Subject: coling / acl workshop on multilingual information management : report

coling - acl ' 98 workshop multilingual information management : current levels and future abilities august 16 , 1998 universite de montreal montreal / canada the coling / acl workshop on multilingual information management is a follow-on to an nsf - sponsored workshop held in conjunction with the first international conference on language resources and evaluation in granada , spain ( may 1998 ) . the goal of the workshop was to consider the recent history and likely near-term future of a number of research areas pertaining to language that are related ( but still semi-independent at present ) . the conclusions have been gathered into a report , to be submitted to the nsf , le , and other funding agencies in europe and north america , for their consideration in setting funding policies and goals . the draft report is now available at http : / / www . cs . cmu . edu / ~ ref / mlim / at the granada workshop , an international panel of invited experts focused on a set of questions in an attempt to identify the most likely and most effective future directions of computational linguistics research - especially in the context of the need to handle multi-lingual and multi - modal information . the coling workshop , a follow-on , has the aim of opening the discussion to the computational linguistics community as a whole , to solicit the comments , additions , feedback , and contributions of everyone . to register , consult the coling / acl home page at http : / / coling-acl 98 . iro . umontreal . ca / workshop description the development of natural language applications which handle multi - lingual and multi-modal information is the next major challenge facing the field of computational linguistics . over the past 50 years , a variety of language-related capabilities has been developed in areas such as machine translation , information retrieval , and speech recognition , together with core capabilities such as information extraction , summarization , parsing , generation , multimedia planning and integration , statistics-based methods , ontologies , lexicon construction and lexical representations , and grammar . the next few years will require the extension of these technologies to encompass multi-lingual and multi-modal information . extending current technologies will require integration of the various capabilities into multi-functional natural language systems . however , there is today no clear vision of how these technologies could or should be assembled into a coherent framework . what would be involved in connecting a speech recognition system to an information retrieval engine , and then using machine translation and summarization software to process the retrieved text ? how can traditional parsing and generation be enhanced with statistical techniques ? what would be the effect of carefully crafted lexicons on traditional information retrieval ? the workshop is organized as a series of discussion sessions , each one devoted to one aspect of computational language , initiated by a report of the discussions at the granada workshop ( a report summarizing the discussions at granada is available ; see below ) . enough time for discussion has been scheduled . the discussion will focus on the following fundamental questions : 1 . what is the current level of capability in each of the major areas of the field dealing with language and related media of human communication ? 2 . how can ( some of ) these functions be integrated in the near future , and what kind of systems will result ? 3 . what are the major considerations for extending these functions to handle multi-lingual and multi-modal information , particularly in integrated systems of the type envisioned in ( 2 ) ? in particular , we will consider these questions in relation to the following areas : o multi-lingual resources ( lexicons , ontologies , corpora , etc . ) o information retrieval , especially cross-lingual and cross-modal o machine translation , of text and speech o automated ( cross-lingual ) information extraction and summarization o methods and techniques ( both statistics-based and linguistics-based ) o speech recognition and synthesis o multimedia communication , as well as language and speaker identification o evaluation and assessment techniques for each of these areas o government policy for future funding the initial findings of the report will form the basis of the discussion . the draft report is now available at http : / / www . cs . cmu . edu / ~ ref / mlim / major points raised in the discussions will be recorded and included in the report . we eagerly seek your feedback , comments , contributions , and assistance , to make this report as comprehensive and as accurate as possible ! program 9 : 00 - 9 : 10 welcome and overview 9 : 10 - 9 : 55 cross - lingual and cross - modal information retrieval moderator : judith klavans 9 : 55 - 10 : 40 information extraction and automated text summarization moderator : eduard hovy 10 : 40 - 11 : 00 break 11 : 00 - 11 : 45 methods and techniques moderator : nancy ide 11 : 45 - 12 : 30 machine translation of text and speech moderator : bente maegaard 12 : 30 - 2 : 00 lunch 2 : 00 - 2 : 45 multilingual resources moderator : martha palmer 2 : 45 - 3 : 30 speech recognition and synthesis moderator : tba 3 : 30 - 4 : 00 break 4 : 00 - 4 : 45 evaluation and assessment moderator : john white 4 : 45 - 5 : 30 multimedia communication and language / speaker identification moderator : oliviero stock 5 : 30 - 6 : 00 government : development policy and funding moderator : antonio zampolli the report the outcome of the granada and montreal workshops is a report , originally commissioned by the nsf , to be submitted to the nsf , le , and other funding agencies in europe and north america . the first draft of the report is available at http : / / www . cs . cmu . edu / ~ ref / mlim / we eagerly seek your feedback , comments , contributions , and assistance in making this report as comprehensive and as accurate as possible ! organizers robert frederking center for machine translation carnegie - mellon university schenley park pittsburgh , pa 15213-3890 tel : + 1-412 - 268-6656 fax : + 1-412 - 268-6298 email : ref @ nl . cs . cmu . edu eduard hovy information sciences institute of the university of southern california 4676 admiralty way marina del rey , ca 90292-6695 tel : + 1-310 - 822-1511 fax : + 1-310 - 823-6714 email : hovy @ isi . edu nancy ide department of computer science vassar college 124 raymond avenue poughkeepsie , ny 12604-0520 usa tel : + 1-914 - 437 5988 fax : + 1-914 - 437 7498 email : ide @ cs . vassar . edu joseph mariani limsi-cnrs bp 133 91403 orsay cedex france tel : + 33 - 1-69 - 85-8085 fax : + 33 - 1-69 - 85-8088 email : mariani @ limsi . fr antonio zampolli ilc-cnr via della faggiola 32 56100 pisa italy fax : + 39-50 - 556285 email : pisa @ ilc . pi . cnr . it - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - eduard hovy email : hovy @ isi . edu usc information sciences institute tel : 310-822 - 1511 ext 731 4676 admiralty way fax : 310-823 - 6714 marina del rey , ca 90292-6695 project homepage : http : / / www . isi . edu / natural-language / nlp-at - isi . html
