2008
|
Burget, Lukas; Schwarz, Petr; Matejka, Pavel; Hannemann, Mirko; Rastrow, Ariya; White, Christopher; Khudanpur, Sanjeev ; Hermansky, Hynek ; Cernocky, Jan Combination Of Strongly And Weakly Constrained Recognizers For Reliable Detection Of OOVs Inproceedings International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008. Links | BibTeX @inproceedings{lukas-burget:08b,
title = {Combination Of Strongly And Weakly Constrained Recognizers For Reliable Detection Of OOVs},
author = {Lukas Burget and Petr Schwarz and Pavel Matejka and Mirko Hannemann and Ariya Rastrow and Christopher White and Khudanpur, Sanjeev and Hermansky, Hynek and Jan Cernocky},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4518551},
year = {2008},
date = {2008-01-01},
booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Thomas, Samuel; Ganapathy, Sriram ; Hermansky, Hynek Hilbert Envelope Based Features for Far-Field Speech Recognition Inproceedings MLMI, 2008. Links | BibTeX @inproceedings{samuel-thomas:08,
title = {Hilbert Envelope Based Features for Far-Field Speech Recognition},
author = {Samuel Thomas and Ganapathy, Sriram and Hermansky, Hynek},
url = {http://link.springer.com/chapter/10.1007%2F978-3-540-85853-9_11},
year = {2008},
date = {2008-01-01},
booktitle = {MLMI},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Nirenburg, Sergei; McShane, Marjorie; Beale, Stephen Resolving paraphrases to support modeling language perception in an intelligent agent Inproceedings Semantics in Text Processing (STEP), pp. 179–192, Association for Computational Linguistics, Morristown, NJ, USA, 2008. Links | BibTeX @inproceedings{1626496,
title = {Resolving paraphrases to support modeling language perception in an intelligent agent},
author = {Sergei Nirenburg and Marjorie McShane and Stephen Beale},
url = {https://aclweb.org/anthology/W/W08/W08-2215.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Semantics in Text Processing (STEP)},
pages = {179--192},
publisher = {Association for Computational Linguistics},
address = {Morristown, NJ, USA},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ganapathy, Sriram ; Motlicek, Petr; Hermansky, Hynek ; Garudadri, Harinath Temporal Masking For Bit-Rate Reduction In Audio Codec Based On Frequency Domain Linear Prediction Inproceedings International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008. Links | BibTeX @inproceedings{sriram-ganapathy:08,
title = {Temporal Masking For Bit-Rate Reduction In Audio Codec Based On Frequency Domain Linear Prediction},
author = {Ganapathy, Sriram and Petr Motlicek and Hermansky, Hynek and Harinath Garudadri},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4518726},
year = {2008},
date = {2008-01-01},
booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Pinto, Joel; Sivaram, G S V S; Hermansky, Hynek Reverse Correlation for Analyzing MLP Posterior Features in ASR Inproceedings 11th International Conference on Text, Speech and Dialogue (TSD), 2008. Links | BibTeX @inproceedings{joel-pinto:08a,
title = {Reverse Correlation for Analyzing MLP Posterior Features in ASR},
author = {Joel Pinto and G.S.V.S. Sivaram and Hermansky, Hynek},
url = {http://link.springer.com/chapter/10.1007%2F978-3-540-87391-4_60},
year = {2008},
date = {2008-01-01},
booktitle = {11th International Conference on Text, Speech and Dialogue (TSD)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Thomas, Samuel; Ganapathy, Sriram ; Hermansky, Hynek Hilbert Envelope Based Spectro-Temporal Features for Phoneme Recognition in Telephone Speech Inproceedings International Speech Communication Association (INTERSPEECH), 2008. Links | BibTeX @inproceedings{samuel-thomas:08b,
title = {Hilbert Envelope Based Spectro-Temporal Features for Phoneme Recognition in Telephone Speech},
author = {Samuel Thomas and Ganapathy, Sriram and Hermansky, Hynek},
url = {Hilbert Envelope Based Spectro-Temporal Features for Phoneme Recognition in Telephone Speech},
year = {2008},
date = {2008-01-01},
booktitle = {International Speech Communication Association (INTERSPEECH)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ganapathy, Sriram ; Motlicek, Petr; Hermansky, Hynek ; Garudadri, Harinath Autoregressive Modeling of Hilbert Envelopes for Wide-Band Audio Coding Inproceedings 124th Convention of Audioengineering Society, 2008. Links | BibTeX @inproceedings{sriram-ganapathy:08c,
