DOCSLIB.ORG

Machine Learning in a Nutshell

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Machine Learning in a Nutshell Data Sciences = Big Data + Machine Learning + Domain Expertise (NLP, Bio, …) NAS –March, 2015 Jaime Carbonell& Colleagues Language Technologies Institute School of Computer Science Carnegie Mellon University www.cs.cmu.edu/~jgc Computing Departments at CMU Systems Lang Tech Theory Comp Bio Natural Machine Sciences Comp Hardware Software Learning Eng Robotics Computer Science Engineering 3/9/2015 Jaime G. Carbonell, CMU 2 Computing Departments at CMU Systems Lang Tech Theory Comp Bio Data Sciences Natural Machine Sciences Comp Hardware Software Learning Eng Robotics Computer Science Engineering 3/9/2015 Jaime G. Carbonell, CMU 3 How Big is Big? Dimensions of Big Data Analytics Billions++ of entries: Terabyes/Petabyesof data Trillions of potential relations among entries (graphs) Millions of attributes per entry (but typically sparse encoding) 3/9/2015 Jaime G. Carbonell, CMU 4 The Big-Data “Stack” Analytics Algorithms --Machine Learning --Pattern Detection Alerts, Visualization Big-DataArchitecture --Hadoop/H-Table --Asynch/Pegasus Sensors Big-Data “Plumbing” --Cloud/Storage Knowledge --ResourceAllocator Historical & base Normative Data 3/9/2015 Jaime G. Carbonell, CMU 5 The Big-Data “Stack” Analytics Algorithms --Machine Learning --Pattern Detection Alerts, Visualization Big-DataArchitecture --Hadoop/H-Table --Asynch/Pegasus Sensors Big-Data “Plumbing” --Cloud/Storage Knowledge --ResourceAllocator Historical & base Normative Data 3/9/2015 Jaime G. Carbonell, CMU 6 Machine Learning • Objectives – Discover patterns in data à make useful predictions • General approach – Select & train functional models on historical data – Apply trained models to make predictions on new data • Applications – Robotics, speech, medicine, biology, finance, cyber, energy, … • Hot topics – Deep neural networks – Transfer and proactive learning 3/9/2015 Jaime G. Carbonell, CMU 7 Machine Learning in a Nutshell r r r r o Training data: {xi , yi}i=1,...k +{xi}i=k +1,...n + O : xi ® yi n Special case: k = 0 o Functional space: Á = { f j ´ pl } o Fitness Criterion: n a.k.a. loss function éæ r ö ù arg min ç y - f (x ) ÷ + b ( f , p ) ê å i j, pl i j l ú j,l ëè i ø û o Active Sampling Strategy: r r r r argmin L( fˆ(x , yˆ ))| x È{x ,...,x } r r r ( test test i 1 k ) xiÎ{xk+1,...,xn } 3/9/2015 Jaime G. Carbonell, CMU 8 The Big Picture Unbalanced Rare Learning in Classifier Unlabeled Category Unbalanced Data Set Detection Settings Feature Feature Extraction Representation Relational Raw Data Temporal 3/9/2015 Jaime G. Carbonell, CMU 9 LL Evolutionary Tree of MT Paradigms Large- Large- scale TMT scale TMT Transfer Transfer MT MT w stat Interlingua phrases MT Context- Analogy Based MT MT Example- based MT Stat MT on syntax struct. Decoding Statistic Phrasal MT al MT SMT 10 1950 1980 2010 Morpho-Syntactics & Multi-Morphemics oIñupiaq(North Slope Alaska, Lori Levin) nTauqsiġñiaġviŋmuŋniaŋitchugut. n‘We won’t go to the store.’ oKalaallisut(Greenlandic, Per Langaard) nPittsburghimukarthussaqarnavianngilaq nPittsburgh+PROP+Trim+SG+kar+tuq+ssaq+qar+n aviar+nngit+v+IND+3SG n"It is not likely that anyone is going to Pittsburgh" 11 Context Needed to Resolve Ambiguity Example: English à Japanese Machine Translation Power line –densen(電線) Subway line –chikatetsu(地下鉄) (Be) on line –onrain(オンライン) (Be) on the line –denwachuu(電話中) Line up –narabu(並ぶ) Line one’s pockets – kanemochininaru (金持ちになる) Line one’s jacket – uwagio nijuunisuru(上着を二重にする) Actor’s line –serifu(セリフ) Get a line on –johoo eru(情報を得る) Sometimes local context suffices (as above) 3/9/2015 Jaime G. Carbonell, CMU 12 Active Learning for MT Parallel Expert corpus Translator S,T Trainer S Sampled Model corpus MT System Source Language Active Corpus Learner 3/9/2015 Jaime G. Carbonell, CMU 13 Active Crowd Translation S,T 1 S,T 2 Trainer . Translation . Selection . S,T Model n S Sentenc e Selectio n MT System Source Language ACT Corpus Framework 3/9/2015 Jaime G. Carbonell, CMU 14 Structure Learning for Next-Generation Machine Translation •Tree-tree aligner enforces equivalence constraints and optimizes over terminal alignment scores (words/phrases) •Resulting aligned nodes are highlighted in figure •T ransferrules are partially lexicalized and read off tree. 3/9/2015 Jaime G. Carbonell, CMU 15 Active vs Proactive Learning Active Learning Proactive Learning Number of Oracles Individual (only one) Multiple, with different capabilities, costs and areas of expertise Reliability Infallible (100% right) Variable across oracles and queries, depending on difficulty, expertise, … Reluctance Indefatigable (always Variable across oracles and answers) queries, depending on workload, certainty, … Cost per query Invariant (free or constant) Variable across oracles and queries, depending on workload, difficulty, … Note: “Oracle” Î {expert, experiment, computation, …} 3/9/2015 Jaime G. Carbonell, CMU 16 Proactive Learning: Wind Sampling o Predict: Prevalent Direction, Speed, seasonality o Measurement towers: Expensive –where, when? 3/9/2015 Jaime G. Carbonell, CMU 17 Inferring the Protein Interactome o Degree distribution / Hub analysis / Disease checking o Graph modules analysis (from bi-clustering study) o Protein-family based graph patterns (receptors / ligands/ etc ) 3/9/2015 Jaime G. Carbonell, CMU 18 18 PPIs: Protein-Protein Interactions o The cell machinery is run by the proteins n Enzymatic activities, replication, translation, transport, signaling, structural o Proteins interact with each other to perform these functions Through physical contact Indirectly Indirectly in pathway in a protein complex Indirectly in a pathway 3/9/2015 Jaime G. Carbonell, http://CMUwww.cellsignal.com/reference/pathway/Apoptosis_Overview.html Host Pathogen Interactomes Fusion HIV-1 depends on the cellular machinery in every Reverse aspect of its life cycle. transcription Transcription Budding Maturation Peterlin and Torono, Nature Rev Immu 2003. 3/9/2015 Jaime G. Carbonell, CMU 20 ROTEIN (Borrowed from: Judith P S Klein-Seetharaman) Sequence à Structure à Function Primary Sequence MNGTEGPNFY VPFSNKTGVV RSPFEAPQYY LAEPWQFSML AAYMFLLIML GFPINFLTLY VTVQHKKLRT PLNYILLNLA VADLFMVFGG FTTTLYTSLH GYFVFGPTGC NLEGFFATLG GEIALWSLVV LAIERYVVVC KPMSNFRFGE NHAIMGVAFT WVMALACAAP PLVGWSRYIP EGMQCSCGID YYTPHEETNN ESFVIYMFVV HFIIPLIVIF FCYGQLVFTV KEAAAQQQES ATTQKAEKEV TRMVIIMVIA FLICWLPYAG VAFYIFTHQG SDFGPIFMTI PAFFAKTSAV YNPVIYIMMN KQFRNCMVTT LCCGKNPLGD DEASTTVSKT ETSQVAPA Folding 3D Structure Complex function within network of proteins Normal 3/9/2015 Jaime G. Carbonell, CMU 21 PROTEINS Sequence à Structure à Function Primary Sequence MNGTEGPNFY VPFSNKTGVV RSPFEAPQYY LAEPWQFSML AAYMFLLIML GFPINFLTLY VTVQHKKLRT PLNYILLNLA VADLFMVFGG FTTTLYTSLH GYFVFGPTGC NLEGFFATLG GEIALWSLVV LAIERYVVVC KPMSNFRFGE NHAIMGVAFT WVMALACAAP PLVGWSRYIP EGMQCSCGID YYTPHEETNN ESFVIYMFVV HFIIPLIVIF FCYGQLVFTV KEAAAQQQES ATTQKAEKEV TRMVIIMVIA FLICWLPYAG VAFYIFTHQG SDFGPIFMTI PAFFAKTSAV YNPVIYIMMN KQFRNCMVTT LCCGKNPLGD DEASTTVSKT ETSQVAPA Folding 3D Structure Complex function within network of