File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/94/c94-1005_metho.xml
Size: 25,356 bytes
Last Modified: 2025-10-06 14:13:34
<?xml version="1.0" standalone="yes"?> <Paper uid="C94-1005"> <Title>Towards Machine \]ranslal; on U. inf C, onC(,xt, m,1 hfforma,tion</Title> <Section position="3" start_page="0" end_page="57" type="metho"> <SectionTitle> 3 The MT System </SectionTitle> <Paragraph position="0"> The transhd, km system present,ed here is ;t model systent whidl is being used to investigai, e t, he techniques proposed. The translation Imr~ is carried out h, Pl{.O1,0(\] usinp; nn l,FC-LIike gramma.tieal formalism 2.</Paragraph> <Paragraph position="1"> '\]'he current, dictionaries conl,~dn information to translal.e aboul; 300 words. There are 350 grammar rules which (:own' a wide range of sentence pal,terns.</Paragraph> <Paragraph position="2"> The context monil,or operates using information retrieved from file f-sLrueturc of ;t SOlli.eltCe al't(W analysis. This ilfforlnal.ion is then used during the transfer 2'\['\[le cn'igimd lm,gl.anl for l;;hgllnh-Spanlsh iranslallcm deveh,p,,d I,y (1, Amm'es \[:\m, wes'89\] has been widely adapted and eldal'ged Io .I-I'; & E-J Iranslallon.</Paragraph> <Paragraph position="3"> of tile source f~structure to the target f-structure. As context processing is carried out on only a shallow level, only information for lexical item, nurnber, person, gender, case role etc is used in the context system, along with semantic inIi)rtnation from the semantic network. The way that this information is used will be explained below in regard to the specific problems that tile use of context is intended to resolw~.</Paragraph> </Section> <Section position="4" start_page="57" end_page="57" type="metho"> <SectionTitle> 4 The Context Monitor </SectionTitle> <Paragraph position="0"> The context monitor proposed in this pal)er uses a standard focussing theory as a basis (\[Sidner 81\]),\[Sid,ler 8(i\]), amlough sonrexvhat simplified according to the bes* :press approach that we are adopting. It is planned to increase the COml~lexily of this initial algorithm to reflect more current wn'sions of the theory as the system is developed.</Paragraph> <Paragraph position="1"> The context monitor has a number of basic data structures: Current l;k)cus, Actor l'~oeus, Potential l,'o null cus List, Potential Actor I;'ocus List, Discourse Segment Stack and Actor I:ocus Stack. There is also a Current State List that maintains a record of all the semantic items currently hehl in any of the other data structures and the semantic features to whMl they are linked. This list is updated (entries added :rod removed) after every sentence.</Paragraph> <Paragraph position="2"> In ordc'r to lilnlt the scope of the context information required in the context monitor, an analysis was made of the main differences between 3apanese aml English that provide problenas for MT syst.ems. The basis of the analysis was to find what information can be gained from context to solve these problems.</Paragraph> <Section position="1" start_page="57" end_page="57" type="sub_section"> <SectionTitle> 4.1 Plural Fomns </SectionTitle> <Paragraph position="0"> Japanese is (in general a) mmlarkc'd for mlmber. I';nglish, however, differentiates between singular and plural, q'his fact causes problems when translating tY=om Japanese to English as the mlmber information required for the inflection and declension of English is not available from the analysis of the 3apanese. I:or example: (I,oy(s),,,~, dog(s)o,,s lille) The boy likes th.e do~j.