1997 — 2003 |
Goodrich, Michael (co-PI) [⬀] Goodrich, Michael (co-PI) [⬀] Yarowsky, David Kumar, Subodh (co-PI) [⬀] Taylor, Russell (co-PI) [⬀] Kosaraju, S. Rao Amir, Yair (co-PI) [⬀] Wolff, Lawrence [⬀] Tamassia, Roberto (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Cise Research Infrastructure: a Networked Computing Environment For the Manipulation and Visualization of Geometric Data @ Johns Hopkins University
CDA-9703080 Wolf, Lawrence Johns Hopkins University A Networked Computing Environment for the Manipulation and Visualization of Geometric Data This award is for the acquisition of an infrastructure for geometric computing providing a unified environment for five research laboratories in the Department of Computer Science at Johns Hopkins University (and one researcher at Brown University) having a large commonality in interests. This infrastructure will be used primarily as follows: The Center for Geometric Computation will be developing an interactive interface for geometric computation over the internet which will be used by the participating research laboratories and made available to other laboratories; the Computer Graphics Laboratory will focus on interactive visualization of large and complex geometric environments which also includes efficient utilization of network and distribute computing resources; the Computer Vision Laboratory is working on computational techniques for the visualization of the differential geometry of surfaces, visualizing and matching of signatures for Automatic Target Recognition, and real-time image understanding techniques for medical imaging; The Computer Integrated Surgery Laboratory will be conducting a number of projects in medical robotics including the development of techniques for minimally invasive surgery using navigation and guidance during neurosurgery and lung surgery, and, image and model registration techniques that use various 2D imaging modalities. The Natural Language Processing Laboratory will be studying document-space visualization in a high-dimensional space for information retrieval as well as clustering algorithms for high-dimensional word and document spaces.
|
1 |
2000 — 2006 |
Yarowsky, David |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Career: Resolving Lexical Ambiguities in Natural Language Processing @ Johns Hopkins University
This is the first year of funding of a 4 year, continuing award. One of the major roadblocks in the efficient and accurate communication between humans and machines is the resolution of the ambiguity inherent in natural languages. A major bottleneck in developing solutions is the severe shortage of training data that distinguishes word senses, and the high cost of inputting this information manually. A focus of this project is the development of unsupervised and minimally supervised algorithms for acquiring such skills without costly hand-tagged training data. Such methods will exploit the distribution properties observed in very large text corpora (over 10 billion words); the PI will also investigate richer representations of feature space, class models, smoothing methods and learning algorithms specialized for classification in very high-dimensional featurespaces. In addition to the problem of word-sense disambiguation, this project will explore shared solutions to a closely related set of lexical-ambiguity tasks including spelling correction, propername classification, capitalization restoration, accent and diacritic restoration for, diverse languages, vowel restoration in Hebrew and Arabic, speech synthesis on homographs, lexical choice in machine translation, and certain aspects of choosing among phonetically confusable candidates in speech recognition. These diverse problems are not normally recognized as being members of the same class, and this project seeks to exploit the synergies present by developing methods and training data on one member of the class and utilizing the methods and data on other. problems in the class. Thus this unified approach offers the potential for rapid parallel progress on key problems in human-computer interaction and information extraction.
|
1 |
2001 — 2008 |
Jelinek, Frederick [⬀] Khudanpur, Sanjeev (co-PI) [⬀] Yarowsky, David Byrne, William (co-PI) [⬀] Eisner, Jason |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Itr/Im+Pe+Sy: Summer Workshops On Human Language Technology: Integrating Research and Education @ Johns Hopkins University
We propose to organize yearly, intensive six-week research workshops at Johns Hopkins University, focusing on Language Engineering, including the mutually related areas of automatic speech recognition and synthesis, natural language processing, machine translation, information extraction and summarization. Applications of language engineering techniques to other domains such as language instruction or bioinformatics will also be appropriate workshop topics. These workshops will bring together teams of leading professionals and graduate and undergraduate students in a cooperative effort to advance the state of the art. The first goal of the proposed workshop series is to establish new research directions in Language Engineering. The second goal is to attract students to the field and to offer them an intensive hands-on mentored research education. The third is to engender extensive cross-fertilization between researchers distributed across industrial, academic and government institutions, forging intensive links in the 6-week summer period and offering a shared research environment for follow-on collaborative work. To ensure that the projects address current problems in the state of the art, each year an open call for workshop project proposals will be issued to researchers in the worldwide language engineering community. The proposals received will be evaluated competitively at planning meetings held each year. The meetings will draw together project proponents, government representatives, and experts from related fields to assess the viability and promise of the proposals and to identify three candidate projects for the summer workshop. Throughout this process of soliciting proposals and recruiting the personnel to carry them out, we will make a diligent attempt to include researchers from underrepresented institutions and communities.
|
1 |
2007 — 2012 |
Yarowsky, David Callison-Burch, Chris (co-PI) [⬀] |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Ri: Multi-Level Modeling of Language and Translation @ Johns Hopkins University
Previous approaches to statistical machine translation (SMT) have employed phrase-based models which represent phrases as sequences of fully-inflected words, and are otherwise devoid of linguistic detail. Such approaches are unable to generalize and essentially rely on memorizing the translations of words and phrases that are observed in training data.