proteins Cancer: 3/9/2015 Jaime G. Carbonell, CMU unckecked cellular 22 replicaiton The “Folding Problem:” 3D Protein Structure Determination In Silico o In Vitro Lab experiments: time, cost, uncertainty, … n X-ray crystallography (months to crystalize, uncertain outcome) Nobel Prize, Kendrew & Perutz, 1962 n NMR spectroscopy (only works for small proteins or domains) Nobel Prize, Kurt Wuthrich, 2002 o The gap between sequence and structure necessitates computational methods of protein structure determination n 3,023,461 sequences v.s. 36,247 resolved structures (1.2%) 3/9/2015 Jaime G. Carbonell, CMU 23 Linked Segmentation CRF o Node: secondary structure elements and/or simple fold o Edges: Local interactions and long-range inter-chain and intra-chain interactions o L-SCRF: conditional probability of y given x is defined as 1 P(y,...,y|x,...,x)=exp(lmf(x,y))exp(gy(x,xy,,)) 1R1RZÕåkkii,jÕålkiai,,jab yi, jGÎVklyyi,,j,abGÎE Joint Labels 3/9/2015 Jaime G. Carbonell, CMU 24 Fold Alignment Prediction: β-Helix o Predicted alignment for known β -helices on cross-family validation 3/9/2015 Jaime G. Carbonell, CMU 25 Parting Thoughts o Data Science = Big Data + ML + Domains n Big data requires big (scalable) ML n Leverage scarce human expertise o Machine Learning is Engine for AI n Heretofore it was hand-coded knowledge n Applicable to virtually any domain o Big Impact Everywhere n Bio: genetic, molecular, healthcare n Language: speech, MT, text mining n Education: student models, transfer n Energy: optimization, production, conservation n Finance: investment, fraud detection, risk analysis 3/9/2015 Jaime G. Carbonell, CMU 26 THANK YOU! 3/9/2015 Jaime G. Carbonell, CMU 27.
Load more

Recommended publications
  • Proactive Learning for Building Machine Translation Systems for Minority Languages
    Proactive Learning for Building Machine Translation Systems for Minority Languages Vamshi Ambati Jaime Carbonell [email protected] [email protected] Language Technologies Institute Language Technologies Institute Carnegie Mellon University Carnegie Mellon University Pittsburgh, PA 15213, USA Pittsburgh, PA 15213, USA Abstract based MT systems require lexicons that provide cov- erage for the target translations, synchronous gram- Building machine translation (MT) for many mar rules that define the divergences in word-order minority languages in the world is a serious across the language-pair. In case of minority lan- challenge. For many minor languages there is guages one can only expect to find meagre amount little machine readable text, few knowledge- of such data, if any. Building such resources effec- able linguists, and little money available for MT development. For these reasons, it be- tively, within a constrained budget, and deploying an comes very important for an MT system to MT system is the need of the day. make best use of its resources, both labeled We first consider ‘Active Learning’ (AL) as a and unlabeled, in building a quality system. framework for building annotated data for the task In this paper we argue that traditional active learning setup may not be the right fit for seek- of MT. However, AL relies on unrealistic assump- ing annotations required for building a Syn- tions related to the annotation tasks. For instance, tax Based MT system for minority languages. AL assumes there is a unique omniscient oracle. In We posit that a relatively new variant of active MT, it is possible and more general to have multiple learning, Proactive Learning, is more suitable sources of information with differing reliabilities or for this task.
