| Rapidly Customizable Spoken Dialogue Systems |
28-Jan-2009 |
12 pages |
| Authors:
James Allen; FLORIDA INSTITUTE FOR HUMAN AND MACHINE COGNITION INC PENSACOLA FL
|
 | Building a robust spoken dialogue system for a new application, task, or domain currently requires considerable effort, including substantial efforts in data collection, building language models, grammar/parser development, building a custom dialogue manager, and developing the connection to the system's back-end systems (e.g., a database query or knowledge based system). This project developed key parts of a technology base upon which spoken dialogue systems can be rapidly constructed for new ... |
|
| Cross-Cultural Skills for Deployed Air Force Personnel: Defining Cross-Cultural Performance |
Jan-2009 |
|
| Authors:
Chaitra M Hardison; Carra S Sims; Farhana Ali; Andres Villamizar; Ben Mundell; Paul Howe; RAND CORP SANTA MONICA CA
|
 | Air Force leadership recognizes that the cross-cultural performance of Air Force members now plays a greater role in mission success than ever before. The Air Force therefore asked RAND to assist in developing a comprehensive program for preparing members of the Air Force in cross-cultural skills. RAND researchers responded by first creating a taxonomy covering all behaviors relevant to cross-cultural performance after a review of the literature and discussions with ... |
|
| Question Generation via Overgenerating Transformations and Ranking |
Jan 2009 |
16 pages |
| Authors:
Michael Heilman; Noah A Smith; CARNEGIE-MELLON UNIV PITTSBURGH PA LANGUAGE TECHNOLOGIES INST
|
| We describe an extensible approach to generating questions for the purpose of reading comprehension assessment and practice. Our framework for question generation composes general-purpose rules to transform declarative sentences into questions, is modular in that existing NLP tools can be leveraged, and includes a statistical component for scoring questions based on features of the input, output, and transformations performed. In an evaluation in which humans rated questions according to several ... |
|
| Natural Language Dialogue Architectures for Tactical Questioning Characters |
Dec-2008 |
9 pages |
| Authors:
Anton Leuski; David Traum; Bilyana Martinovski; Susan Robinson; Antonio Roque; Sudeep Gandhe; David DeVault; Jillian Gerten; UNIVERSITY OF SOUTHERN CALIFORNIA MARINA DEL REY CA INST FOR CREATIVE TECHNOLOGIES
|
| In this paper we contrast three architectures for natural language questioning characters. We contrast the relative costs and benefits of each approach in building characters for tactical questioning. The first architecture works purely at the textual, using cross-language information retrieval techniques to learn the best output for any input from a training set of linked questions and answers. The second architecture adds a global emotional model and computes a compliance ... |
|
| Studies in Intelligence. Volume 52, Number 4, December 2008 |
Dec 2008 |
59 pages |
| Authors:
Michael S Goodman; David Omand; Michael Bennett; Stephen C Mercado; John Ehrman; Hayden B Peake; CENTRAL INTELLIGENCE AGENCY WASHINGTON DC
|
| This issue of Studies in Intelligence contains two articles: What Analysts Need to Understand: The King's Intelligence Studies Program and The US Coast Guard and OSS Maritime Operations during World War II. This issue also includes three book reviews: Nisei Linguists: Japanese Americans in the Military Intelligence Service during World War II, by James C. McNaughton, is reviewed by Stephen C. Mercado, and An Ordinary Spy, by Joseph Weisberg, is ... |
|
| Coherence of Off-Topic Responses for a Virtual Character |
Dec 2008 |
7 pages |
| Authors:
Ron Artstein; Jacob Cannon; Sudeep Gandhe; Jillian Gerten; Joe Henderer; Anton Leuski; David Traum; UNIVERSITY OF SOUTHERN CALIFORNIA MARINA DEL REY CA INST FOR CREATIVE TECHNOLOGIES
|
| We demonstrate three classes of off-topic responses which allow a virtual question-answering character to handle cases where it does not understand the user's input: ask for clarification, indicate misunderstanding, and move on with the conversation. While falling short of full dialogue management, a combination of such responses together with prompts to change the topic can improve overall dialogue coherence. |
