Automatic Detection of Discourse Structure by Checking Surface Information in Sentences

نویسندگان

  • Sadao Kurohashi
  • Makoto Nagao
چکیده

Ill this [)~/I)(?l" , WL' [)1'()])(1:-;4! ~lll ~lt l{ ,() l l l~l l i (! i i lO l ] l ( ) ( [ for det.octing disc.oiirse, s l r t l c l , l i r e IlSillgj ;i var iely of chics exisLhig in I.]ie surf;ice info lunal ion of ~>euten('es. ~,Jl/(? [lilVC cousi(ler(!(] l,[il'(!e Dyl)eb o1' (:hie illFOl'lllfll, iou: (;lil(? (~Xl)l'eS;y;ioIIS, occl i l ' r (~ l i ( : ( ) ()[' i(l(~lll, i ( ; ; i ] / s y l i O l l y l l i O i l S words/phra,~e,~, aii(] shuihwii.y I ) e l W ( ' ( ! u l~v(.)<~(uli(! i l(: /"~, l ' ]x lmr i l l ien ln l resull.q ]l;/ve ~,li()wu l l l ; l l , ill Ill<, (';iq(' c>[' scieui, ific and I.echliiC;/] lexL<,, ('on~i(Ior;ihl~' i larl ()[ Ill<, discol lrse S4(l'il(~l.lli'O Cilli I)() es l i l l la led I) 3 iu( 'or l )or ; t l iug > t.he i.hree I.yl)eS o[ clue i l l [ 'or i l ia l io l l , ~ i i l i ou i i)(,r['orui ing senleiicl~ i in(](u'slan(l ing I)i'(~ce~;se~ which re(liJirc's givi,g k n o w l e d g e I.o COl l i l ) t l l ( ! r~ i , 1 I n t r o d u c t i o n '1'o / l l l ( ]o . rs lJ i l l d i i ( ,ext o r dialogue, o u e I I I i l s l II'~/(:k. t i l e d i s ( ' . ( ) u r s e <'.4(;i'lilll;lll'(~ ( [ ) g ) , Sl)i!(:il')'iue , (h'lail<,d knowledge wil.h [)roatl coverage ava ih ih i l i l y Io coi l i ] ) i l l ers is unl ike ly I.o I)e. cousl, ru('.led [or l l le i)l'(!S(lll. Oil I l le ol.her hand, rec(,l i l ral)i(I ilicrt?;l:~e ill Ihe ;ll l lo~lnl o [ oul i l le l.exl.s has force(I ii~; Io ail;l177,e I1()1, (.)lily i<~oli/led S()II[,fHI(I()S ] ) i l l a l so ( l i s c o i i r s e s ll<4illl ,) ])1"1),4(7111 avai lable I~l~owle(Ige. \Ve i)i'ol~os(~ lu~l'e ~lli au lo lna t i c ulc~lh(~d 17)r (.<4{ilil;lli l lg [)P-; in s(: iei i l i f ic and te(' l i l i i ( 'nl I<'xls I) 3 , a v;u'iely o[ keys exisLin/+; iu lhe surface hif 'orl i l ; l l iOll o]' senleli('eq. ()li(! i inl)orl,ailt, key for I)S is cJue words (e.g., (Jo ]Jell 198,'1; (ir()sz and Si(li?er 1,9S($; l tei( 'hin; in 19<'45). I" i l r l . i ier inore, we have considere(I lwo ii1o1'(! il l l l)Oi'Lanl clues. ( ) l i e iS I.Im ()CCtll'r(~il(:(! o [ ic lel l l . ical l~Yn(mynlous wor(Is/phra. d ( i l i l i l l a l l L chnln i i lorLanl, con. s t i tueuis , like sq..3 and s,]-6 in Api~ei.lix. (JOIIILI'~I,NI; : S i aim Sj involw? c<.~ut, rastil~g events or !-;t~lt(!s, o r (:Ollll'~l~d.illg illll)ol'i.~tlll. (:oll.c,(,i[,llOlll,s. T,.:,pic c l i a i n i n g : Si and Sj haw~ dist, incL pre(lica I, ious ahouL Lhe sanle t, opic, like s I-13 am] s l i9 . Tol)iC-,.l,.mfimm.t: c h a h i h l g : A dolninanl> constii,ueuL al:,m'l f rom a giw~n tol)ic iN Si i)ecolnes a t, ol)ic in Sj, like s,] d ;m(] s,'t-5, I']hll)(:,raLion : Sj gives (let,ails ah, olfl; ;~ constiLueut intr,:)duced in S±, like s]-16 aud s1.17. lb:!a.s,.ni : Sj is Lhe reason for S:i., l i k e s l [ 3 and sl-.ld. C a n s e : .<-;j <:)c('urs as a result of Si , lil,:e sl..17 and sl 18, I A [ [)l'l!~,l!lit~ W(! reT, ard ;t NL'JI((!II((] IllD.l'J';f!d o f f ]Jy ~l i)(!l'iOd ,:is it disc~>tu'<.e uu i l , (Jt+lll!l'ellCl! rel ;dloi ls ;ire ex ls th ig also bel, ween cl;lll~;ey, iu tt sf ill#lllC(!, \~Ie I l ih lk lilll" al) ln'om:h ex ; i l i /h i i l lg stlrf~l.ce clue ] l l [)n'ulal i<ul fJt.ii IJ(! adapted Io exlra,.;[ Ihc i r I 'elations, ;t i id W() i l l l ( ! l l r l Io (?Nil!lid OIIl' $ysl(?l/I ill hlt l ld le ih(! l l l ,

