper, we make several observations about the state of the art in automatic word sense disambiguation. Mo-tivated by these observations, we offer sev-eral specific proposals to the...
Semi-automatic acquisition of domain-specific translation lexicons (1997)
resnik~umiacs, umd. edu We investigate the utility of an algo-rithm for translation lexicon acquisition (SABLE), used previously on a very large corpus to acquire general translation lexi-cons, when...
Semi-Automatic Acquisition of Domain-Specific Translation Lexicons (1997)
We investigate the utility of an algorithm for translation lexicon acquisition (SABLE), used previously on a very large corpus to acquire general translation lexicons, when that algorithm is applied...
A Perspective on Word Sense Disambiguation Methods and Their Evaluation (1997)
In this position paper, we make several observations about the state of the art in automatic word sense disambiguation. Motivated by these observations, we offer several specific proposals to the...
A Language Identification Application Built on the Java Client/Server Platform (1997)
We describe an experimental system implemented using the Java(TM) programming language which demonstrates a variety of application-level tradeoffs available to distributed natural language processing...
A Language Identification Application Built on the Java Client/Server Platform (1997)
We describe an experimental system implemented using the Java(TM) programming language which demonstrates a variety of application-level tradeoffs available to distributed natural language processing...
Evaluating Multilingual Gisting of Web Pages (1997)
We describe a prototype system for multilingual gisting of Web pages, and present an evaluation methodology based on the notion of gisting as decision support. This evaluation paradigm is...
Implicit Object Constructions and the (In)transitivity Continuum (1997)
Mari Broman Olsen, Philip Resnik
this paper we show that the aspectual and selectional criteria for implicit objects are accounted for within the framework described by Hopper and Thompson's (1980; H&T) transitivity...
Evaluating Multilingual Gisting of Web Pages (1997)
We describe a prototype system for multilingual gisting of Web pages, and present an evaluation methodology based on the notion of gisting as decision support. This evaluation paradigm is...
Disambiguating Noun Groupings with Respect to WordNet Senses (1995)
Word groupings useful for language processing tasks are increasingly available, as thesauri appear on-line, and as distributional word clustering techniques improve. However, for many tasks, one is...
Using Information Content to Evaluate Semantic Similarity in a Taxonomy (1995)
This paper presents a new measure of semantic similarity in an IS-A taxonomy, based on the notion of information content. Experimental evaluation suggests that the measure performs encouragingly well...
Disambiguating Noun Groupings with Respect to WordNet senses (1995)
Word groupings useful for language processing tasks are increasingly available, as thesauri appear on-line, and as distributional word clustering techniques improve. However, for many tasks, one is...
Using Information Content to Evaluate Semantic Similarity in a Taxonomy (1995)
This paper presents a new measure of semantic similarity in an is-a taxonomy, based on the notion of information content. Experimental evaluation suggests that the measure performs encouragingly well...
A Rule-Based Approach To Prepositional Phrase Attachment Disambiguation (1994)
In this paper, we describe a new corpus-based approach to prepositional phrase attachment disambiguation, and present results comparing performance of this algorithm with other corpus-based...
Structural Ambiguity and Conceptual Relations (1993)
resnik @ linc.cis.upenn.edu Lexical co-occurrence statistics are becoming widely used in the syntactic analysis of unconstrained text. However, anal-yses based solely on lexical relationships suffer...
Left-Corner Parsing and Psychological Plausibility (1992)
It is well known that even extremely limited centerembedding causes people to have difficulty in comprehension, but that left- and right-branching constructions produce no such effect. If the...
A class-based approach to lexical discovery (1992)
In this paper I propose a generalization of lexical association techniques that is intended to facilitate statistical discovery of facts involving word classes rather than individual words. Although...
In this paper, I argue for the use of a probabilistic form of tree-adjoining grammar (TAG) in statistical natural language processing. I first discuss two previ-ous statistical approaches--- one that...