This project aims to improve the quality of SMT through the introduction of more sophisticated models which represent phrases using multiple levels of information. This can include basic linguistic information such as part of speech, lemmas, and agreement information (case, number, person), as well as more sophisticated linguistic detail including semantic classes, argument structure, co-reference, phrase boundaries, and information propagated from syntactic heads.
By annotating all data with this information and extending models appropriately, there is the potential to learn much more from training than was possible under previous approaches. There is now the potential to learn translations of unseen words if other forms of the words occur; it is now possible to learn general facts about a language's word order; it is now feasible to use linguistic context to generate grammatical output. Such generalization has the potential to result in much higher quality translation, especially for languages that only have small amounts of training data. It therefore represents a significant advance over previous approaches to SMT.
Multi-level models have the potential for wide-ranging impact on all language technologies. Simultaneous modeling of different levels of representation is an extremely useful and natural way of describing language. This project is developing a general framework for the creation of multi-level probabilistic models of language and translation, and exploring its application to tasks beyond translation including generation, paraphrasing, and the automatic evaluation of natural language technologies.
|
1 |
2008 — 2009 |
Yarowsky, David |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Scientific Community On-Site Assessment Workshop For Robust Intelligence @ Johns Hopkins University
NSF currently sponsors an intensive summer research workshop series in human language technology and robust intelligence, organized and hosted by Johns Hopkins University. These workshops have exhibited a relatively unique model of interactive peer review, dynamic expert team generation, research acceleration via a condensed and unusually close collaboration environment and intensive student mentorship. A Scientific Community On-Site Assessment Workshop (OSAW) is being held on July 30-31, 2008, to review and and improve upon this model and investigate the potential for its extension to new scientific disciplines. During the OSAW, a team of expert research-community stakeholders observes current summer workshop processes, interviews participants, receives detailed briefs on prior peer-review, topic-selection and research team recruitment processes, and reaches findings and makes recommendations regarding these goals.
The OSAW workshop will contribute to the progress of science by: (1) improving the existing NSF-sponsored intensive summer workshop series that has already engaged over 300 international participants and lead to hundreds of peer-reviewed publications and major scientific innovations, (2) the insights and conclusions reached by the OSAW, especially with respect to the interactive peer-review and intensive mentorship processes employed by the summer workshop, have the potential to inform and provide ideas for other peer-review and mentorship processes, such as utilized by NSF and other organizations, (3) the recommendations of the OSAW will provide a roadmap for the extension of the intensive summer-workshop model to other fields, with potential for the accelerated scientific progress and unique collaboration framework already realized by this model in human-language-technology fields.
|
1 |
2010 — 2015 |
Hager, Gregory Jelinek, Frederick (co-PI) [⬀] Khudanpur, Sanjeev (co-PI) [⬀] Yarowsky, David Vidal, Rene |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Cross-Cutting Research Workshops On Intelligent Information Systems @ Johns Hopkins University
A series of annual research workshops on Intelligent Information Systems, centered on machine learning for speech, language and vision technologies, are being organized at Johns Hopkins University to bring together diverse ?dream teams? of leading professionals, graduate students, and undergraduates, in a truly cooperative, intensive, and substantive effort to advance the state of the science. The primary goals of the proposed workshop series are to develop machine learning principles applicable to a broad spectrum of intelligent systems, to attract students to the field and to prepare them for research by putting them to work on exciting problems alongside senior researchers in a highly collaborative environment. Creation of research infrastructure and lasting collaborations are secondary goals. An open call for workshop project proposals is being issued each year to researchers in the worldwide IIS community. Received proposals are competitively evaluated and cooperatively refined at interactive peer review meetings, where project proponents, government representatives, and experts from related fields meet to assess their scientific merit, viability and potential impact. The graduate students attending the workshop are familiar with the field and are selected in accordance with their demonstrated performance. The undergraduates are entering seniors who are new to the field and who have shown outstanding academic promise; they are selected through a national search. The participation of undergraduates in these research programs encourages talented young scholars to pursue graduate studies in IIS. By the end of this 3-year workshop series (beginning 2010), more than a hundred individuals will have conducted intensive collaborative research: about 30 academic and industry researchers, 20 researchers from government and national laboratories, 30 graduate students, and 20 undergraduates. Additional benefits of the workshops will be the collection or creation, and dissemination of valuable tools and data for IIS research, the establishment of fruitful and long-lasting collaborations, and the cross-fertilization of ideas among the participants.
|
1 |