title = {Autoregressive Modeling of Hilbert Envelopes for Wide-Band Audio Coding},
author = {Ganapathy, Sriram and Petr Motlicek and Hermansky, Hynek and Harinath Garudadri},
url = {http://www.aes.org/e-lib/browse.cfm?elib=14611},
year = {2008},
date = {2008-01-01},
booktitle = {124th Convention of Audioengineering Society},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ganapathy, Sriram ; Motlicek, Petr; Hermansky, Hynek ; Garudadri, Harinath Spectral Noise Shaping: Improvements in Speech/Audio Codec Based on Linear Prediction in Spectral Domain Inproceedings International Speech Communication Association (INTERSPEECH), 2008. Links | BibTeX @inproceedings{sriram-ganapathy:08d,
title = {Spectral Noise Shaping: Improvements in Speech/Audio Codec Based on Linear Prediction in Spectral Domain},
author = {Ganapathy, Sriram and Petr Motlicek and Hermansky, Hynek and Harinath Garudadri},
url = {http://www.isca-speech.org/archive/interspeech_2008/i08_0675.html},
year = {2008},
date = {2008-01-01},
booktitle = {International Speech Communication Association (INTERSPEECH)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Karakos, D; Khudanpur, S; Marchette, D; Papamarcou, A; Priebe, C On the Minimization of Concave Information Functionals for Unsupervised Classification via Decision Trees, Statistics and Probability Letters Journal Article pp. 975–984, 2008. BibTeX @article{karakos2008ontheminimization,
title = {On the Minimization of Concave Information Functionals for Unsupervised Classification via Decision Trees, Statistics and Probability Letters},
author = {D. Karakos and S. Khudanpur and D. Marchette and A. Papamarcou and C. Priebe},
year = {2008},
date = {2008-01-01},
pages = {975--984},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Mayfield, J; Dorr, B J; Finin, T; Oard, D W; Piatko, C D Knowledge base evaluation for semantic knowledge discovery Inproceedings NSF Sponsored Symposium Semantic Knowledge Discovery, Organization and Use, 2008. Abstract | Links | BibTeX @inproceedings{9prxi1or,
title = {Knowledge base evaluation for semantic knowledge discovery},
author = {J. Mayfield and B.J. Dorr and T. Finin and D.W. Oard and C.D. Piatko},
url = {http://ebiquity.umbc.edu/_file_directory_/papers/429.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {NSF Sponsored Symposium Semantic Knowledge Discovery, Organization and Use},
abstract = {Semantic knowledge discovery has traditionally been evaluated at the
text level. For example, evaluations such as MUC [MUC-7] and ACE
[ACE 2008] evaluate the information extraction of particular types
of semantic roles and relations primarily at the mention level. We
suggest that evaluating at the level of a knowledge base (KB) extracted
from the text has significant advantages over evaluation at the text
level. By knowledge base, we mean the combination of a database,
a descriptive schema for the contents of the database, a collection
of background knowledge, and an inference capability.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Semantic knowledge discovery has traditionally been evaluated at the
text level. For example, evaluations such as MUC [MUC-7] and ACE
[ACE 2008] evaluate the information extraction of particular types
of semantic roles and relations primarily at the mention level. We
suggest that evaluating at the level of a knowledge base (KB) extracted
from the text has significant advantages over evaluation at the text
level. By knowledge base, we mean the combination of a database,
a descriptive schema for the contents of the database, a collection
of background knowledge, and an inference capability. |
Parthasarathi, Sree; Motlicek, Petr; Hermansky, Hynek Exploiting contextual information for speech/non-speech detection Inproceedings 11th International Conference on Text, Speech and Dialogue (TSD), 2008. Links | BibTeX @inproceedings{sree-hari-krishnan-parthasarathi:08,
title = {Exploiting contextual information for speech/non-speech detection},
author = {Sree Parthasarathi and Petr Motlicek and Hermansky, Hynek},
