http://www.cs.cornell.edu/home/llee/emnlp/proceedings.html
EMNLP 2001
http://www.cs.cornell.edu/home/llee/emnlp/papers/schone.pdf	11	Is Knowledge-Free Induction of Multiword Unit Dictionary Headwords a Solved Problem?	accurate acquisition acronymfinder address algorithm algorithms already also american amount analysis angeles annual apparently application approaches april area aslin assoc association associations attempted automatic balancing based belgium bell best between boundaries brent brighton british bureau cambridge capture carg cartwright center chang chap chicago chinese choueka church classification cognition coincidence collection collections collocation collocational collocations combined combining communications compared compositionality compression computation computational computer conclusions concordances conference congress congressional constraints contextual conversational corpora corpus could croft cues current daille darpa database databases decide deerwester deliverable dependent development dias dice discourse dispersion distributed distributional document documentation does dumais dunning ecologic ecology effects effort either engineering entropy euralex eurospeech evaluations expansion expressions extensive extracting extraction fair fano ferreira filtering finch finding finite finke foltz fontenelle foslerlussier foundations francisco free from furnas future gains gale giuliano gold grams gregory guillor hanks harshman haystack headword headwords heid help hindle homogeneity hong however http ideal identification identifies ieee implementation improvements independent indexing induction infoplease information interesting international interpretation introduction issues itri jacquemin jansen jones journal jurafsky justeson katz kauffman kilgariff klavans knowledge kong laboratory laham landauer language languages large latent lattices learning lexical lexicography library liege like line linguistic linguistics lisbon little local locating looking lopes madrid manning manuscript march marcken massachusetts material mathematics maxima maximum mcnab measures mechanism mechanized meeting memory method methods metrics mikheev miller miscellaneous mlap mode model modeling models more morgan morphology much multi multiword mutual nagata national natural need needed needles networks neural newport normalization norms noted noun obtain obtained occurrences onelook order oriental oxford paper parallel part particularly pereira perform phonotactic ponte predicateargument predictability press proc procedure proceedings processes processing production project pronunciation properties proposed provide provision publication publishers raymond realization recognition record references regardless regularity report representations required research resnik resources results retargetable retrieval retrieving riao rigid rijsbergen role rose safely saffran schone science scores searches seem segmentation selectional semantic several shih shimohata silva similar similarity sixth smadja small society some somewhat sparck speaking species speech sproat standard standards state statistical statistics stevens still stochastic strength structures study substitutivity sugio surprise survey symbolic symposium syntactic syntax tagging taln teahan tech technical techniques terminology terms text textual that them theoretic this thomas those thus times together tools transmission tutorial tzoukermann units univ university unrestricted unsupervised useful useg using vanallemeersch vocabulary ways webbased weibel which with witten word wordnet words work wvlc xtract yingyin ziff
http://www.cs.cornell.edu/home/llee/emnlp/papers/evenzo~1.pdf	1	A Sequential Model for Multi-Class Classification	academic accent acquisition addressed advances allwein although ambiguities ambiguity among annual answering application approach arti attachment automatic bakiri based bayesian binary boston brill candidates capable case cation ceedings charniak choose chunk church cial class classi clustering codes coling college computational computer computers conclusion conference conll context continuous contrastive cooccurrence corpora corpus correcting correction could coupling cvpr cybernetics daelemans dagan database decision deletions deriving dermatas developing dietterich digit disambiguating distributional divergence dokl driven each edition editors error even experts extracts features french from gale gcnu general generatingfunctionology golding guessing hand handwritten hastie have high hinton humanities hybrid identi ieee immediate induction inductive inference information insertions instantiation intelligence international issue joint jordan journal july kasif kearns kokkinakis kudoh landgrebe language large learning level levenshtein levinson lexical linear linearly linguistic linguistics lisbon lists ljolje logic london machine machines madrid mangu margin matsumoto mcgrawhill measure meeting memory method methodology michael mikheev miller minimizing mitchell