</Paragraph> <Paragraph position="1"> The bo W like the cloy.</Paragraph> <Paragraph position="2"> The boy likes Zhe dolls.</Paragraph> <Paragraph position="3"> The bow like Hie do!Is.</Paragraph> <Paragraph position="4"> Bogs like doas.</Paragraph> <Paragraph position="5"> In the current system an initial sellt.ence analyzed by the system is processed to find possible: ff)ci. II,ents which are in the l)lural or are in conjunction are stored as a set. 'Che set as a whole is given phlral nultll)er, aNote the use of .t'~ ('l(tchi') with mainly people and anlm.ls, but consists of imlividual items or, as} in the case of &quot;/we ~e,v 7'V models and fo~tr 7~ew video models&quot;, as subsets. Subsets or individual items within the sets are available as antecedents to subsequ.etlt referring expressiolls.</Paragraph> <Paragraph position="6"> '\]_'hus, in the example text. in Section 1, after the initial sentence is analysed, the proposed focus is two new TV models and fmtr new video models, the strut.lure o\[&quot; which is shown in Figure 3 below: 4</Paragraph> <Paragraph position="8"> mod:\[pred:kishu(model), SlmC :\[pred : yo,,(fiJwl 9, -.\]\]\], rcf:set3\], ,'of:set 1\] l:igure 3: PIi.Of, OG Structure Sentence 2 (S?) is analysed and a test is made to see if any items in that sentence confirm or reject the proposed focus. 'l'he structure for the item g'7&quot;~ (&quot;a video/videos&quot;) is matched by mfiIication with the structure for the prol)osed focus and can Im matched with a subset of it., namely ~)i k. v,/2&quot;-)~ ~ - IJtl,~K~{\[( (&quot;d new video models&quot;). That item is there.fore taken Io conllrm the proposed R)t:us.</Paragraph> <Paragraph position="9"> That proposed I'oeus is, however, hnmedhttely PUSlled onto the focus stack because the subset of 4 vhleos is taken as the current \['ocus 5. 'Phe item 13-)~&quot;;t of $2 inherits the feal.tlrcs of the set. of videos fronl S I. aml is therefore expressed ill the I(nglish with a plural form: &quot;videos&quot;. It is hoped that in this way the conl ext monitor will be able to distinguish between singular alld plural in at least some cases.</Paragraph> <Paragraph position="10"> II/ sonic cases t, here is Iio way of disl.inlguishing between singular and l/lural rei~renee in .Japanese as in tile case o\[&quot; the sel/tellce below: &quot;/'eve (~)1C/1 llm~al,:o bO,:lht a ca\]w.. 7'l.~ey ale it &quot;i~ lhe park.</Paragraph> <Paragraph position="11"> Taro aT*d lf m*ako I)o,:lht (some) ('ak(~s. The?/ ate them il~ the park.</Paragraph> <Paragraph position="12"> 'tln a shnplilied fi-wm, showing relevant delal\] only. Italics &l'e tl'&llSl&liOIIS for exl)lanation only and do not, appear in the s\[ t'llC\[ u l'e |)l'Ol)el' 5q'he syslem currmllly deals only with local foe.us - there is no account (if gl.ba\] focus Ill stleh cases L\]le e()llLexID lllOIiil,of Cal\]liO~, resolve slnguhlr or t;lural and so the MT system del'a/llt> will be relied on. l\[owever, l.ll~ conLexL nlo~lit,or at. leasL allows 15r coherence with Sll\])Se(\]tlelllL, \]srollOllllS.</Paragraph> </Section> <Section position="2" start_page="57" end_page="57" type="sub_section"> <SectionTitle> 4.2 Translation of Pronouns </SectionTitle> <Paragraph position="0"> .Jl_tplineso make,q llltich /1se oF l.he zero I)l'OllOlll/ (marked hero by &quot;O&quot;), especially in 1.1w sulLiecl, posil;ion, bu~ equa\]ly for other roles. I.'or exalIiple: (~ C/ lIIOIl tabeLc shillla\[l.a) (O~,d,j Oot, j ah'eady eel A UX\] \[ U) haw al,'e,,,O e<a,,,, (i 0 (:rh~,:D h<,~,~, ,~,'~,,,,0 ~<a,,,, (~/,,:,,,) (H<) h<,, ,~,'<<,<0 e<a~,, (~h,<,,,) This illelitllS that. i,hore is no illfornlal.ioli availahh, frolll l, he single, sellLellee Lo aid the choice c.