url = {http://download.springer.com/static/pdf/385/chp%253A10.1007%252F978-3-540-87391-4_58.pdf?auth66=1398273321_04fdde1585b188d5c87bbfbd58d9ff2c&ext=.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {11th International Conference on Text, Speech and Dialogue (TSD)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sivaram, G S V S; Hermansky, Hynek Emulating Temporal Receptive Fields of Auditory Mid-brain Neurons for Automatic Speech Recognition Inproceedings 16th European Signal Processing Conference, 2008. Links | BibTeX @inproceedings{sivaram:08a,
title = {Emulating Temporal Receptive Fields of Auditory Mid-brain Neurons for Automatic Speech Recognition},
author = {G.S.V.S. Sivaram and Hermansky, Hynek},
url = {http://www.eurasip.org/Proceedings/Eusipco/Eusipco2008/papers/1569104358.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {16th European Signal Processing Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Dorr, Bonnie ; Mohammad, Saif; Hirst, Graeme Computing Word-Pair Antonymy Inproceedings Empirical Methods in Natural Language Processing (EMNLP), 2008. Abstract | Links | BibTeX @inproceedings{agzueykp,
title = {Computing Word-Pair Antonymy},
author = {Dorr, Bonnie and Saif Mohammad and Graeme Hirst},
url = {2011/09/2008emnlpmohammadantonymy.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
abstract = {Knowing the degree of antonymy between words has widespread applications
in natural language processing. Manually-created lexicons have limited
coverage and do not include most semantically contrasting word pairs.
We present a new automatic and empirical measure of antonymy that
combines corpus statistics with the structure of a published thesaurus.
The approach is evaluated on a set of closest-opposite questions,
obtaining a precision of over 80%. Along the way, we discuss what
humans consider antonymous and how antonymy manifests itself in utterances.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Knowing the degree of antonymy between words has widespread applications
in natural language processing. Manually-created lexicons have limited
coverage and do not include most semantically contrasting word pairs.
We present a new automatic and empirical measure of antonymy that
combines corpus statistics with the structure of a published thesaurus.
The approach is evaluated on a set of closest-opposite questions,
obtaining a precision of over 80%. Along the way, we discuss what
humans consider antonymous and how antonymy manifests itself in utterances. |
McNamee, Paul N-gram Tokenization for Indian Language Text Retrieval Inproceedings Working Notes of the Forum for Information Retrieval Evaluation, 2008. Links | BibTeX @inproceedings{ixvrijve,
title = {N-gram Tokenization for Indian Language Text Retrieval},
author = {McNamee, Paul},
url = {2011/09/2008firemcnameeindianlangs.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Working Notes of the Forum for Information Retrieval Evaluation},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sivaram, G S V S; Hermansky, Hynek Introducing Temporal Asymmetries in Feature Extraction for Automatic Speech Recognition Inproceedings International Speech Communication Association (INTERSPEECH), 2008. Links | BibTeX @inproceedings{sivaram:08b,
title = {Introducing Temporal Asymmetries in Feature Extraction for Automatic Speech Recognition},
author = {G.S.V.S. Sivaram and Hermansky, Hynek},
url = {http://www.isca-speech.org/archive/interspeech_2008/i08_0890.html},
year = {2008},
date = {2008-01-01},
booktitle = {International Speech Communication Association (INTERSPEECH)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Zaidan, Omar; Eisner, Jason ; Piatko, Christine Machine Learning with Annotator Rationales to Reduce Annotation Cost Inproceedings Workshop on Cost Sensitive Learning at NIPS, 2008. BibTeX @inproceedings{zaidan:08,
title = {Machine Learning with Annotator Rationales to Reduce Annotation Cost},
author = {Omar Zaidan and Eisner, Jason and Piatko, Christine},
year = {2008},
date = {2008-01-01},
booktitle = {Workshop on Cost Sensitive Learning at NIPS},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Ganapathy, Sriram ; Thomas, Samuel; Hermansky, Hynek Front-end for Far-Field Speech Recognition based on Frequency Domain Linear Prediction Inproceedings International Speech Communication Association (INTERSPEECH), 2008. BibTeX @inproceedings{sriram-ganapathy:08b,