    [Show full text]
  • Jaime Carbonell Massively Multilingual Language
    Jaime Carbonell Carnegie Mellon University Massively Multilingual Language Technologies The so-called "digital divide" addressed the challenge of poorer people not having access to the internet and all the myriad resources that come from being digitally connected. With the advent and spread of affordable smart phones, the present challenge is the "linguistic divide" where speakers of rare languages, often in poorer nations or regions, lack access to the vast content of information contained only in major languages. We -- CMU and InterAct -- have long sought solutions, via machine translation and via methods that extend to rare languages with minimal on-line data, well beyond the major languages with economic clout that the ma- jor search engines address. The presentation outlines some of the challenges and methods to bridge the linguistic divide. Dr. Jaime Carbonell is the Director of the Language Technologies Institute and Allen Newell Professor of Computer Science at Carnegie Mellon University. He received SB degrees in Physics and Mathe- matics from MIT, and MS and PhD degrees in Computer Science from Yale University. His current research includes machine learning, data / text mining, machine translation, rare-language analysis and computational proteomics. He invented Proactive Machine Learning, including its underlying decision-theoretic framework. He is also known for the Maximal Marginal Relevance principle in information retrieval, for derivational analogy in problem solving and for example-based machine translation and for machine learning in structural biology, and in protein interaction networks. Overall, he has published some 350 papers and books and supervised some 60 PhD dissertations. .
    [Show full text]
  • Information Extraction Lecture 5 – Named Entity Recognition III
    Information Extraction Lecture 5 – Named Entity Recognition III CIS, LMU München Winter Semester 2016-2017 Dr. Alexander Fraser, CIS Administravia • Seminar • There is now a LaTeX template for the Hausarbeit on the Seminar web page • Please don't forget to send me your presentation (as a PDF) after giving it • And, as you know, the Hausarbeit is due 3 weeks after your presentation! 2 Outline • IE end-to-end • Introduction: named entity detection as a classification problem 3 CMU Seminars task • Given an email about a seminar • Annotate – Speaker – Start time – End time – Location CMU Seminars - Example <[email protected] (Jaime Carbonell).0> Type: cmu.cs.proj.mt Topic: <speaker>Nagao</speaker> Talk Dates: 26-Apr-93 Time: <stime>10:00</stime> - <etime>11:00 AM</etime> PostedBy: jgc+ on 24-Apr-93 at 20:59 from NL.CS.CMU.EDU (Jaime Carbonell) Abstract: <paragraph><sentence>This Monday, 4/26, <speaker>Prof. Makoto Nagao</speaker> will give a seminar in the <location>CMT red conference room</location> <stime>10</stime>-<etime>11am</etime> on recent MT research results</sentence>.</paragraph> IE Template Slot Name Value Speaker Prof. Makoto Nagao Start time 1993-04-26 10:00 End time 1993-04-26 11:00 Location CMT red conference room Message Identifier (Filename) [email protected]. EDU (Jaime Carbonell).0 • Template contains *canonical* version of information • There are several "mentions" of speaker, start time and end- time (see previous slide) • Only one value for each slot • Location could probably also
    [Show full text]
  • Probabilistic Approaches for Answer Selection in Multilingual Question Answering
    Probabilistic Approaches for Answer Selection in Multilingual Question Answering Jeongwoo Ko Aug 27 2007 Language Technologies Institute School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Thesis Committee: Eric Nyberg (Chair) Teruko Mitamura Jaime Carbonell Luo Si (Purdue University) Copyright c 2007 Jeongwoo Ko This work was supported in part by ARDA/DTO Advanced Question Answering for Intelligence (AQUAINT) program award number NBCHC040164 and used the NTCIR 5-6 corpus. Keywords: Answer ranking, answer selection, probabilistic framework, graphi- cal model, multilingual question answering To my family for love and support. iv Abstract Question answering (QA) aims at finding exact answers to a user’s natural language question from a large collection of documents. Most QA systems combine information retrieval with extraction techniques to iden- tify a set of likely candidates and then utilize some selection strategy to generate the final answers. This selection process can be very challenging, as it often entails ranking the relevant answers to the top positions. To address this challenge, many QA systems have incorporated semantic re- sources for answer ranking in a single language. However, there has been little research on a generalized probabilistic framework that models the correctness and correlation of answer candidates for multiple languages. In this thesis, we propose two probabilistic models for answer ranking: independent prediction and joint prediction. The independent prediction model directly estimates the probability of an individual answer candi- date given the degree of answer relevance and the amount of supporting evidence provided in a set of answer candidates. The joint prediction model uses an undirected graph to estimate the joint probability of all answer candidates, from which the probability of an individual candidate is inferred.