model models mooney multi multiclass murthy naalp national natural nearest neighbors network neural nips novel number oblique only order original output pages pairwise paper paradigm parse part pattern pereira perform phonetic phys prediction press probabilities problem problems proc proceedings processing products programming protugal punyakanok queries question range rasoul real recognition reducing references relevant report research resolution resolve resolving restoration reversals roth rule salzberg sara schapire second senses sensitive separable separators sequential similarity similaritybased singer small solla solving spain spanish special speech spelling statistical stochastic study such support survey system systems tagging task tasks technical teow texts that this tibshirani training transactions transcription transformation translation tree trees unifying university unknown used using vector veenstra very vision volume wide wilf will winnow with word workshop yarowsky zavrel zelenko zelle zohar
http://www.cs.cornell.edu/home/llee/emnlp/papers/rosario.pdf	9	Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy	aaai abduction academic acta agentivity algorithm ambiguity american analysis anick appelt applications applied approach approaches arti assessing asso assocation association attachment australian automatic automatically barnett based beatrice bergler biocomputing biomedical brill cabulary cardie case causatives center cessing chicago christiane cial ciation ciency ciety claire class cognitive coling collaboration columbus communications complex compound compounds computational conceptual conference corpora corpus creation csli current cutting database decem development disambiguating disamibuation disease dissertation donald douglas douglass downing dras drugs dynamics editor editors eighth electronic ellen empirical english eric esch extraction fellbaum finin force frames from generalizing generating genes gothoburgensis groupings hang headings hearst henry hindle hobbs humphreys hunter hwee hybrid illinois informatics information innovative institute intel interpreta interpretation ircs italy jacobs jama james ject jerry john joint journal judith julian june kupiec language lapata large lauer lawrence learning lecture levi lexical liberman ligence ligent lindberg linguistic linguistics literature lorraine lowe lucy magazine magnesium maria mark marti martin mats matters medical meet meeting menlo mesh metho naoki national natural neurologic neuroscience nominalizations nominals notes noun nounnoun nouns octo olman oxford paci pages parasession park partof patterns paul pedersen penelope pennsylvania perform peter philip phrase phrases practical prepositional press principle probabilistic proceedings processing pustejovsky references regional relations relationships report research resnik respect restricted retrieval richard rilo rind rule sabine scho science searches selection semantic semantics senses sequences sibun smalheiser speech sproat statistical statistics stickel stress structual structural structure swanson symposium syntax system systems szabolsci tagger talmy tanabe techniques text theory thesaurus thesis third thirteenth thomas thought timothy tion trento understanding universitatis university untagged urbana using vanderwende vapnik very warren weinstein with wordnet workshop york zelle
http://www.cs.cornell.edu/home/llee/emnlp/papers/uchimoto.pdf	10	The Unknown Word Problem: a Morphological Analysis of Japanese Using Maximum Entropy Aided by a Dictionary	acquired adam adwait akira algorithm analysis analyzer annual applied approach association automatically backward based berck berger best black brill building case chapter clustering coling combination computational conference context corpora corpus cutting daelemans data decision della department dependency dictionary distributional doung driven eacl empirical entropy eric error errordriven estimation eubank european extraction ezra feature flexiia forward from generator gills halteren hans haruno helmut hideki hierarchical hinrich hitoshi improvement improving informatics information international isahara jakub japan japanese journal julian juman kashioka kitauchi kiyotaka koichi kupiec kurohashi kyoto language large learning linguistics makoto markov masaaki masahiko matsumoto maximum meeting memory method methods mistake mixture model models mori morpheme morphological morphology nagao nagata natural networks neural ninth paci padr pages parameter parsed parsing part partof pedersen penelope peter pietra practical probabilistic proceedings processing ratnaparkhi references rquez sadao satoshi schmid schutze search sekine selection shinsuke sibun singer society speech statistical stephen steven stochastic structure study symposium system tagger tagging takehito takeuchi third transactions transformation tree trees uchimoto university unknown using utsuro variable version very vincent walter while with without word wordclass words workshop yoram yuji zavrel