|
| Portable Language-Independent Adaptive Translation from OCR |
Dec 2008 |
5 pages |
| Authors:
Prem Natarajan; BBN TECHNOLOGIES CAMBRIDGE MA
|
| This is the fifth R&D quarterly progress report of the BBN-led team under DARPA's MADCAT program. The Multilingual Automatic Document Classification, Analysis and Translation (MADCAT) program will develop an end-to-end system to automatically translate handwritten and printed foreign documents into English with very high accuracy. The report is organized by technical task area. |
|
| Integrating Language and Cultural Knowledge into the Army Officer Corps |
12-Nov-2008 |
8 pages |
| Authors:
Jennifer L Purser; UNIV OF MILITARY INTELLIGENCE FORT HUACHUCA AZ
|
| As the Contemporary Operating Environment (COE) has shifted away from a necessity to apply conventional tactics towards a counterinsurgency fight, culture has become increasingly important to the U.S. Army. In the wake of such a tremendous tactical policy change, the U.S. Army must find a way to increase the cultural knowledge and strategic language capabilities within its Officer Corps. The Army's Training and Doctrine Command (TRADOC) recognizes this need and ... |
|
| DERI at TREC 2008 Enterprise Search Track |
Nov 2008 |
11 pages |
| Authors:
Ronan Cummins; Colm O'Riordan; NATIONAL UNIV OF IRELAND GALWAY
|
| This paper describes the work carried out by DERI for the Enterprise Search track at TREC 2008. We participated in both the expert search task and document search task of the track. For both tasks we made use of novel learned term-weighting schemes. For the expert search task, we used two different approaches (namely a profiling approach and a two-stage document centric approach). We found that the document centric approach ... |
|
| CSIR at TREC 2008 Expert Search Task: Modeling Expert Evidence in Expert Search |
Nov 2008 |
8 pages |
| Authors:
Jiepu Jiang; WEI LU; Haozhen Zhao; WUHAN UNIV (CHINA) SCHOOL OF ELECTRONIC INFORMATION
|
| In this paper, we described our method for the expert search task in TREC 2008. First, we proposed an adaption to the language modeling method for expert search, which considers the probability of query generation separately using each kind of expert evidence (full name, abbreviated name, and email address). Current expert search models can be easily integrated into our method. Our experiments indicated that our method can make use of ... |
|
| Word Importance Discrimination using Context Information |
Nov 2008 |
8 pages |
| Authors:
Danil Nemirovsky; Vladimir Dobrynin; FRENCH NATIONAL INSTITUTE FOR RESEARCH IN COMPUTER SCIENCE AND CONTROL SOPHIA ANTIPOLIS- MEDITERRANEAN RESEARCH CENTER (FRANCE)
|
| Word importance discrimination is a task deserving attention when one treats a topic from TREC where a topic is quite long. The goal of the process is to estimate importance of words which carry any (additional) information about user information needs. In our experiments we estimated word importance using context information of a word. |
|
| TREC 2008 at the University at Buffalo: Legal and Blog Track |
Nov 2008 |
13 pages |
| Authors:
Jianqiang Wang; Ying Sun; Omar Mukhtar; Rohini Srihari; STATE UNIV OF NEW YORK AT BUFFALO DEPT OF LIBRARY AND INFORMATION STUDIES
|
| In the TREC 2008, the team from the State University of New York at Buffalo participated in the Legal track and the Blog track. For the Legal track, we worked on the interactive search task using the Web-based Legacy Tobacco Document Library Boolean search system. Our experiment achieved reasonable precision but suffered significantly from low recall. These results, together with the appealing and adjudication results, suggest that the concept of ... |
|
| UTDallas at TREC 2008 Blog Track |
Nov 2008 |
12 pages |
| Authors:
Bin Li; Feifan Liu; Yang Liu; TEXAS UNIV AT DALLAS
|
| This paper describes our participation in the 2008 TREC Blog track. Our system consists of 3 components: data preprocessing, topic retrieval, and opinion finding. In the topic retrieval task, we applied Lemur IR toolkit and used various techniques for query expansion. In the opinion finding and polarization task, we employed a feature-based classification approach. Then re-ranking was performed using a linear combination of the opinionated score and the topic relevance ... |