\[ eq/iiva\]0iil. I'\]ii glish \]H'OllOllll (which i\]lllSl, iI()l'lli;ll\]}, l;l! I!xprl'ssed). As showll ill 2 and \[I o\[' t, lm exalnl)lC Lexl, in I&quot;ig;m'e 1, M'F systelns use a, nullllmr o\[ niol.hods I()add all ovi,rt. l)roliOllii> of ),on involviug I, hc' riser in l.he Iili;tl choice. IL is claimed t>hat, if Lherc is a l)roliOtlli in ~ Selitellce> it; ll\]llS~ re\[er Lo tile foells of that l, exL se~lllelll, (ill or(lor 1,o continue, the current segment) and it' there are more IL\]I~II/ ()lie prOllOllllS, ~l{, letlsID one ()f t.helll IlltlSi, re\[or Io t, he focus. By tol.3Ckillg l,hC/~ fOellS of H t,ext~ Seglllel/l,, 0 |srollOllllS ill .\]~'/\])illlese, shollld he able (,(; he rescflved so LhaL il~li approl)riaLe overl, pl'oliOilli in ll;ll/.,;\]i~;ll ceil be selected for Lhe Lranslal, ion.</Paragraph> <Paragraph position="1"> '~V\]ieii a zero pl'Ol/OUIi iS deLect.ed iii a Seli(,l!ll(:c, il'ali aliLecedent, Call \])o foun(\] for ii., al/d L\]lal, ;liil.ect!(\]ellL is a, seL of it.eHis~ the= ov(~rt, l)roiiouu inslu'tc(I ill Ihe \];',ngllsh will I)e plural.</Paragraph> <Paragraph position="2"> Thus in '1 of/.he exainple from Figure 2, we soc thai, l.he zero pi'OliOtlll in &quot; 0~,d,j <~: ~(~) j{t ~ \[/l~TL/.: &quot; is alia\].. ysed as ref0rring Lo Lhe D.vo video models released au(\] is L\]ierefore Ll'~tlISIaLed wiLh ;t plur;d \])r(lll()till: &quot;7'\]tC:\] sohl verT! wel?'.</Paragraph> <Paragraph position="3"> Noi, e, howew;r, thai. t.here is allil)i<,,;uily hi ,%'iilellce 3 t)el.wcen whei, her l.he Zei'o I)rc, llOUli ill O \[.\[~{~.~/l(~<~; J C ~'.'~5'd L./.: (0 released t~vo models .,sl,'aigDI a,,ay) r0fers t,o Lhe Chief l)ew~'\]opinenf.. FAlgiIicer or l}ie Sales ~ecLion.</Paragraph> <Paragraph position="4"> \'Vheli faeed wil.h anl\])iguil.y SllC\]l i/s l.\]iis> l;u'g<!~sc;i\]e a, LLenipLs aL coid.ext, undersl.anding lnig, hl. use in(t!)'ellCC plans LO solve Lhe aill\];igtlil.y. \[Iowever, 1)OC,:tlISO of )>he lhniLat.ions of a Slii:,l\]l size MT sy~;lelu allcl i.h(~ feel Lhal, eveil \[al't~e s(;ale deep level seniaul, ic l)ro('essing has noL heeli saLisfaetorily realised lksr linlilniLed donlains (wit,h which our lkl'l' syst.eui is in)elided 1,() work), we decided t.o atteilllst liuiit~d infereileillg hy the addil.ion of sortie features aim links I.(5 i.he selllmi-.</Paragraph> <Paragraph position="5"> Lic network oft.he MT sysl.eln. The hff~,'encing ahle Lo be lmrfornio(\] I)y such a niei.ho(l is quite simple> \])til.</Paragraph> <Paragraph position="6"> is hoped 1.o I)e suflicienl, for our nee@ in accordaliee wiLh l, he besl guess policy.</Paragraph> </Section> <Section position="3" start_page="57" end_page="57" type="sub_section"> <SectionTitle> 4.3 Selilani.ic Networks </SectionTitle> <Paragraph position="0"> ~emantic networks are has)tally a hierarchy of con..</Paragraph> <Paragraph position="1"> cept.s which are linked t,o one alloi, her in a neLx(,orl< t, ype sLrllcL/ll'e. ~elH311|,ic Ilet, works were ilfl,rochlced by Quilliau in 19\[i8 \[QuilliaN (ill\] am1 were wldely us~d in aLl.empt.s aL l(uowledge Ilasod ~ys\[elllS, imrticu larly dm'iltg the l;ll.e 1980s.</Paragraph> <Paragraph position="2"> As all ex:uuple o(' suc\]l a system leL us hriei<ly consider I.he syM.elll I'or Japanese-l&quot;.nglish tl'ausla-I.ion using couLexl.ual iuh:~rnulLion prol~osed hy I1. isahara aml S. Ishizaki (\[lsaha,.a 86\], \[lsahara 87\], \[lshizaki 89\] and \[\[sahara 90\]) as oue l(nowledge llased apl~roach aml compare it, to the Lechniques used in i, he system proposed in I, he curreni, paper.