Philip Resnik

News flash (December 2008): I have just added What kind of student are you looking for? to my FAQ for prospective students. News flash (November 2008): Brief interview on Federal News Radio discussing cloud computing and its relevance to language technology. News flash (October 2008): Press release on a new project! News flash (September 2008): Speaking of new projects, Alec Jay Resnik (we're calling him Jay) was born last week! Everyone's doing fine. I'm not taking any official time off, though I may be a bit less responsive than usual to e-mail for the next few weeks.

FAQ for prospective advisees/applicants

• List of publications
  List of students

• Since September 1996 I have been a member of the Linguistics faculty at the University of Maryland, College Park, with a joint appointment at the University of Maryland Institute for Advanced Computer Studies (UMIACS). I am also an affiliate associate professor in the Department of Computer Science.

  I do research in computational linguistics, with interests both in the modeling of human linguistic processes (especially lexical semantics, lexical acquisition, and on-line sentence processing) and in the application of natural language processing techniques to practical problems such as cross-language searching and machine translation. My general research agenda for language technology is to improve the state of the art by finding the right balance between knowledge-free statistical modeling and linguistically informed techniques -- and in so doing, to obtain a better scientific understanding of human language itself.

  My recent work has largely been focused on machine translation and multilingual natural language processing, exploiting parallel corpora and linguistically informed modeling in statistical machine translation and in multilingual natural language processing more generally (with a focus on Chinese and Arabic, as well as other less-studied languages). As part of this effort, my postdoc David Chiang (now at USC/ISI) developed Hiero, the first syntax-based system to demonstrate performance comparable to state-of-the-art statistical MT systems (see 2005 NIST MT Evaluation results). I have been working with a number of students to further improve hierarchical phrase-based translation, and some recent innovations include the introduction of lattice decoding (useful in translation of speech recognition output and also for text translation of morphologically complex languages), development of efficient algorithms for using suffix array representations in hierarchical decoding, and the use of English-to-English translation to create artificial references translations for use in parameter tuning.

  I have also been ramping up on work in sentiment analysis, with a particular interest in the connections among lexical semantics, surface linguistic expression, and underlying internal state. For example, why does my toddler say "My toy broke" instead of "I broke my toy"? He's employing "spin" in just the same way that Ronald Reagan did in 1987 when he sidestepped attributing responsibility for the Iran-contra scandal ("Mistakes were made"). My student Dr. Stephan Greene recently completed a fascinating dissertation on this topic, and I'm eagerly pursuing it further.

  During the next several years, I hope to re-engage more fully with my interests in computational psycholinguistics. I'm particularly interested in the possibility that ideas from (statistical) information theory may have a useful role to play in explaining why language works the way it does. (This is an idea I first began exploring in my dissertation [ps, pdf].)

  See my on-line list of publications for links to papers on the above research topics and more.

• I spent academic year 2003-2004 on sabbatical at Johns Hopkins University, focusing on machine translation and on some interesting work related to child language acquisition.

• I spent parts of May and August 2001 as a visiting researcher at the spoken language processing group of LIMSI-CNRS (Orsay, near Paris), working with Patrick Paroubek on automatic processing of medical research articles to help identify synonymous gene identifiers.

• I spent January 2000 as a visiting professor in Linguistics at the University of Paris 7.

• After finishing my doctorate I spent 3 years as a research scientist at Sun Microsystems Laboratories, near Boston, Massachusetts. Arriving at Sun Labs in October 1993, I spent much of my time there working on the Conceptual Indexing project (which got a nice writeup in the April 1996 issue of The Atlantic Monthly). I also started up a project looking at multilingual issues on the World Wide Web, in collaboration with Gary Adams. One result of this was United States Patent 6,615,168 awarded to Resnik, et al., September 2, 2003: Multilingual agent for use in computer systems.

• I did my Ph.D. in Computer and Information Science at the University of Pennsylvania. I spent most of my time at Penn at the Institute for Research in Cognitive Science (IRCS), a truly wonderful interdisciplinary environment. My dissertation received the 1994 Rubinoff Award.

• I spent the summer of 1991 working at IBM's T.J. Watson Research Center, resulting in my being included as co-inventor on Patent 5,267,345, issued November 30, 1993, "Speech recognition apparatus which predicts word classes from context and words from word classes", with co-inventors Peter Brown, Stephen Della Pietra, Vincent Della Pietra, Robert Mercer, and Stanley Chen.

• Before going back for my Ph.D. at Penn, I worked for two years as a research scientist at Bolt Beranek and Newman (BBN) in the area of language understanding.

• And before BBN, I was an undergraduate at Harvard (class of '87), where I concentrated in Computer Science.

• For several years, I served as the UMD Linguistics Department's undergraduate advisor. That role is now being filled ably by Dr. Tonia Bleam (tbleam _AT_ umd *DOT* edu). Linguistics undergrads with advising questions should see the Linguistics Undergraduate Advising FAQ for answers to many common questions.