title = {Front-end for Far-Field Speech Recognition based on Frequency Domain Linear Prediction},
author = {Ganapathy, Sriram and Samuel Thomas and Hermansky, Hynek},
year = {2008},
date = {2008-01-01},
booktitle = {International Speech Communication Association (INTERSPEECH)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Marchette, D; Priebe, Carey Predicting Unobserved Links in Incompletely Observed Networks Journal Article pp. 1373–1386, 2008. Links | BibTeX @article{marchette2008predicting,
title = {Predicting Unobserved Links in Incompletely Observed Networks},
author = {D. Marchette and Priebe, Carey},
url = {http://ac.els-cdn.com/S0167947307001193/1-s2.0-S0167947307001193-main.pdf?_tid=adfb89e0-c659-11e3-82c1-00000aacb35d&acdnat=1397757602_82b55b823de03e51151041df6fca0c29},
year = {2008},
date = {2008-01-01},
pages = {1373--1386},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
McNamee, Paul JHU ad hoc experiments at CLEF 2008 Inproceedings Evaluating Systems for Multilingual and Multimodal Information Access, pp. 170–177, 2008. Links | BibTeX @inproceedings{apgtjikz,
title = {JHU ad hoc experiments at CLEF 2008},
author = {McNamee, Paul},
url = {2011/09/mcnamee-clef2008.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Evaluating Systems for Multilingual and Multimodal Information Access},
pages = {170--177},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Thomas, Samuel; Ganapathy, Sriram ; Hermansky, Hynek Recognition Of Reverberant Speech Using Frequency Domain Linear Prediction Journal Article 2008. Links | BibTeX @article{samuel-thomas:08a,
title = {Recognition Of Reverberant Speech Using Frequency Domain Linear Prediction},
author = {Samuel Thomas and Ganapathy, Sriram and Hermansky, Hynek},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4666765},
year = {2008},
date = {2008-01-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Pinto, Joel; Bayya, Yegnanarayana; Hermansky, Hynek ; Magimai-Doss, Mathew Exploiting Contextual Information For Improved Phoneme Recognition Inproceedings International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008. Links | BibTeX @inproceedings{joel-pinto:08,
title = {Exploiting Contextual Information For Improved Phoneme Recognition},
author = {Joel Pinto and Yegnanarayana Bayya and Hermansky, Hynek and Mathew Magimai-Doss},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4518643},
year = {2008},
date = {2008-01-01},
booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Mohammad, S; Dorr, B; Hirst, G Towards Antonymy-Aware Natural Language Applications Inproceedings NSF Symposium on Semantic Knowledge Discovery: Organization and Use, 2008. Abstract | Links | BibTeX @inproceedings{02affhvd,
title = {Towards Antonymy-Aware Natural Language Applications},
author = {S. Mohammad and B. Dorr and G. Hirst},
url = {http://www.umiacs.umd.edu/~saif/WebDocs/antonymy-SKD.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {NSF Symposium on Semantic Knowledge Discovery: Organization and Use},
abstract = {Manually-created lexicons of antonym pairs have limited coverage and
do not include most semantically contrasting word pairs. Although
some approaches have been proposed before, it is only now that automatic
measures of word-pair antonymy are approaching a maturity in precision
and coverage (Turney 2008, Mohammad et al. 2008). However, the different
computational approaches capture different facets of this intuitive,
but complex, phenomenon. We describe several issues that must be
negotiated before arriving at a successful antonymy-aware natural
language system (outlined briefly in the next two paragraphs). Additionally,
we detail various tasks that can benefit by knowing which terms are
antonymous},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Manually-created lexicons of antonym pairs have limited coverage and
do not include most semantically contrasting word pairs. Although
some approaches have been proposed before, it is only now that automatic
measures of word-pair antonymy are approaching a maturity in precision
and coverage (Turney 2008, Mohammad et al. 2008). However, the different