</Paragraph> <Paragraph position="3"> The l,ranslaLion sysi,eln CON'I'll, AST tr;mshlt,ed ,lal~;mese m~wspaper ari,icles into EnglMl. llowew~r, a major di/l',,rence r~gardiug our syst~ln is I, hat con.</Paragraph> <Paragraph position="4"> lext, umh'rsl.al.ling illvolv~,d analysing a sent,ence A (,'r; with au (~vort, ~.\]h\],,ct) and a s,~m,em',, I~ (,~g wilh a ~:ov,.rl sul>.i,<'t) ;rod thel, mal,&i.g I, hese SellHmc~s againM, ;~ immbcr o\[ Selll,l!llCe \])al,l,el'llS. \[\[&quot; i~ llla\[,c\]l was I'omid Lllese would form a l,(~xl, paLLern C, wit.h A aud B as sulfl)arl.s. The snhject of A would he used (if slfil,able) 1o provide the subject lbr IL By adding I\[ei'liS, ),he syslelll will t?dl. Oiir sysl.elil is inLended for lllore gell01.;l\] l/lllgjlla<t./,/tilt\] as We CallllOl. predicL Lhe lenglh of a I.exl: or whal. kinds of selil.0lico will occur v.'illliu I}lat. (exL, (.he (;oniexl. Monil.or lsrovi(Ies o11.. <u;oing; colilcxl.ua\] analysis wiihouL F, rel)resllliiill<t.~ tim lellgLh or nat.ure of l.he l.e.xl,.</Paragraph> <Paragraph position="6"> alld evelllS referred 1.o ill t.\]m i,exl, al'(~ ~/liaiysed and IIl~lde avail;ihle t.o i'esolw, ~ SllllSeqllelll, analysis prol)\[elliS. The t.raliSi;iLion i'OlHaiilS Sellt.eilce \])y SOllt.CliCC~ all.hough tile ~,elier;ll coliLexl, of Lhe Lext. is lllOllil.ored.</Paragraph> <Paragraph position="7"> Fiually, ~oinaiit.ic. Nei,worles, sucli as I.hal. l)rOl)osed by lsahiir;i eL el., )ire sl, al.ie n()Lworks. The links do lioi, chalice I)cq',veen nodes. The possibh~ pal, hs Lhal.</Paragraph> <Paragraph position="8"> are av;iihll)le l.hrough I.he nel.work lilay (!hal)g0 hut Lile links l.helilselves do ilOL challge, hi olir syst.el~u, t.he</Paragraph> <Paragraph position="10"> network and these links can change dynamically in respect to the specific objects and colicepts referred to in thc text. This provides a powerflil augnlentation to the basic nctwork.</Paragraph> </Section> <Section position="4" start_page="57" end_page="57" type="sub_section"> <SectionTitle> 4,4 The Augmented Semantic Net- </SectionTitle> <Paragraph position="0"> work Tile semantic network in this system is basically a hierarchy of Objects, States and Events. The addition of features to the semantic network in effect adds links to the network. Two kinds of link are proposed: permanent links and temporary links. Permanent' links are conditions that must be true for a certain action or state-of-affairs to bold. The other, temporary, links are used to create a default state for the objects mentioned in the text. As the text is processed, these links may change, so that the information awtilable to the system will differ from one sentence to the next.</Paragraph> <Paragraph position="1"> The division between Objects, States and Events is reflected in tlle type of feature given to semantic itclnS. For exainple, Events typically coilgain features about the sort of things that are affected by that event; States contain information the types of objects that may be in that state; Objects contain iilforlnaiiou about any subparts or if they themselves are typically part of another (larger) object and wliat type of Event they are typically involved in.</Paragraph> <Paragraph position="2"> On this basis, the following types of link are proposed: null . Condition (=c): (permanent) a condition that must |lold for a State or Event to come about.</Paragraph> <Paragraph position="3"> , Before Condition (BC::): (pernianeut) a condition that must be trlie before an Event or State conies about.