|
| University of Waterloo at TREC 2008 Blog Track |
Nov 2008 |
9 pages |
| Authors:
Olga Vechtomova; WATERLOO UNIV (ONTARIO) DEPT OF MANAGEMENT SCIENCES
|
| The paper reports the University of Waterloo participation in the opinion and polarity tasks of the Blog track. The proposed method uses a lexicon built from several linguistic resources. The opinion discriminating ability of each subjective lexical unit was estimated using the Kullback-Leibler divergence. The KLD scores of subjective words occurring within fixed-size windows around instances of query terms were used in calculating document scores. The described system also used ... |
|
| Words Mean Things: The Case for Information System Attack and Control System Attack |
31-Oct-2008 |
28 pages |
| Authors:
Mark J Matsushima; NAVAL WAR COLL NEWPORT RI JOINT MILITARY OPERATIONS DEPT
|
| War fighters in the U.S. Department of Defense (DoD) need a more precise, focused lexicon and a common understanding of cyberspace-related terminology; the term Computer Network Attack (CNA) is too broad. DoD should incorporate two new terms into the DoD information operations (IO) lexicon as CNA subcategories: Information Systems Attack (ISA) and Control Systems Attack (CSA). Use of these two new terms will help the joint force commander (JFC) and ... |
|
| IIT Kharagpur at TREC 2008 Blog Track |
25 Oct 2008 |
10 pages |
| Authors:
Robin Anil; Sudeshna Sarkar; INDIAN INST OF TECH KHARAGPUR
|
| Blogs are often informally written, poorly structured, and filled with spelling and grammatical errors and nontraditional content. Performing linguistic analysis on blogs is plagued by two additional problems: (1) the presence of spam blogs and spam comments, and (2) extraneous noncontent, including blog-rolls, link-rolls, advertisements, and sidebars. Our system of retrieving the documents was made using the Apache Lucene search engine. Lucene was able to index the whole Blog06 dataset ... |
|
| Support for the Annual Meeting (30th) of the Cognitive Science Society |
Oct 2008 |
53 pages |
| Authors:
Christopher A Sanchez; ARIZONA STATE UNIV TEMPE ARIZONA BOARD OF REGENTS
|
| The Annual Meeting of the Cognitive Science Society is the premier international event for cognitive science work, and it also has been the historical center for interdisciplinary research related to cognition, as well as work that is specifically based on computational cognitive modeling. The objective of this project was to support student attendance for the 30th Annual Cognitive Science Conference by reducing the registration fees for students so that it ... |
|
| Portable Language-Independent Adaptive Translation From OCR |
30 Sep 2008 |
5 pages |
| Authors:
Prem Natarajan; BBN TECHNOLOGIES CAMBRIDGE MA
|
| This is the fourth R&D quarterly progress report of the BBN-led team under DARPA's MADCAT program. The Multilingual Automatic Document Classification, Analysis and Translation (MADCAT) program will develop an end-to-end system to automatically translate handwritten and printed foreign documents into English with very high accuracy. The report is organized by technical task area. |
|
| Statement of Rear Admiral Daniel P. Holloway Before the Oversight and Investigations Subcommittee of the House Armed Services Committee on Foreign Language and Cultural Awareness Transformation |
10-Sep-2008 |
12 pages |
| Authors:
Daniel P Holloway; HOUSE OF REPRESENTATIVES WASHINGTON DC
|
| Chairman Snyder, Congressman Akin, and distinguished members of the subcommittee, thank you for this opportunity to present an overview of Navy's Language, Regional Expertise and Culture transformation efforts and for your interest in, and support for, these vital programs. Navy leadership views language, regional expertise and culture, or LREC, as a force multiplier in the global, international maritime environment of the 21st Century. Catalyzed by the attack on USS Cole ... |
|
| Differential Effect of Correct Name Translation on Human and Automated Judgments of Translation Acceptability: A Pilot Study |