computational approaches capture different facets of this intuitive,
but complex, phenomenon. We describe several issues that must be
negotiated before arriving at a successful antonymy-aware natural
language system (outlined briefly in the next two paragraphs). Additionally,
we detail various tasks that can benefit by knowing which terms are
antonymous |
Eisner, Jason ; Smith, David Dependency parsing by belief propagation Inproceedings Empirical Methods in Natural Language Processing (EMNLP), 2008. Abstract | Links | BibTeX @inproceedings{wzfa3nqb,
title = {Dependency parsing by belief propagation},
author = {Eisner, Jason and David Smith},
url = {2011/09/2008emlnpsmithparsing.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
abstract = {We formulate dependency parsing as a graphical model with the novel
ingredient of global constraints. We show how to apply loopy belief
propagation (BP), a simple and effective tool for approximate learning
and inference. As a parsing algorithm, BP is both asymptotically
and empirically efficient. Even with second-order features or latent
variables, which would make exact parsing considerably slower or
NP-hard, BP needs only O(n3) time with a small constant factor. Furthermore,
such features significantly improve parse accuracy over exact first-order
methods. Incorporating additional features would increase the runtime
additively rather than multiplicatively.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We formulate dependency parsing as a graphical model with the novel
ingredient of global constraints. We show how to apply loopy belief
propagation (BP), a simple and effective tool for approximate learning
and inference. As a parsing algorithm, BP is both asymptotically
and empirically efficient. Even with second-order features or latent
variables, which would make exact parsing considerably slower or
NP-hard, BP needs only O(n3) time with a small constant factor. Furthermore,
such features significantly improve parse accuracy over exact first-order
methods. Incorporating additional features would increase the runtime
additively rather than multiplicatively. |
Pinto, Joel; Szoke, Igor; Prasanna, S R M; Hermansky, Hynek Fast Approximate Spoken Term Detection from Sequence of Phonemes Inproceedings The 31st Annual International ACM SIGIR Conference, 2008. BibTeX @inproceedings{pinto-joel:08,
title = {Fast Approximate Spoken Term Detection from Sequence of Phonemes},
author = {Joel Pinto and Igor Szoke and S.R.M. Prasanna and Hermansky, Hynek},
year = {2008},
date = {2008-01-01},
booktitle = {The 31st Annual International ACM SIGIR Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Lee, N; Priebe, C; Miller, M; Ratnanather, J Validation of Alternating Kernel Mixture Method: Application to Tissue Segmentation of Cortical and Sub-cortical Structures Journal Article 2008. BibTeX @article{lee2008validation,
title = {Validation of Alternating Kernel Mixture Method: Application to Tissue Segmentation of Cortical and Sub-cortical Structures},
author = {N. Lee and C. Priebe and M. Miller and J. Ratnanather},
year = {2008},
date = {2008-01-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Dorr, Bonnie ; Farwell, David; Green, Rebecca; Habash, Nizar; Helmreich, Stephen; Hovy, Eduard; Levin, Lori; Miller, Keith; Mitamura, Teruko; Rambow, Owen; Reeder, Florence Interlingual Annotation of Parallel Text Corpora: A New Framework for Annotation and Evaluation Journal Article pp. 1–41, 2008. Abstract | Links | BibTeX @article{9gqmjy73,
title = {Interlingual Annotation of Parallel Text Corpora: A New Framework for Annotation and Evaluation},
author = {Dorr, Bonnie and David Farwell and Rebecca Green and Nizar Habash and Stephen Helmreich and Eduard Hovy and Lori Levin and Keith Miller and Teruko Mitamura and Owen Rambow and Florence Reeder},
url = {2011/09/nle2008oct.pdf},
year = {2008},
date = {2008-01-01},
pages = {1--41},
publisher = {NLE},
abstract = {This paper focuses on the next step in the creation of a system of
meaning representation and the development of semantically-annotated
parallel corpora, for use in applications such as machine translation,
question answering, text summarization, and information retrieval.