</Paragraph> <Paragraph position="4"> * After Condition (AC::): (permanent) a co,ldition that becomes trtie after an Event or State comes about.</Paragraph> <Paragraph position="5"> * Has Subpart (l,as): (tenlporary) an Object lias re-lated subparts or is a subpart of another Object. * Characteristic (has Semautic.Label): (I.emliorary) an Object has the characteristic of Senmntie_Lal)el (usually an Abstract_Relation: Size, Shape Colour etc.). This takes the form of: &quot;lteni has Senlautie_Label&quot;, such as &quot;Pelerhas Existel,ee Lif~span&quot;. Tiffs states that an item witll tile semantic item Peter has an existence of some kind and filrther locates tllat itenl on a path of the network to the abstract relation of lAfespan. Iu this way, nodes between these two points are all available for reference by the inference system.</Paragraph> <Paragraph position="6"> . Ability (able_to): (temporary) This is not fully defined in tim current systenl but represents characteristic features of items e.g. &quot;dooF' often appears in the tlleme position of tile Events Open aud ,O'hll\[.</Paragraph> <Paragraph position="7"> These liuks are considered sutllcient for tile current capabilities of the system. I,inks may be deleted or others added as the range of the sytem widens, if this is tllought necessary or desirable.</Paragraph> <Paragraph position="8"> The dlfference between perrnallent and I;enll)orary links is iu the nature of the iuformation that they convey. Permauent links are those that are augmented to tile lletwork and COlllleCt uodes cue I,o tile other in accordance with the features found in those nodes. ~Bef(~re Condition and Aries&quot; Condition links are permanent, although the hiformation contaiued in the uodes that, t.hey connect to will only become awdlable to the context nlonitor iu accordance with the tense al/d aspect of the verb (i.e.. all After Condilion is obviously only valid crier the completion of the (for exalnplc) action denoted by a verb has finished. Teniporary liuks are those that supply default illforfllation to the COlltext Il~Ollitor coucerning nodes that it is COliCerlied wii.h. 'Fhus, for exaluF, le > an entry for a bird iuight state that it is Able_To Fly. llowever, if the input text were to state that a particular bird is unable to fly, that A1Ao &quot;l'o link would be cancelled. Thus tolllporary links provide the iliforulatioil that the colitext nlonitor rises> using the teinporary links to spread throughoilt the network (within set search constraints) aild gat.hering inPoruiatioii that Call lie used for infcreilcing.</Paragraph> <Paragraph position="9"> All exalllple Of the features used to a/l~_~Illent tile seniantic network can be <tivoli tlsiilg the exalrll)le: Peler heard that ,\]olui had died. lie was very ::3 a d, (-liven the dict, ionary entry shown (here sirnplified) I)elow, &quot;l'clcF' will lie analysed as a male proper 11OI111, dic(n ,'l>eter',\[selu f'eat:\[hmnali:yes\], i)n'opcr:yes, L~t~\]) d (!r :lu as(', I l)r&quot;d:peter\]).