ABSTRACT GENERATION 
BASED ON 
RHETORICAL STRUCTURE EXTRACTION 
Kenjl Ono, Kazuo Sumlta, Seijl Miike 
Research and Development Center 
Toshiba Corporation 
Komukai-Toshiba-cho 1, Saiwai-ku, Kawmsaki, 210, Japan 
ono@isl.rdc.toshiba.co.jp 
1 ABSTRACT 
We have developed an automatic abstr~mt genera- 
tion system for Japanese expository writings based 
on rhetorical structure extraction. The system first 
extracts the rhetorical structure, the compound of 
the rhetorical relations between sentences, and then 
cuts out less important parts in the extracted struc- 
ture to generate an abstract of the desired length. 
Evaluation of the generated abstract showed that it 
contains at maximum 74% of the most important 
sentences of the original text. The system is now 
utilized as a text browser for a prototypicaI interac- 
tive document retrieval system. 
2 INTRODUCTION 
Abstract generation is, like Machine Translation, one 
of the ultimate goal of Natural Language Process- 
ing. IIowever, since conventional word-frequency- 
based abstract generation systems(e.g. \[Kuhn 58\]) 
are lacking in inter-sentential or discourse-structural 
analysis, they are liable to generate incoherent ab- 
stracts. On the other hand, conventional knowl- 
edge or script-based abstract generation systems(e.g. 
\[behnert 801, \[Fum 86\]), owe their success to the li,n- 
itation of the domain, and cannot be applied to doc- 
ument with varied subjects, such ,as popular scientific 
magazine. To realize a domain-independent abstract 
generation system, a computational theory for ana- 
lyzing linguistic discourse structure and its practical 
procedure must be established. 
ltobbs developed a theory in which lie arranged 
three kinds of relationships between sentences from 
the text coherency viewpoint \[Hobbs 79\]. 
Grosz and Sidner proposed a theory which ac- 
counted for interactions between three notions on 
discourse: linguistic structure, intention, and atten- 
tion \[C, rosz et al. 86\]. 
l,itman and Allen described a model in which 
a discourse structure of conversation was built by 
recognizing a participanUs plans \[Litman et al. 87\]. 
'l'hese theories all depend on extra-linguistic knowl- 
edge, the accumulation of which presents a problem 
in the realization of a practical analyzer. 
Cohen proposed a framework for analyzing the 
structure of argumentative discourse \[Cohen 87\], yet 
did not provkle a concrete identification procedure 
for 'evidence' relationships between sentences, where 
no linguistic clues indicate the relationships. Also, 
since only relationships between successive sentences 
were considered, the scope which the relationships 
cover cannot be analyzed, even if explicit connectives 
are detected. 
Mama and Thompson proposed a linguistic struc- 
ture of text describing relationships between sen- 
tences and their relative importance \[Mann et al. 87\]. 
llowever, no method for extracting the relationships 
from superficial linguistic expressions was described 
in their paper. 
We have developed a computational rnodel of 
discourse for Japanese expository writings, and im- 
plemented a practical procedure for extracting dis- 
course structure\[Sumita 92\]. In our model, discourse 
structure is deiined ,as the rhetorical structure, i.e., 
the compound of rhetorical relations between sen- 
tences in text. Abstr~t generation is realized ~s a 
suitaMe application of the extracted rhetorical struc- 
ture. In this paper we describe briefly our discourse 
model and discuss the abstract generation system 
based on it. 
344 
3 RHETORICAl, STRUCTURE 
Rhetorical structure represents relations between var- 
ions chunks of sentences in the body of each section. 
In this paper, the rhetorical structure is represented 
by two layers: intra-paragraph and inter-paragral)h 
structures. An intra-paragraph structure is a struc- 
ture whose representation units are sentences, and an 
inter-paragraph structure is a structure whose rep- 
resentation units are paragraphs. 