    [Show full text]
  • Active Learning
    AI, Machine Learning and Language Technologies: What’s Next? Army Mad Scientists Program March 7, 2017 Jaime Carbonell, and colleagues School of Computer Science Carnegie Mellon University www.cs.cmu.edu/~jgc AI Touches Virtually All Areas of Computer Science Systems Entertain Lang + Theory Tech Tech Fine Arts Comp Artificial Intelligence Bio Sciences Machine Learning Human-Comp Interaction Robotics Computer Humanities Science Engineering 3/6/2017 Jaime G. Carbonell, Language 2 Technolgies Institute AI is Becoming Central to the World Economy (Davos 2016) “The fourth Industrial Revolution” is characterized by: n “Ubiquitous and mobile internet”, n “Smaller and more powerful sensors”, n “Artificial Intelligence”, and n “Machine Learning” -- Prof. Klaus Schwab, founder of the Davos World Economic Forum, 2016 3/6/2017 Jaime G. Carbonell, Language 3 Technolgies Institute Key Components of AI o Automated Perception n Vision, sonar, lidar, haptics, … o Robotic Action n Locomotion, manipulation, … o Deep Reasoning n Planning, goal-oriented behavior, projection, … o Language Technologies n Language, speech, dialog, social nets, … o Machine Learning n Adaptation, reflection, knowledge acquisition, … o Big Data 3/6/2017 Jaime G. Carbonell, Language 4 Technolgies Institute Key Components of AI o Automated Perception n Vision, sonar, lidar, haptics, … o Robotic Action n Locomotion, manipulation, … o Deep Reasoning n Planning, goal-oriented behavior, projection, … o Language Technologies n Language, speech, dialog, social nets, … o Machine Learning Today’s main focus n Adaptation, reflection, knowledge acquisition, … My research o Big Data 3/6/2017 Jaime G. Carbonell, Language 5 Technolgies Institute How Big is Big? Dimensions of Big Data Analytics LARGE-SCALE : TERABYTES PETABYTES EXOBYTES Billions++ of entries: Terabyes/Petabyes of data HIGH-COMPLEXITY Trillions of potential relations among entries (graphs) HIGH-DIMENSIONAL Millions of attributes per entry (but typically sparse encoding) 3/6/2017 Jaime G.
    [Show full text]
  • Active Learning and Crowd-Sourcing for Machine Translation
    Active Learning and Crowd-Sourcing for Machine Translation Vamshi Ambati, Stephan Vogel, Jaime Carbonell Language Technologies Institute Carnegie Mellon University, Pittsburgh, PA 15213, USA fvamshi,vogel,[email protected] Abstract In recent years, corpus based approaches to machine translation have become predominant, with Statistical Machine Translation (SMT) being the most actively progressing area. Success of these approaches depends on the availability of parallel corpora. In this paper we propose Active Crowd Translation (ACT), a new paradigm where active learning and crowd-sourcing come together to enable automatic translation for low-resource language pairs. Active learning aims at reducing cost of label acquisition by prioritizing the most informative data for annotation, while crowd-sourcing reduces cost by using the power of the crowds to make do for the lack of expensive language experts. We experiment and compare our active learning strategies with strong baselines and see significant improvements in translation quality. Similarly, our experiments with crowd-sourcing on Mechanical Turk have shown that it is possible to create parallel corpora using non-experts and with sufficient quality assurance, a translation system that is trained using this corpus approaches expert quality. 1. Introduction tive learning approaches help us identify sentences, which Corpus based approaches to automatic translation like Ex- if translated have the potential to provide maximal improve- ample Based and Statistical Machine Translation systems ment to an existing system. Crowd-sourcing techniques, on use large amounts of parallel data created by humans to the other hand help us reach a significant number of trans- train mathematical models for automatic language transla- lators at very low costs.