• I have been on the editorial board of The Open Cybernetics and Systemics Journal since June 2007, and I'm also on the editorial board of Linguistic Issues in Language Technology, a new journal that focuses on relationships between linguistic insights, which can prove valuable to language technology, and language technology, which can enrich linguistic research. Past editorial board service includes Cognitive Linguistics from January 2005 to December 2006, Computational Linguistics from 1998-2000, Cognition from 1994-2004, and Computers and the Humanities from 1997 to 2005.

• I'm a (very) occasional contributor to Language Log.

• I helped instigate the SENSEVAL evaluations for word sense disambiguation.

• Why Work on Machine Translation?

• Why Do We Teach?

• First on the list of important things in my life would have to be my family: Ben (with his own home page, of which he is rightfully proud, though it needs an update) my incredibly wonderful wife, Becky, and our toddler, Harry. And let's not forget Annie the Dog.

• I am, believe it or not (sometimes I don't), a Sunday school music teacher, at Beth Chai, the The Greater Washington Jewish Humanist Congregation. Beth Chai is a lovely community of people from all over the D.C. area, and it's really growing.

• I am also, believe it or not, an advanced brown belt in Thai Kickboxing. (Just in case the Sunday School approach doesn't solve all my problems, you know? :->) I've learned many challenging moves, and I'm looking forward to progressing bit by bit toward a black belt.

• In 2000 I became a homeowner. Eeek! To get an idea what the joys of home ownership are like, take a look at my Home Problem Solving page.

• Other goings on... I've been interested in swing and ballroom dance since taking some classes at MIT and even, once upon a time, competing at the Fifth Annual Harvard Ballroom Dance Team Invitational Competition. (Newcomer category, made the quarter finals in East coast swing and managed not to embarass either my partner or myself at tango and foxtrot.) Here's a somewhat personalized list of useful dancing sites in the D.C. area.

• I came across an old dance acquaintance on the Web, helping illustrate why I like lindyhop. :-)

• In 1996 I sang at the 50th anniversary concert of the Harvard Krokodiloes, a 12-man a capella singing group of which I am an alumnus. In the blink of an eye, the 60th anniversary rolled around and I sang in one of the alumni performances for that event, too.

• A while back I took a rather interesting trip to New Orleans for Mardi Gras, and wrote up some of my adventures.

• Check out artist Janet Echelman's Web page. I'm pleased to have helped put together her original page, years ago in the dark ages when Janet was a Web novice. She's now obviously surpassed my meager Web talents by a long shot.

• I just stumbled across a bit of ancient history. Pretty fun to be able to document my Internet presence back to 1989.

• Quite some time back, I added a bullet recommending that people check out Annie's Census Song, a trifle of satire written by a dear friend, author and screenwriter Nicki Galland, in a mad fit of boredom. I wrote, "Nicki is much busier these days, having published a well received first novel entitled The Fool's Tale; then a second novel (Revenge of the Rose, which came out in August 2006). Her third novel is, I believe, due out in early 2008." Well, that novel came out --- Crossed: A Tale of the Fourth Crusade --- and although it's great historical fiction on its own, you should check out this YouTube promo for a fascinating take on how the book only seems to be about the fourth crusade but is, in a deeper sense, really about what's been going on in Iraq.

• Photo for a neat science fair project for which I helped provide a few pointers. (How many 7th graders do you know who are looking into information theory?!)

• Once upon a time, Ben invented Scimon Cards, which are like Pokemon cards but for science-minded kids.

• A few favorite books, ones that I revisit every few years once they are "ripe" for re-reading...
  • Mark Helprin, Winter's Tale
  • Peter S. Beagle, A Fine and Private Place
  • Orson Scott Card, Ender's Game
  • William Goldman, The Princess Bride
  • Frances Hodgson Burnett, The Lost Prince
  • Margaret Atwood, The Handmaid's Tale (Are we there yet?)
  • Neal Stephenson, Cryptonomicon
  • George Orwell, 1984
  • Victor Frankl, Man's Search for Meaning
  • Faber and Mazlish, How to Talk So Kids Will Listen and Listen So Kids Will Talk

  Philip Resnik, Associate Professor
  Department of Linguistics and Institute for Advanced Computer Studies

  1401 Marie Mount Hall            UMIACS phone: (301) 405-6760       
  University of Maryland           Linguistics phone: (301) 405-8903
  College Park, MD 20742 USA	   Fax   : (301) 405-7104       
  http://umiacs.umd.edu/~resnik	   E-mail: resnik [AT] umd _DOT_ edu

  UMIACS office: AV Williams 3143

  By far the best way to reach me is by e-mail to resnik [AT] umd _DOT_ edu.