The work described below constitutes the first effort of any kind
to annotate multiple translations of foreign language text with interlingual
content.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper focuses on the next step in the creation of a system of
meaning representation and the development of semantically-annotated
parallel corpora, for use in applications such as machine translation,
question answering, text summarization, and information retrieval.
The work described below constitutes the first effort of any kind
to annotate multiple translations of foreign language text with interlingual
content. |
Burget, Lukas; Schwarz, Petr; Matejka, Pavel; Hannemann, Mirko; Rastrow, Ariya; White, Christopher; Khudanpur, Sanjeev ; Hermansky, Hynek ; Cernocky, Jan Combination Of Strongly And Weakly Constrained Recognizers For Reliable Detection Of Out-Of-Vocabulary Words (OOVs) Inproceedings International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008. BibTeX @inproceedings{lukas-burget:08,
title = {Combination Of Strongly And Weakly Constrained Recognizers For Reliable Detection Of Out-Of-Vocabulary Words (OOVs)},
author = {Lukas Burget and Petr Schwarz and Pavel Matejka and Mirko Hannemann and Ariya Rastrow and Christopher White and Khudanpur, Sanjeev and Hermansky, Hynek and Jan Cernocky},
year = {2008},
date = {2008-01-01},
booktitle = {International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Elsayed, T; Lin, J; Oard, D W Pairwise document similarity in large collections with MapReduce Conference Association for Computational Linguistics (ACL), 2008. Links | BibTeX @conference{elsayed2008pairwise,
title = {Pairwise document similarity in large collections with MapReduce},
author = {T. Elsayed and J. Lin and D.W. Oard},
url = {http://aclweb.org/anthology/P/P08/P08-2067.pdf},
year = {2008},
date = {2008-01-01},
booktitle = {Association for Computational Linguistics (ACL)},
pages = {265--268},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2007
|
McNamee, Paul ; Mayfield, James N-gram Morphemes for Retrieval Inproceedings Working Notes for the Cross Language Evaluation Forum (CLEF), 2007. Abstract | Links | BibTeX @inproceedings{g41s3wqo,
title = {N-gram Morphemes for Retrieval},
author = {McNamee, Paul and Mayfield, James},
url = {http://www.clef-campaign.org/2007/working_notes/mcnameeCLEF2007.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {Working Notes for the Cross Language Evaluation Forum (CLEF)},
abstract = {Stemming, an approximation to morphological analysis, is a commonly
used technique to improve performance in information retrieval systems.
In the MorphoChallenge 2007 evaluation we applied a simple zero-knowledge
technique that is based on frequency counts rather than machine learning.
Our method is based on substituting a single fixed-length substring
for each word that appears in documents or queries. We hope to discover
whether this method, which has been used in previous IR evaluations
with good effect, will be as effective for the information retrieval
task as the unsupervised methods used by other participants. It should
be emphasized that out submission was not a credible attempt to learn
morphology and thus is not expected to perform well in the morphology
induction task.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stemming, an approximation to morphological analysis, is a commonly
used technique to improve performance in information retrieval systems.
In the MorphoChallenge 2007 evaluation we applied a simple zero-knowledge
technique that is based on frequency counts rather than machine learning.