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The Prosody of Discourse Structure and Content in the Production of Persian EFL Learners

The present research addressed the prosodic realization of global and local text structure and content in the spoken discourse data produced by Persian EFL learners. Two newspaper articles were analyzed using Rhetorical Structure Theory. Based on these analyses, the global structure in terms of hierarchical level, the local structure in terms of the relative importance of text segments and the ...

متن کامل

Using Machine Learning Algorithms for Automatic Cyber Bullying Detection in Arabic Social Media

Social media allows people interact to express their thoughts or feelings about different subjects. However, some of users may write offensive twits to other via social media which known as cyber bullying. Successful prevention depends on automatically detecting malicious messages. Automatic detection of bullying in the text of social media by analyzing the text "twits" via one of the machine l...

متن کامل

Automatic Pavement Crack Detection Based on Aerial Imagery

Road health information is an important indicator for assessing the status of the road in management systems. Identifying the abandonment of surfaces is an important process in maintaining roads and traffic safety, which is traditionally conducted on the basis of field surveys. Today, remote sensing methods, especially photogrammetric imaging, are presented. In this article, based on by UAVs im...

متن کامل

Automatic Discourse Segmentation using Neural Networks

In example (1), a sentence from a Wall Street Journal article taken from the Penn TreeBank corpus is further segmented into four EDUs, (1a), (1b), (1c) and (1d) (RST, 2002). Discourse segmentation, clearly, is not as easy as sentence boundary detection. The lack of consensus with regards to what constitutes an elementary discourse unit adds to the difficulty. Building a rule based discourse seg...

متن کامل

A survey on Automatic Text Summarization

Text summarization endeavors to produce a summary version of a text, while maintaining the original ideas. The textual content on the web, in particular, is growing at an exponential rate. The ability to decipher through such massive amount of data, in order to extract the useful information, is a major undertaking and requires an automatic mechanism to aid with the extant repository of informa...

متن کامل

Multilingual Annotation and Disambiguation of Discourse Connectives for Machine Translation

Many discourse connectives can signal several types of relations between sentences. Their automatic disambiguation, i.e. the labeling of the correct sense of each occurrence, is important for discourse parsing, but could also be helpful to machine translation. We describe new approaches for improving the accuracy of manual annotation of three discourse connectives (two English, one French) by u...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994