</Paragraph> <Paragraph position="10"> When the enibedded clause is analysed, &quot;Jolin&quot; will be analysed in a similar way. The semantic feature human:yes locates these l, wo lexical items as subsurned by the semantic feature &quot;Living&quot; in the network. Augmerited Featin'es Ibr a mah; bureau such as the objects relZ'rred to by the nanles Pcler aud Jolin are shown below in Figure d below along with possible entries for the l,\]w!nt die and the St~te be sad, It ca,l be seen that one of the Before Conditions o\[' the I'\]wmt Die is I,hat the actor role is filled by all il, em I;hat has the seilialllic feature &quot;Living&quot;. The del'ault asstllUl'd, iou for &quot;JoDll&quot; is thai. lie is I\[llman and therefore l,iving, llowever, the After (\]ontliLiol;s of the Event Die cancel the feature laving lil connection with &quot;John&quot; ('~o1' means that a \[?ature aml all tile other features underneath it in the tree should not be reachable by that item), and state, that the item should be associated with the fimture &quot;Corpse&quot; (a semantic label in the system for something that was living but is no longer). Thus the semantic item &quot;John&quot; is first linked with the semantic feature &quot;lluman&quot; and all the other featm'es inherited from that feature. However, the features associated with the semantic item &quot;Die&quot; cause the links associated with &quot;John&quot; to change. This means that when tile seeend sentence is analysed, the possilfle candidates f()r the exl)erieneer role of the semantic item &quot;lhLSa(f' are analysed, an itmn with the semantic feature &quot;Allinmte&quot; will be sought, and so the item &quot;,/ok.&quot; will not be considered in the. search as it is no long,-r on a path reachable hy &quot;Animate.&quot;. &quot;Pete/' is therefore the only possible antecedent.</Paragraph> </Section> </Section> <Section position="5" start_page="57" end_page="57" type="metho"> <SectionTitle> 4.~ Articles </SectionTitle> <Paragraph position="0"> Japanese does not use de.finite and indefinite artides and so when there is no ow.'rt determiner in the aal)anese, one must be supplied for the English translation. For example, Sentence 2 of ore&quot; example text: 155&quot; M&quot; 1:111~3E l~ll V- ~l~',Ij: U/:: ,, They passed the videos to the Sales ,qeetion.</Paragraph> <Paragraph position="1"> Where a simple default rule is used for articles, ibis eouhl equally be machine translated as: I\]te 9 llaSsed videos to the Sales Division ~, where it can be co.sidered that some of the sense of the original seuteuce is lost.</Paragraph> <Paragraph position="2"> While the use of contextual informatDm canl~.t solve all of the prolflems of art.Mes, it is hoped that at least in some eases incorrect possil)ililies (:;m I)e eliminated (following tile &quot;l>est guess&quot; policy). I1, lhe cases that the context monitor cannot decide, an article, the MT system default will be re.lied upon.</Paragraph> <Paragraph position="3"> % decide between a definite and indefinite article in \]'~nglish, a simple rule of thumb in the present system is that once an object has been specified in a coiitexL, 6ttSstlnlillg that the noun is defined as phu'al l)y sonic (~lher process, oLherwlse a vtdeo is als~ a l)osslbilily ;ill subsequent references to that parLichh~r object in the saine context will be definite r.</Paragraph> <Paragraph position="4"> In the method proposed here, as objects are analysed, they are giwm a unique reference number (re*) that separates them l'ron~ all other objects of file same type. Thus, the first time that an object is analysed, it will be nLade indefinite, unless the reference can l)e analysed as being ;t generic one (e.g. The lio~ is a da~lerous animal et(:).</Paragraph> <Paragraph position="5"> l&quot;rom then on, if an item ill the text can be linked to an il.em which is the current focus, a potential focus or an i(.em on the focus stack, it will l)e made definite i. the English tr;mslation. Therefore, the two video models of Sentence 3 are recognised as a sul)set of the four videos that Form the focus and are. given the (lefild/.e article.