Our method is based on substituting a single fixed-length substring
for each word that appears in documents or queries. We hope to discover
whether this method, which has been used in previous IR evaluations
with good effect, will be as effective for the information retrieval
task as the unsupervised methods used by other participants. It should
be emphasized that out submission was not a credible attempt to learn
morphology and thus is not expected to perform well in the morphology
induction task. |
0000
|
Xu, Tan ; McNamee, Paul ; Oard, Doug HLTCOE at TREC 2013: Temporal Summarization 0000. Abstract | BibTeX @{b,
title = {HLTCOE at TREC 2013: Temporal Summarization},
author = {Xu, Tan and McNamee, Paul and Oard, Doug},
abstract = {Our team submitted runs for the first running
of the TREC Temporal Summarization
track. We focused on the Sequential Update
Summarization task. This task involves
simulating processing a temporally ordered
stream of over 1 billion documents to identify
sentences that are relevant to a specific
breaking news stories which contain new
and important content. In this paper, we describe
our approach and evaluation results.},
keywords = {},
pubstate = {published},
tppubtype = {}
}
Our team submitted runs for the first running
of the TREC Temporal Summarization
track. We focused on the Sequential Update
Summarization task. This task involves
simulating processing a temporally ordered
stream of over 1 billion documents to identify
sentences that are relevant to a specific
breaking news stories which contain new
and important content. In this paper, we describe
our approach and evaluation results. |
Irvine, Ann ; Langfus, Joshua; Callison-Burch, Chris The American Local News Corpus Inproceedings Proceedings of the Language Resources and Evaluation Conference (LREC), 0000. Links | BibTeX @inproceedings{irvine-etal-lrec14,
title = {The American Local News Corpus},
author = {Irvine, Ann and Joshua Langfus and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/alnc_lrec14.pdf},
booktitle = {Proceedings of the Language Resources and Evaluation Conference (LREC)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Irvine, Ann ; Callison-Burch, Chris Hallucinating Phrase Translations for Low Resource MT Inproceedings Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 0000. Links | BibTeX @inproceedings{irvine-callisonburch-conll14,
title = {Hallucinating Phrase Translations for Low Resource MT},
author = {Irvine, Ann and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/irvineCCB_Hallucinating_CoNLL_14.pdf},
booktitle = {Proceedings of the Conference on Computational Natural Language Learning (CoNLL)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Irvine, Ann ; Callison-Burch, Chris Using Comparable Corpora to Adapt MT Models to New Domains Inproceedings Proceedings of the ACL Workshop on Statistical Machine Translation (WMT), 0000. Links | BibTeX @inproceedings{irvine-callisonburch-wmt14,
title = {Using Comparable Corpora to Adapt MT Models to New Domains},
author = {Irvine, Ann and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/irvineCCB_wmt14.pdf},
booktitle = {Proceedings of the ACL Workshop on Statistical Machine Translation (WMT)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Hermansky, Hynek; Variani, Ehsan; Peddinti, Vijayaditya Mean Temporal Distance: Predicting ASR Error from Temporal Properties of Speech 0000. Abstract | Links | BibTeX @{b,
title = {Mean Temporal Distance: Predicting ASR Error from Temporal Properties of Speech},
author = {Hynek Hermansky and Ehsan Variani and Vijayaditya Peddinti},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6639105&queryText%3DMean+Temporal+Distance%3A+Predicting+ASR+Error+from+Temporal+Properties+of+Speech},
pages = {7423 - 7426},
publisher = {IEEE},
address = {Vancouver, BC},
abstract = {Extending previous work on prediction of phoneme recognition error from unlabeled data that were corrupted by unpredictable factors, the current work investigates a simple but effective method of estimating ASR performance by computing a function M(Δt), which represents the mean distance between speech feature vectors evaluated over certain finite time interval, determined as a function of temporal distance Δt between the vectors. It is shown that M(Δt) is a function of signal-to-noise ratio of speech signal. Comparing M(Δt) curves, derived on data used for training of the classifier, and on test utterances, allows for predicting error on the test data. Another interesting observation is that M(Δt) remains approximately constant, as temporal separation Δt exceeds certain critical interval (about 200 ms), indicating the extent of coarticulation in speech sounds.},
keywords = {},
pubstate = {published},
tppubtype = {}
}
Extending previous work on prediction of phoneme recognition error from unlabeled data that were corrupted by unpredictable factors, the current work investigates a simple but effective method of estimating ASR performance by computing a function M(Δt), which represents the mean distance between speech feature vectors evaluated over certain finite time interval, determined as a function of temporal distance Δt between the vectors. It is shown that M(Δt) is a function of signal-to-noise ratio of speech signal. Comparing M(Δt) curves, derived on data used for training of the classifier, and on test utterances, allows for predicting error on the test data. Another interesting observation is that M(Δt) remains approximately constant, as temporal separation Δt exceeds certain critical interval (about 200 ms), indicating the extent of coarticulation in speech sounds. |