In text, various rhetorical patterns art,. used to 
clarify the principle of argument. Among them, co,> 
nectivc expressions, which state inter-sentence rela- 
tionships, are the most significant. The tyl)ieal grant- 
matical categories of the connective expressions are 
connectives and sentence predicates. They can I>c 
divided into the thirty four categories which are ex- 
ernplified in Table 1. 
Table h Example Of rhetorical relations 
Relation Expressions 
serial (<SR>) 
su'n{lnarizatiou 
(<su>) 
negative (<NG>) 
dak'ara (thus) 
'kh.a.,aOk.,, (after all) 
shikashi (I)ut) 
example {<EG>) tatoeba (for example) 
espeeial(<ES>) tokuni (particuli~rly) 
re.~son !<aS>) ,mzenara (because) 
s{ipplcment (<SP>) 
background (<BI>) 
parallel (<PA>) 
exteflsion (<EX>) 
rei)hra~e (<RF>) 
direction (<DI>) 
mochiron (of course) 
juurai (hitherto) 
mata.(and) 
kore wa (this is) 
tsumari (that is to say) 
k'okode wa ... wo nobeT~l 
(here ... is described) 
The rhetorical relation of a sentence, which is 
the relationship to the preceding part of the text., 
can be extracted in accordance with the connective 
expression in the sentence. For a sentence without 
any explicit connective exl)ressions , extension rela- 
tion is set to the sentence. The relations exemplitied 
in Table 1 are used for representing the rhetorical 
structure. 
Fig. 1 shows a paragral)h from an article titled 
"A Zero-Crossing l{ate Which Estimates the Fre- 
quency of a Speech Signal," where underlined words 
indicate connective exl)ressions. Although the fourth 
and fifth sentences are clearly the exemplification 
of the first three sentences, the sixth is not. Also 
the sixth sentence is the concluding sentence for the 
first five. Thus, tile rhetorical structure for this text 
can be represented by a binary-tree as shown in 
Fig. 2.This structure is also represented as follows: 
\[\[\[1 <EZ> 2\] <gs> \[3 <E(\]> \[4 <EX> 5\]\]\] <sa> 6\] 
1: In tile context of discrete-time signals, zero- 
crossing is said to occur if successive samples 
have dilfereut algebraic signs. 
2: Tile rate at which zero crossings occur is a 
simple measure of tile frequency content of st 
sig,ml. 
3: This is .particularly true of narrow band 
signals. 
4: For example, a si,msoidal signal of frequency 
P0, sanll)led at a rate fs, h,'~s i'~/t"~ samples 
per cycle of the siue wave. 
5: Each cycle has two zero crossings so that the 
hmg-term average rate of zero-crossings is 
z = 2F0/s;;. 
6: Thus, tile average zero-crossing rate gives a 
reasonable way to estinmte the frequency of a 
sine wave. 
(L.lt.l(abiner and \[{.W.Schafer, Digital l','ocessing of 
Speech Siffmtls, Prentice-llall, 1978, p.127.) 
Figure 1 : Text example 
1 2 3 4 5 6 
Figure 2: Rhetorical structure for the text in l,'ig.1 
The rhetorical structure is represented by a bi- 
nary tree on the analogy of a syntactic tree of a natu- 
ral language sentence. Each sub tree of the rhetorical 
structure forms an arg,rnentative constituent, just as 
each sub-tree of tile syntactic tree forms a gram,nat- 
ical constituent. Also, a sub-tree of the rhetorical 
structure is sub-categorlzed by a relation of its par- 
ent node as well as a syntactic tree. 
345 
5 Implementation Note 
The current version of TECIIDOC is run- 
ning on Sun Spare stations with LUCI\]) 
CommonLISP 1.4 and LOOM 1.41 (a port 
to LOOM 2.1 is underway), and a PEN- 
MAN version fl'om 199i. The user interface 
is based on the CommonbISP Motif interface 
package CI,M and the application building 
tool GINA \[Spenke ct al., 1992\]. 