    [Show full text]
  • Jaime G. Carbonell -- Curriculum Vita
    Jaime G. Carbonell -- Curriculum Vita Business Address Language Technologies Institute Carnegie Mellon University Pittsburgh, Pennsylvania 15213 USA Telephone: (412) 268-7279 Fax: (412) 268-6298 Email: [email protected] http://www.cs.cmu.edu/~jgc/ Personal: Born: July 29, 1953. Citizenship: USA Academic and Professional Positions Held 1996 - Present Director, Language Technologies Institute, Carnegie Mellon University 1995 - Present Allen Newell Professor of Computer Science, Carnegie Mellon University 2006 - Present Adjunct Faculty, Dept of Computational Biology, U Pittsburgh Medical School. 2003 - 2009 Chief Scientist, Meaningful Machines Inc. 2001 - 2011 Co-Founder, Board chairman, Carnegie Speech Incorporated 1995 - 2003 Co-Founder, Board chairman, Wisdom Technologies Corporation 1986 - 1996 Director, Center for Machine Translation, Carnegie Mellon University 1987 - 1995 Professor of Computer Science, Carnegie Mellon University 1983 - 1987 Associate Professor of Computer Science, Carnegie Mellon University 1983 - 1996 Co-Founder, Director, Scientific advisor, Carnegie Group Inc. 1979 - 1983 Assistant Professor of Computer Science, Carnegie Mellon University 1975 - 1978 Research Fellow in Computer Science, Yale University 1975 - 1977 Teaching Assistant in Computer Science, Yale University 1974 - 1975 Research Assistant, Center for Space Research, MIT 1971 - 1975 Research Programmer, Artificial Intelligence, BBN, Cambridge, MA Education 1975 - 1979 Yale University PhD 1979 – Computer Science MPhil 1977 - Computer Science MS 1976 - Computer Science 1971 - 1975 Massachusetts Institute of Technology SB 1975 - Physics SB 1975 - Mathematics Professional Organizations and Activities Member: ACM (elected Chair of SIGART 1983-85), ACL, AAAI (AAAI Fellow 1988-present, AAAI executive committee 1990-92), Cognitive Science Society, Sigma Xi, AMTA. Government Committees: NIH Human Genome Scientific Advisory Committee, aka "Watson Committee" (1988- 1992).
    [Show full text]
  • Naacl Hlt 2010
    NAACL HLT 2010 Workshop on Active Learning for Natural Language Processing (ALNLP-10) Proceedings of the Workshop June 6, 2010 Los Angeles, California USB memory sticks produced by Omnipress Inc. 2600 Anderson Street Madison, WI 53707 USA c 2010 The Association for Computational Linguistics Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 [email protected] ii Introduction Labeled training data is often required to achieve state-of-the-art performance in machine learning solutions to natural language tasks. While traditional supervised learning relies on existing labeled data, active learning algorithms may select unlabeled data for labeling with the goal of reducing annotation costs, while maintaining high accuracy. Thus, active learning has emerged as a promising framework for NLP applications and annotation projects where unlabeled data is readily available (e.g., web pages, audio recordings, minority language data), but obtaining labels is cost-prohibitive. The 2010 Workshop on Active Learning for Natural Language Processing (ALNLP) is the sequel to a successful 2009 meeting of the same name—both co-located with the Annual Conference of the North American Chapter of the Association for Computational Linguistics—with the intent of exploring key practical and theoretical aspects of active learning applied to real-world NLP problems. As we assembled the program committee, the topic’s timeliness resonated with researchers both in machine learning (who see natural language as an important application domain for active learning), and with those in language technologies (who see maturing active learning methods as an important part of their toolbox).