01-Sep-2008 |
28 pages |
| Authors:
Michelle Vanni; James Walrath; ARMY RESEARCH LAB ADELPHI MD COMPUTATIONAL AND INFORMATION SCIENCES DIRECTORATE
|
| This study proffers two important findings: (1) automated machine translation (MT) evaluation is insensitive to the cognitive gravitas of proper names, contributing to its weak modeling of human judgments of higher quality MT output, and (2) there is a "new" methodology that produces superior measurement of translation acceptability. Twenty Arabic sentences, each with average name density of 3.7 names in 22 words, were translated into English with a research-grade MT ... |
|
| Effective Presentation Media for Passenger Safety I: Comprehension of Briefing Card Pictorials and Pictograms |
01-Sep-2008 |
62 pages |
| Authors:
Cynthia L Corbett; Garnet A McLean; Donna K Cosper; FEDERAL AVIATION ADMINISTRATION OKLAHOMA CITY OK CIVIL AEROSPACE MEDICAL INST
|
| Federal regulations require airlines to provide safety briefings and briefing cards to inform passengers of routine and emergency safety procedures onboard transport airplanes. The exact content and presentation media used for safety briefings and cards are the responsibility of the airlines to implement, as long as the required minimum safety information is delivered. Consequently, passenger safety briefings and briefing cards vary greatly, and passenger attention to such briefings has been ... |
|
| Conversation Thread Extraction and Topic Detection in Text-Based Chat |
01-Sep-2008 |
|
| Authors:
Paige H Adams; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| Text-based chat systems are widely used within the Department of Defense, but the standard systems available do not provide robust capabilities for search, information retrieval, or information assurance. The objective of this research is to explore methods for the extraction of conversation threads from text-based chat systems in order to enable such tasks. As part of the research, we manually annotated over 20,000 Internet Relay Chat posts with conversation thread ... |
|
| U.S. Airline Transport Pilot International Flight Language Experiences, Report 1: Background Information and General/Pre-Flight Preparation |
01-Sep-2008 |
70 pages |
| Authors:
O V Prinzo; Alan Campbell; FEDERAL AVIATION ADMINISTRATION OKLAHOMA CITY OK CIVIL AEROSPACE MEDICAL INST
|
| In 1998, the International Civil Aviation Organization (ICAO) took a heightened interest in the role of language in airline accidents. Its Air Navigation Commission was directed to complete the task of strengthening relevant ICAO provisions concerning language requirements. Member states agreed to take steps to ensure air traffic control (ATC) personnel and flight crews involved in flight operations in airspace where the use of the English language is required were ... |
|
| Reasoning About Authorization and Security |
01-Sep-2008 |
7 pages |
| Authors:
Joseph Y Halpern; CORNELL UNIV ITHACA NY
|
| This project had three main thrusts: (1) to create a language for expressing authorization policies that satisfied numerous desiderata, including being expressive, being easy to use, having precise semantics, and allowing for accountability: (2) to add the ability to express knowledge based specifications to Nuprl, a well-developed language that has been used extensively to prove that programs satisfy their specifications, with the intent of then using Nuprl to automatically synthesize ... |
|
| Interrogation: World War II, Vietnam, and Iraq |
Sep 2008 |
264 pages |
| Authors:
James A Stone; David P Shoemaker; Nicholas R Dotti; NATIONAL DEFENSE INTELLIGENCE COLL WASHINGTON DC CENTER FOR STRATEGIC INTELLIGENCE RESEARCH
|
| In September 2004, the Intelligence Science Board, an advisory board appointed by the Director of National Intelligence, initiated the Study on Educing Information (EI). This study is an ongoing effort to review what is known scientifically about interrogation and other forms of human intelligence collection and to chart a path to the future. As part of our efforts, we have worked closely with faculty and students of the National Defense ... |
|