Acknowledgements 
~l'he success of the TECIIDOC i)rojeet depended 
heavily on eontril)utimls from a lltllllb(!r of student 
interns, in alphabetie;d order: Brigit.te Grote,, Sitll- 
(Ira Kiibler, Itaihua Pan, .lochen Schoepl>, Alex~m- 
dot Sigel, Ralf Wagner, and Uta We, is. ~i'hey ~dl 
have contributed to gl'&lltll'Lar or le×icon coverage ill 
one wa~y or another. Qerhard Peter has implemented 
TI'~CtlDOC-I, an intera(:tiw~ version giving c~tr mMn- 
tainanee ~tssist;tnce. Thorsten Liebig hats imph~- 
mented TECtlDOC's user interface for workstatim~s 
using CLM and GINA, Ilartmut Peuehtmiiller has 
~t(tded multimedia facilities ~md mouse-sensitive text 
mltlmt. We also have to thank the PlgNMAN ~tn(l 
LOOM groups ~tt USC/ISI and the KOMET project 
~tt GMD Darmstadt, wire gave us inwdmd~te help. 
References 
\[Bateman, 1990\] ,h)hn A. Bateman, Upper model- 
ing: A level of semantics for n;tt~lrltl l~tngu~tge 
processing. In PTvcecdings of the Fifth hJter.n,- 
tional Workshop on Nahu'al Lang~tagc G'eneration, 
Pittslmrgh, PA., 3 - (; June 1909. 
\[Grote et al., 1993\] Brigitte Grote, D~etmar llSsner, 
~tnd Manfred Stede. ll.epresentation lewzls in mul- 
tilingual text genera.tion. In Brigitte (\]r(~te, Di- 
etmar R.i~sner, Manfred Stede, and Uta Wets, edi- 
tors. From l(no'wledge 1o L~t~gmtge Three l)~tpers 
on MMtiling~ml tea:t Ge*teration. FAW Uhn, FAW- 
T11.-93017, 1993. 
\[LOOM, 19911 q'h,~ LOOM l~nowledge l~.present;t- 
t, ion Systellt. \])oettlllell~,~ttil)ll \]~;tcklt\[! i!~ 
USC/Information Sciences Institute, Marina l)el 
I{ey, CA., 1991. 
\[Mann and Thompsm~, 1987\] Willi;tm C. Mam~ and 
Sandra A. Thompson. IlhetoricM structure the- 
ory: A theory of text ()rg;tnization. In L.Pohmyi, 
editor, 7'he Sl*"uctttre of Discmtrse. Ablex, Nor- 
wood, N.J., 1987. Also as USC/Informatim~ Sci- 
ences Institute Research Report IIS-87-t90. 
\[\[I.i~sner and Stede, 1992;~\] 
Dietmar Ri~sner \[tnd Manfred Stede. Customiz- 
ink I1.ST for the automatic production of tech- 
nical manuals. In R. D;tle, \]'~. Ihwy, D. l/Sslw.r, 
and O. Stock, editors, Aspects of A'utomatcd Nat- 
'ltral Language Generation - l)roeeeditlos of the 6tb 
lnter~mtio',.al WS (m Natural LaTLg'uaqe Geneva- 
~ic, n, Lecture Notes in Artificial Intelligence 587. 
Springer, llerlin/l\[eidelberg, 19(.12. 
\[IlSsner itnd SLed.e, 1992b\] Dh, tm~u' I/Ssner ;tn(| 
Manfred Stede. TEC\[ll)OC : A system fi~r the au- 
t.mnatic l~roduction of multilingual technical doc- 
uments. In C,, Giirz, editor, KONVENS' 92, Reihe 
\[nformat.ik aktuell. Springer, l~erlin/Ihfidelherg, 
19\[)2. 
\[Spenke et ,l., 1992\] Miehltel Spenke, Christian 
\[~eilken, 'Phomas Berlage, And.'e~s Bi\[cker, ~tnd 
Andreas (\]rau. UlNA lh'feve',ce Ma'n'~utl Versio'n 
2. I. G~wmlm Ni~tion;d F/esea.rch Center for Con> 
purer Science, Snnkt Augustin, Cb~rmany, 19(.12. 