    [Show full text]
  • The Natural Language Sourcebook
    National Center for Research on Evaluation, C R E S S T Standards, and Student Testing Technical Report You can view this document on your screen or print a copy. UCLA Center for the Study of Evaluation in collaboration with: University of Colorado NORC, University of Chicago LRDC, University of Pittsburgh The RAND Corporation NATURAL LANGUAGE SOURCEBOOK Walter Read, Michael Dyer, Eva Baker, Patricia Mutch Frances Butler, Alex Quilici, John Reeves Center for Technology Assessment Center for the Study of Evaluation and Computer Science Department UCLA 1990 This overall project was directed by Eva L. Baker, funded by DARPA and administered by ONR, Contract Number N00014-86-K- 0395. We wish to thank the following people for assistance Craig Fields, MCC, Susan Chipman, ONR, Steve Kaisler, formerly of DARPA, Bob Simpson and Charles Wayne of DARPA, and, at UCLA, Sherry Miranda and Richard Seligman of the Office of Contracts and Grants Administration. In addition, the authors would like to thank the following people for their contributions at various stages in the development of the Natural Language Sourcebook: Kathleen Brennan, Rory Constancio, Cheryl Fantuzzi, Jana Good, Dayle Hartnett, Jill Fain Lehman, Elaine Lindheim, Mark Neder, and Jean Turner. Finally, Jaime Carbonell, Martha Evens, Evelyn Hatch, David Kieras, Carol Lord, and Merlin Wittrock served as consultants for the Sourcebook. Their suggestions were invaluable to the authors. © 1990 by the Regents of the University of California Table of Contents Introduction .............................................. 1 Sourcebook classification ................................. 13 Group I: Single-utterance issues ......................... 14 Identification of syntactic units .................... 15 Ambiguity ............................................ 23 Modifier attachment .................................. 50 Reference ............................................ 61 Metaphor and novel language .........................
    [Show full text]
  • Jaime G. Carbonell -- Curriculum Vita
    Jaime G. Carbonell -- Curriculum Vita Business Address Language Technologies Institute Carnegie Mellon University Pittsburgh, Pennsylvania 15213 USA Telephone: (412) 268-7279 Fax: (412) 268-6298 Email: [email protected] http://www.cs.cmu.edu/~jgc/ Citizenship: USA Academic and Professional Positions Held 2012 - Present University Professor, School of Computer Science, Carnegie Mellon University 1996 - Present Director, Language Technologies Institute, Carnegie Mellon University 1995 - Present Allen Newell Professor of Computer Science, Carnegie Mellon University 2006 - Present Adjunct Faculty, Dept of Computational Biology, U Pittsburgh Medical School. 2001 – Present Co-Founder, Board chairman, Carnegie Speech Corporation 1995 - 2003 Co-Founder, Board chairman, Wisdom Technologies Corporation 1986 - 1996 Director, Center for Machine Translation, Carnegie Mellon University 1987 - 1995 Professor of Computer Science, Carnegie Mellon University 1983 - 1987 Associate Professor of Computer Science, Carnegie Mellon University 1983 - 1996 Co-Founder, Director, Scientific advisor, Carnegie Group Inc. 1979 - 1983 Assistant Professor of Computer Science, Carnegie Mellon University 1975 - 1978 Research Fellow in Computer Science, Yale University 1975 - 1977 Teaching Assistant in Computer Science, Yale University 1974 - 1975 Research Assistant, Center for Space Research, MIT 1971 - 1975 Research Programmer, Artificial Intelligence, BBN, Cambridge, MA Education 1975 - 1979 Yale University PhD 1979 – Computer Science MPhil 1977 - Computer Science MS 1976 - Computer Science 1971 - 1975 Massachusetts Institute of Technology SB 1975 - Physics SB 1975 - Mathematics Professional Organizations and Activities Member: ACM (elected Chair of SIGART 1983-85), ACL, AAAI (AAAI Fellow 1988-present, AAAI executive committee 1990-92), Cognitive Science Society, Sigma Xi, AMTA. Government and other Committees: NSF/CISE Scientific Advisory Committee (2010-2014), NIH Human Genome Scientific Advisory Committee, aka "Watson Committee" (1988-1992).
