Abstract. We are going to present an architecture for natural language processing sys-tems especially designed for spontaneous speech. We introduce the notion of a layered chart for information separation and information hiding. Complex distributed systems can be built using this approach which do not rely on a central data structure or control model. We describe a typed feature formalism with appropriateness suitable for such sys-tems by providing a compact and relocatable storage schema for feature structures. We set out an architecture for spontaneous speech translation that relies on partial parsing to minimize complex operations at an early syntactic stage, but rather carries out ut-terance integration after building up small scale syntactic objects. We adopt the notion of a variable depth of analysis by providing a module specialized to the translation of idioms and show how an global scoring schema for sub-paths in graphs can be used to block further operation on idioms already accounted for. 1

Larr vocabular y continuous speech reech ition can benefitfre an e#cient data strR turfor rrR/sentingalarE number of acoustic hypotheses compactly. Wor gr1:1 or lattices have been chosen as such an e#cientinter face between acousticroust ition engines and subsequent languageprguag ing modules. This paper firR investigates the e#ect ofprEI/-- dur ing acoustic decoding on the quality ofwor lattices and shows that by combiningdi#erEE pre ing options (at the model level and wor level), we can obtain wor lattices withcompar bleaccurE/ to theorRE/ al lattices and a manageable size. In orer to use the wor lattices as the inputfor a post-prt-RI ing language module, they shouldprx--:/1 thetar/E hypotheses andtheir scor while being as small as possible. In this paper weintr oduce awor grC comprmpR/-- algor thm that significantlyrnt ces the number ofwor-- in thegrRxEE alrRx---- entation without eliminatingutter ance hypothesesor distortRI their acousticscort . Wecompar this wor grR comprCx/)R algor thm withsever lother latticesize-rRI cing appr aches and demon strnR thereRx1C-- strx gth of the new wor gr1/ comprw sionalgor:I+ for decr: ing the number ofworC in thereR/) entation. ExperR entsar conductedacrRI corRI/ and vocabular sizes todeterE/R the consistency of theprR/--) and comprC sionrnRIIC) # 2003 Elsevier Science Ltd. AllrlRI srEIE ved. 1.I5k4 Wor latticesar often chosen as theinter/C1 between an acousticrusticRx-- and a subsequent prubsequ using amor complex language model (LM)or mor specific acoustic model because of www.elsevierw.elsevi te/csl COMPUTER SPEECH AND LANGUAGE * Corr)R)R)Rr author Tel.: +1-765-494-3652; fax: +1-765-494-3371. E-mailaddr9(--)b harRxC/1:Rwxxx/Rrx+ yangl@ecn.purxxx/Rr (M.P.Har.RIC mike.johnson@marrx+Rwxx (M.T. Johnson),lhj@ecn.pur)xRwEE...