346 
that case the system cuts out terminal nodes from 
the last sentences, which are given the same penalty 
score. 
If the text is written loosely, tile rhetorical struc- 
ture generally contains many BothNuelevs relations 
(e.g., parallel(marc(and, also)), and the system can- 
not gradate the penalties and cannot reduce sen- 
tences smoothly. 
After sentences of each paragraph are reduced, 
inter-paragraph structure reduction is carried out in 
the same way based on the relative importance ju~lge- 
ment on the inter-paragraph rhetorical structure. 
If the penalty calculation mentioned above is 
accomplished for the rhetorical structure shown in 
Fig. 2, each penalty score is calculated as shown ill 
Fig. 3. In Fig. 3 italic numbers are the penalties the 
system imposed on each node of tile structure, and 
broken lines are the boundary between the nodes int-- 
posed different penalty scores. The figure shows that 
sentence four and five have penalty score three, that 
sentence three has two , that sentence one and two 
have one, and that sentence six has no penalty score. 
In this ease, the system selects sentence one, two, 
three and six for the longest abstract, and and also 
could select sentence one, two and six as a shorter 
abstract, and also could select sentence six as a still 
more shorter abstract. 
After the sentences to be included in tile al)- 
stract are determined, the system alter,atcly arranges 
the sentences and the connectives from which the re- 
lations were extracted, and realizes the text of tile 
abstr~t. 
The important feature of the generated abstr,'mts 
is that since they are composed of the rhetoriealy 
consistent units which consist of several sentences 
and form a rhetorical substructure, the abstract does 
not contain fragmentary sentences which can,ot be 
understood alone. For example, in the abstract gen- 
eration mentioned above, seutence two does not al> 
pear solely in the abstract, but appears ahvays with 
sentence one. If sentence two apl)eared alone in the 
abstract withont sentence one, it wouhl be difficult 
to understand the text. 
6 EVALUATION 
The generated abstracts were evaluated from the point 
of view of key sentence coverage. 30 editorial articles 
of"Asahi Shinbun", a Japanese newspaper, and 42 
technical papers of "Toshiba Review", a journal of 
Toshiba Corp. which publishes short expository pa- 
pers of three or four pages, were selected and three 
subjects judged tile key sentences and tile most im- 
portant key sentence of each text. As for the cdito- 
q'able 2: R.elative importance of rhetorical relations 
Relation Type ltelation hnport. Node 
serial, 
RighlNncleus smnmariz~t- right node 
tion, 
negative, ... 
exalnplc~ 
LeflNvclens reason, left node 
especial, 
SUl)plernen t, 
l)arallcl, 
llothNuclcus extension, both nodes 
rel)hrase , ... 
Ij ; 
$ 
1 2 3 4 5 6 
Figure 3: Penalties on relative iml)ortance for the 
rhetorical structure in Fig.2 
rial articles, The average correspondence rates of the 
key sente.ce and tile most important key sentence 
among the subjects were 60% and 60% respectively. 
As for the technical l)apcrs, they were 60% and 80 % 
resl)ectlvely. 
Then tile abstracts were generated and were 
compared with the selected key sentences. The re- 
s,lt is shown in Table 3. As for the technical papers, 
tile average length ratio( abstract/original ) w;~s 24 
%, and tile coverage of tl,e key sentence and the most 
important key sentence were 51% and 74% respec- 
tively. Whereas, ~s for the editorials, tile average 
length ratio( abstract/original ) was 30 %, and the 
coverage of the key sentence and the most important 
key sentence were 41% and 60% respectively. 