| ReSEARCH: A Requirements Search Engine: Progress Report 2 |
Sep 2008 |
49 pages |
| Authors:
Paige Adams; Pranav Anand; Grant Gehrke; Ralucca Gera; Marco Draeger; Craig Martell; Kevin Squire; NAVAL POSTGRADUATE SCHOOL MONTEREY CA GRADUATE SCHOOL OF BUSINESS AND PUBLIC POLICY
|
| This research addresses three closely related problems. (1) Most current search technology is based on a popularity metric (e.g., PageRank or ExpertRank), but not on the semantic content of the searched document. (2) When building components in a serviceoriented architecture (SOA), developers must investigate whether components that meet certain requirements already exist. (3) There is no easy way for writers of requirements documents to formally specify the meaning and domain ... |
|
| A Review of Contributions by Australian Research Institutions into Speech Processing |
Aug-2008 |
|
| Authors:
Trevor C Tao; DEFENCE SCIENCE AND TECHNOLOGY ORGANISATION EDINBURGH (AUSTRALIA) COMMAND CONTROL COMMUNICATIONS AND INTELLIGENCE DIV
|
| This report is a survey of contributions by various research institutions within Australia into several important applications of speech processing, such as speech and speaker recognition. The purpose of this report is to give a rough snapshot of where a number of individual research institutions stand. For each application, a number of research papers within Australia are discussed in detail. Although much of the above research is directed towards simple ... |
|
| Speechlinks: Robust Cross-Lingual Tactical Communication Aids |
01-Jun-2008 |
194 pages |
| Authors:
Shrikanth Narayanan; Panayiotis Georgiou; UNIVERSITY OF SOUTHERN CALIFORNIA LOS ANGELES
|
| This project was directed toward developing a unique tactical language translator with context-aware, mixed-initiative capability for tactical missions. The specific goals were to: 1) enable robust mixed-initiative tactical communication targeting multiple languages, 2) develop algorithms and tools that enable rapid construction and deployment of systems for new missions and languages, and 3) develop and implement a holistic evaluation process for cross-lingual communication systems that unifies usability, task achievement and cost. ... |
|
| Semantical Machine Understanding |
01-Jun-2008 |
44 pages |
| Authors:
Ying Zhao; Chetan Kotak; Charles C Zhou; QUANTUM INTELLIGENCE INC SANTA CLARA CA
|
| Semantical Machine Understanding is the foundation for automatic sense and decision making of multinational, multicultural, and coalition applications. We show an innovative semantical machine understanding system that can be installed on each node of a network and used as a semantic search engine. Innovations of such a system include 1" text mining: extract concepts and meaning clusters based on contexts using pattern recognition and machine learning; 2" meaning learning: extract ... |
|
| Orchestration: The Movement and Vocal Behavior of Free-Ranging Norwegian Killer Whales (Orcinus Orca) |
01-Jun-2008 |
304 pages |
| Authors:
Ari D Shapiro; MASSACHUSETTS INST OF TECH CAMBRIDGE JOINT PROGRAM IN APPLIED OCEAN SCIENCE AND ENGINEERING
|
| Studying the social and cultural transmission of behavior among animals helps to identify patterns and content of interaction. Killer whales likely acquire traits culturally based on their stable social groups, population-specific feeding behaviors, and group-distinctive vocal repertoires. Digital tags were used to record the movements and vocalizations of Norwegian killer whales. These animals carousel feed, corralling herring into a ball before tail slapping, incapacitating and eating the fish. Periods of ... |
|
| Department of Defense Dictionary of Military and Associated Terms |
30-May-2008 |
781 pages |
| Authors:
JOINT CHIEFS OF STAFF WASHINGTON DC
|
| The "Department of Defense Dictionary of Military and Associated Terms" (short title: Joint Pub 1-02 or JP 1-02) sets forth standard U.S. military and associated terminology to encompass the joint activity of the Armed Forces of the United States in both U.S. joint and allied joint operations, as well as to encompass the Department of Defense (DoD) as a whole. These military and associated terms, together with their definitions, constitute ... |