</Paragraph> <Paragraph position="6"> Note also that as subparts of objects are inch|ded in the features attached to selllantic items using the has feature, objects related to an item already ment.ioned call also be treated to solne extent and translated with deft. ite a,'tich.'s: llannkr) bought a new video. She I.ook it back l.o the she 1) as II~c gape. head was damaged.</Paragraph> <Paragraph position="7"> This, howew% a very simple apl)|'oach nnd cannot accounl. \['or :Ill possibh', uses of the definite/ indefinil.e articles, lh)wevm', the appro;u:h outlined above also t~llows the &quot;besl ~j,rss&quot; strategy; where, this strate.gy fails the nornml (h:l'ault rules of the translation system Lake over.</Paragraph> <Paragraph position="8"> 4.6 Restrictions on the Repetition of&quot; \])roltouns In l';nglish, ov,'rt pronouns are repeatabh~ and in sonic cases obligatory in a sentence to preserve meaning. In ,\]~ll'*g/llege ,however) overt pl'()tlOllllS arc llot repe~/tal)le as shown ill the i)elow s.</Paragraph> <Paragraph position="9"> lie dtx'.s his work when Jig wanls to.</Paragraph> <Paragraph position="10"> (he ,...;~ he..a.iwanls to when his worko~jdoes ) himself ~ ~)~':{J: (b I.k:v, L- ~N ~,:-_ I;I,@a)41:T\]!:@- -~.7., his nwn It is; t.herc:foro. ,Jesh':fl)h'~ t.o have a routine in an MT system to rel~lace ow.'rt pronouns in English with 0 or I'l~a v ('jib,.' oneself) in Japanese. In this case., the use o1' the p,'onomt lie in English will he analysed and recognised as rel>rring to the same person using r'rhls basic i)rlnclpll! is, supple~nent.ed I)y rules based on syn{;ic\[ic i;OllS( i'llcLithllS t!{c a'l'his exal,q)le I;tken frt,.n \[\Vada 90\] the processes outlined above. Separate rnles concerning co-oecnrrenee of pronouns can then be used to substitutc C/ or \[~I~,\]&quot; ('jibun' himself) in t.he Japanese translation.</Paragraph> </Section> <Section position="6" start_page="57" end_page="57" type="metho"> <SectionTitle> 5 Limitations g~ Problems </SectionTitle> <Paragraph position="0"> As shown above, the inferencing carried out is very simple. It depends entirely on the links between nodes of the network and there is an obvious limit as to how complicated those links may I)eeome before the processing required to search all t,he nodes linked to a particular item becomes prohibitiw~'. At, the current, stage of planning, a strnctnre (a semantic il.eni) may be linked to another via one node (constrained l o be an Abstract It.elation). There are no current plans I.o increase the number of such linking nodes.</Paragraph> <Paragraph position="1"> The inference mechanism is also expected to perform poorly where actions denoted by a wn'b are COlllplex. This is due to the very simple feature descriptions that we use in the systenl. It might therefore be desirable that, if the processing is not ccmlpleted within, for example, a constrained time, the process be terminated and the context moiiit,or left to rely on semantic feature matching alone.</Paragraph> <Paragraph position="2"> Another major problem is writing the features for the links in the network. At the moment, all features are written by hand, })tit, it is hoped that sinlilar information might be extracted from semantic and casefi'ame dictionaries.</Paragraph> <Paragraph position="3"> The context monitor is currently written in PII0-LOG 9. The program eui'rently consists of several hundred lines of PROLOG.</Paragraph> </Section> class="xml-element"></Paper>