    [Show full text]
  • Manuela M. Veloso
    Manuela M. Veloso Computer Science Department Home address: Carnegie Mellon University 6645 Woodwell Street Pittsburgh PA 15213-3819 Pittsburgh PA 15217 tel: (412) 268-1474 Citizenship: USA email: [email protected] Birth: Lisbon, Portugal, August 12, 1957 http://www.cs.cmu.edu/˜mmv/ Married; two sons, born 1981 and 1987 Academic Positions July 02 - Professor, Computer Science Department, Carnegie Mellon University July 99 - July 02 Tenured Associate Professor, Computer Science Department, Carnegie Mellon University Aug 99 - Aug 00 Visiting Associate Professor, Electrical Engineering and Computer Science Department, AI Lab, Massachusetts Institute of Technology, on sabbatical leave from Carnegie Mellon University. July 97 - July 99 Associate Professor, Computer Science Department, Carnegie Mellon University Sep 92 - June 97 Assistant Professor Computer Science Department, Carnegie Mellon University Aug 87 - Aug 92 Research Assistant in Computer Science, Carnegie Mellon University Jan 85 - Jul 86 Teaching Assistant/Lecturer in Computer Science, Boston University Oct 80 - Jul 84 Teaching Assistant/Lecturer in Electrical and Computer Engineering, Instituto Superior Tecnico,´ Lisbon, Portugal Education 1992 Ph.D. in Computer Science School of Computer Science, Carnegie Mellon University, Pittsburgh 1986 M.A. in Computer Science Computer Science Department, Boston University, Boston 1984 M.Sc. in Electrical and Computer Engineering Electrical and Computer Engineering Department, Instituto Superior Tecnico,´ Lisbon, Portugal 1980 Licenciatura
    [Show full text]
  • Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics Short Papers
    HLT-NAACL 2006 Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics Short Papers Robert C. Moore, General Chair Jeff Bilmes, Jennifer Chu-Carroll and Mark Sanderson Program Committee Chairs June 4-9, 2006 New York, New York, USA Published by the Association for Computational Linguistics http://www.aclweb.org Production and Manufacturing by Omnipress Inc. 2600 Anderson Street Madison, WI 53704 c 2006 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-570-476-0860 [email protected] ii Table of Contents Factored Neural Language Models Andrei Alexandrescu and Katrin Kirchhoff. .1 The MILE Corpus for Less Commonly Taught Languages Alison Alvarez, Lori Levin, Robert Frederking, Simon Fung, Donna Gates and Jeff Good. .5 Museli: A Multi-Source Evidence Integration Approach to Topic Segmentation of Spontaneous Dialogue Jaime Arguello and Carolyn Rose . 9 Measuring Semantic Relatedness Using People and WordNet Beata Beigman Klebanov . 13 Thai Grapheme-Based Speech Recognition Paisarn Charoenpornsawat, Sanjika Hewavitharana and Tanja Schultz . 17 Class Model Adaptation for Speech Summarisation Pierre Chatain, Edward Whittaker, Joanna Mrozinski and Sadaoki Furui . 21 Semi-supervised Relation Extraction with Label Propagation Jinxiu Chen, Donghong Ji, Chew Lim Tan and Zhengyu Niu . 25 Temporal Classification of Text and Automatic Document Dating Angelo Dalli . 29 Answering the question you wish they had asked: The impact of paraphrasing for Question Answering Pablo Duboue and Jennifer Chu-Carroll . 33 Gesture Improves Coreference Resolution Jacob Eisenstein and Randall Davis .
    [Show full text]