|
| Applying A Formal Language of Command and Control For Interoperability Between Systems |
21-May-2008 |
26 pages |
| Authors:
Ulrich Schade; Michael R Hieb; GEORGE MASON UNIV FAIRFAX VA CENTER FOR EXCELLENCE IN COMMAND CONTROL COMMUNICATIONS COMPUTERS - INTELLIGENCE
|
| Battle Management Language (BML) is being developed as an open standard that unambiguously specifies Command and Control information, including orders and reports built upon precise representations of tasks. BML is both a methodology and a language specification, based on doctrine and consistent with Coalition standards. Recent work has concentrated on leveraging standard data model semantics (particularly the Joint Consultation, Command and Control Information Exchange Data Model ? JC3IDM) for a ... |
|
| Automatically Generating Reading Comprehension Look-Back Strategy: Questions from Expository Texts |
14 May 2008 |
38 pages |
| Authors:
Donna M Gates; CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE
|
| Learning to read is an important skill for both children and adults, whether it takes place in their first language or their second language. According to the National Center for Educational Statistics 2003 Assessment (2007), 5% of adults (16 years and older) in the United States are functionally non-literate. Adults who enroll in literacy programs in the United States desire to improve reading skills for a variety of reasons. But ... |
|
| Data Analysis Project: Leveraging Massive Textual Corpora Using n-Gram Statistics |
01-May-2008 |
31 pages |
| Authors:
Andrew Carlson; Tom M Mitchell; Ian Fette; CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE
|
| We study methods of efficiently leveraging massive textual corpora through n-gram statistics. Specifically, we explore algorithms that use a database of frequency counts for sequences of tokens in a teraword Web corpus to correct spelling mistakes and to extract a list of instances of some category given only the name of the target category. For spelling correction, we use a novel correction algorithm and demonstrate high accuracy in correcting both ... |
|
| ReSEARCH: A Requirements Search Engine |
23-Apr-2008 |
54 pages |
| Authors:
Craig Martell; Paige H Adams; Pranav Anand; Grant Gehrke; Ralucca Gera; Marco Draeger; Kevin Squire; NAVAL POSTGRADUATE SCHOOL MONTEREY CA DEPT OF COMPUTER SCIENCE
|
| This research address three closely related problems. (1) Most current search technology is based on a popularity metric (e.g., PageRank or ExpertRank), but not on the semantic content of the document. (2) When building components in a service-oriented architecture (SOA), developers must investigate whether components that meet certain requirements already exist. (3) There is no easy way for writers of requirements documents to formally specify the meaning and domain of ... |
|
| Real World Cognitive Multi-Tasking and Problem Solving: A Large Scale Cognitive Architecture Simulation Through High Performance Computing-Project Casie |
Mar 2008 |
41 pages |
| Authors:
Santos; Eugene Jr; Kiley McEvoy; Nael Abu-Ghazaleh; Vinay Kolar; Mark Zhang; Zhen Guo; DARTMOUTH COLL HANOVER NH
|
| In its grandest sense, Project CASIE explored the development of a computational system capable of high level perception and problem solving that reflects the cognitive processes of the human brain. Most specifically, it concentrated on better understanding and modeling intuition and insight in a computational fashion. The goal was to address the fundamental problem of modeling and solving communities of tasks from a cognitive point of view through multiple problem ... |
|
| Impact of Language Immersion Programs on Foreign Language |
Mar-2008 |
80 pages |
| Authors:
Jean-Paul Chausse; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING AND MANAGEMENT
|
| Communicating with other nations in their native language is an important and necessary aspect of a successful United States' foreign policy. Critical to this success is the ability of military personnel to communicate clearly when in contact with foreign nationals, whether in peace-time or war. The Air Force has made great strides in the past 10 years to improve its foreign language capability, particularly through its application of the language ... |
|
| Recruiting for Foreign Language Skills Strategies for the Air Force |
15-Feb-2008 |
45 pages |
| Authors:
Maureen B Higgins; AIR WAR COLL MAXWELL AFB AL
|
| How well the U.S. forces analyze and interact with the local people they deal with during the Global War on Terror will be a decisive factor in whether the United States succeeds or fails in counterinsurgency operations. The expeditionary Air Force (AF) mission demands Airmen with international insight, foreign language proficiency, and cultural knowledge to understand the specific regional context in which air and space power may be applied. Lack ... |
|
| Operational Culture: Is The Australian Army Driving the Train or Left at the Station? |
Jan-2008 |
24 pages |
| Authors:
Steven W Brain; MARINE CORPS COMBAT DEVELOPMENT COMMAND QUANTICO VA
|
| Operational culture is a new wave of study enjoying much enthusiasm and popularity within most Western contemporary armies. Governed by the mission at hand, operational culture encompasses those aspects that can influence the outcome of a military operation, or conversely, those military actions that influence the cultural balance within an area of operations. As such, the correct application of operational culture is critical for any military force to favorably shape ... |
|
| Barriers, Bridges, and Progress in Cognitive Modeling for Military Applications |
Jan-2008 |
7 pages |
| Authors:
Kevin Gluck; AIR FORCE RESEARCH LAB MESA AZ WARFIGHTER READINESS RESEARCH DIVISION
|
| The role of the Air Force Research Laboratory (AFRL), like the other service laboratories, is to conduct the basic and applied research and advanced technology development necessary to create future technology options for the Department of Defense. At the Warfighter Readiness Research Division of AFRL's Human Effectiveness Directorate, we have initiated a research program focused on mathematical and computational cognitive process modeling for replicating, understanding, and predicting human performance and ... |
|
| U.S. Navy Language Skills, Regional Expertise, and Cultural Awareness Strategy |
Jan-2008 |
15 pages |
| Authors:
Harvey; J C Jr; OFFICE OF THE CHIEF OF NAVAL OPERATIONS WASHINGTON DC
|
| Given the changes in the strategic landscape since 9/11, the myriad post-Cold War cultures we face, and the unique maritime security challenges of the 21st Century, success in achieving the nation's Maritime Strategy depends in large part on our ability to communicate with and comprehend potential adversaries, enduring allies, and emerging partner nations. As the lessons of Operations Iraqi Freedom and Enduring Freedom attest, communication and comprehension are enabled through ... |
|
| Empirical Properties of Multilingual Phone-To-Word Transduction |
Jan-2008 |
5 pages |
| Authors:
Geoffrey Zweig; Jon Nedel; MICROSOFT RESEARCH REDMOND WA
|
| This paper explores the error-robustness of phone-to-word transduction across a variety of languages. We implement a noisy channel model in which a phonetic input stream is corrupted by an error model, and then transduced back to words using the inverse error model and linguistic constraints. By controlling the error level, we are able to measure the sensitivity of different languages to degradation in the phonetic input stream. This analysis is ... |
|
| Developing a Unit Language Capability for War |
Jan 2008 |
4 pages |
| Authors:
Tunnell; Harry D IV; ARMY (5TH) HQ FORT SAM HOUSTON TX
|
| The Language Enabled Soldier (LES) program is a locally designed and implemented 10-month Arabic language and culture program for selected Stryker Brigade Combat Team (SBCT) Soldiers at Fort Lewis, Washington. The student body ranges in grade from private first class to lieutenant. The concept began as a somewhat traditional Arabic language program. Based on feedback from deployed 4/2 ID (SBCT) LESs, however, it has evolved into more theater-specific training. . ... |
|
| Low-Resource Speech Translation of Urdu to English Using Semi-Supervised Part-of-Speech Tagging and Transliteration |
Jan 2008 |
|
| Authors:
A R Aminzadeh; Wade Shen; MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
| This paper describes the construction of ASR and MT systems for translation of speech from Urdu into English. As both Urdu pronunciation lexicons and Urdu-English bitexts are sparse, we employ several techniques that make use of semi-supervised annotation to improve ASR and MT training. Specifically, we describe 1) the construction of a semi-supervised HMM-based part-of-speech tagger that is used to train factored translation models and 2) the use of an ... |
|
| Odds of Successful Transfer of Low-level Concepts: A Key Metric for Bidirectional Speech-to-Speech Machine Translation in DARPA's TRANSTAC Program |
Jan 2008 |
8 pages |
| Authors:
Gregory A Sanders; Sebastien Bronsart; Sherri Condon; Crsig Schlenoff; NATIONAL INST OF STANDARDS AND TECHNOLOGY GAITHERSBURG MD
|
| The Spoken Language Communication and Translation System for Tactical Use (TRANSTAC) program is a Defense Advanced Research Agency (DARPA) program to create bidirectional speech-to-speech machine translation (MT) that will allow U.S. Soldiers and Marines, speaking only English, to communicate, in tactical situations, with civilian populations who speak only other languages (for example, Iraqi Arabic). A key metric for the program is the odds of successfully transferring low-level concepts, defined as ... |
|
| Learning to Extract Gene-Protein Names from Weakly-Labeled Text |
Jan 2008 |
12 pages |
| Authors:
Richard C Wang; Anthony Tomasic; Robert E Frederking; Isaac Simmons; William W Cohen; CARNEGIE-MELLON UNIV PITTSBURGH PA LANGUAGE TECHNOLOGIES INST
|
| Training a named entity recognizer (NER) has always been a difficult task due to the effort required to generate a significant amount of annotated training data. In this paper, we reduce or eliminate the effort required to create training data by automatically converting other sources of data into annotated training data. The performance of this approach is tested on a gene-protein name extractor by using the mouse and fly data ... |
|
| Integrating a Natural Language Message Pre-Processor with UIMA |
Jan 2008 |
17 pages |
| Authors:
Eric Nyberg; Eric Riebling; Richard C Wang; Robert Frederking; CARNEGIE-MELLON UNIV PITTSBURGH PA LANGUAGE TECHNOLOGIES INST
|
|
| The Jesuits: History's Most Effective Special Operators |
DEC 2007 |
61 pages |
| Authors:
Cary N. Culbertson; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| Jesuit missions to China, India, and Japan from 1540 to 1773 form a useful model for contemporary U.S. special operators seeking influence in societies infinitely different from their own. The year 1540 coincides with the beginning of the Society of Jesus and their entrance into the missionary field alongside the Franciscan and Dominican missionary orders, all subsets of the Roman Catholic Church. The Jesuits' practice of first establishing respect, then ... |
|
| Sequoyah Foreign Language Translation System - Business Case Analysis |
DEC 2007 |
|
| Authors:
Wing S. S. Ong; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| Sequoyah, which is the Department of Defense (DoD)'s Program of Record for automated foreign language translation, is to identify current and developing technologies to meet warfighter requirements for foreign language support. Sequoyah aspires to have MLT capability embedded in other systems, such as Soldier as a System (SaaS) and Future Combat System (FCS), so as to provide automated capability to meet the warfighters' foreign language translation needs when a human ... |
|
| 2-D Processing of Speech with Application to Pitch and Formant Estimation |
10 Nov 2007 |
|
| Authors:
Thomas F Quatieri; Tianyu T Wang; MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
| The grating compression transform (GCT) maps harmonically-related signal components to a concentrated entity in a spatial 2-D frequency plane * The GCT forms the basis of a pitch estimator that uses the radial distance to the largest peak of the GCT * The resulting pitch estimator appears robust under noise conditions and amenable to extension to two-speaker pitch estimation * The GCT forms the basis of a formant estimator that ... |
|
Linguistics