The reason why the compression rate and the 
kc.y sentence coverage of the technical papers were 
higher than that of the editorials is considered as 
follows. The technical papers contains so many rhe- 
torical expressions in general as to be expository. 
347 
That is, they provide many linguistic clues and the 
system can extract the rhetorical structure exactly. 
Accordingly, the structure can be reduced further 
and the length of the abstract gets shorter, without 
omitting key sentences. On the other hand, in the 
editorials most of the relations between sentences are 
supposed to be understood semantically, and are not 
expressed rhetorically. Therefore, they lack linguis- 
tic clues and the system cannot extract the rhetorical 
structure exactly. 
Table 3: Key sentence coverage of the abstracts 
cover ratio Material total length 
num. ratio key \] mosl. 
sentence I iml)°rtant 
Sell \[+etlee 
editorial 30 0.3 0.,11 0.60 
(Asahi Shlnbun) 
tech. journal 42 0.24 0.51 0.7.1 
(Toshiba Review) 
7 CONCLUSION 
We have developed an automatic abstract genera- 
tion system for Japanese expository writings based 
on rhetorical structure extraction. 
The rhetorical structure provkles a natural or- 
der of importance among senteuces in the text, and 
can be used to determine which sentence should be 
extracted in the abstract, according to the desired 
length of the abstract. The rhetorical structure also 
provkles the rhetorical relation between the extracted 
sentences, and can be used to generate appropriate 
connectives between them. 
Abstract generation b~sed on rhetorical struc- 
ture extraction has four merits. First, unlike con- 
ventional word-frequency-based abstract generation 
systems(e.g. \[Kuhn 58\]), the geuerated abstract is 
consistent with the original text in that the connec- 
tives between sentences in the abstract reflect their 
relation in the original text. Second, once the rhe- 
torical structure is obtained, varions lengths of gen- 
erated abstracts can be generated easily. This can be 
done by simply repeating the reduction process until 
one gets the desired length of abstract. Third, un- 
like conventional knowledge or script-b`ased abstr,~t 
generation systems(e.g. \[Lehnert 80\], \[Fum 86\]), the 
rhetorical structure extraction does not need pre- 
pared knowledge or scripts related to the original 
text , aud can be used for texts of any domain , so 
long as they contain enongh rhetoricM expressions 
to be expository writings. Fourth, the generated 
abstract is composed of rhetoriealy consistent units 
which consist of several sentences and form a rhe- 
torical substructure, so the abstract does not contain 
fragmentary sentences which cannot be understood 
alone. 
The limitations of the system are mainly due 
to errors in the rhetorical structure analysis and the 
sentence-selection-type abstract generation, the eval- 
nation of the accuracy of the rhetorical structure 
analysis carried out previously( \[Sumita 92\] ) showed 
74%. Also, to make the length of the abstract shorter, 
It, is necessary to utilize an inner-sentence analysis 
and to realize a phrase-selection-type abstract gen- 
eration b,~sed on it. The anaphora-resolution and 
the toplc-sul)l)leineutation must also be realized in 
the analysis. 
The system is now utilized ,as a text browser for 
a prototypical interactive document retrieval system. 
References 
\[Cohen 87\] Cohen, I/. : "Analyzing the Structure of Ar- 
gtnnentative Discourse", Computational Linguistics, 
Vol.13, pp.ll-24, 1987. 
\[Fum 86\] Finn, D. : "Tailoring Importance Evalnatlon 
to Reader's Goals: A Contribution to Descriptive Text 
Summarization", Proc. of Coling, i117.252-259, 1986. 
\[Grosz et al. 86\] Grosz, B.J. and Sidner, C.L. : "Atten- 
tion, Intentions and the SLruct.ore of Discourse", Com- 
putationM Linguistics, Vol.12, pp.175-204, 1986. 
\[Ilobbs 79\] Hobbs, J.R.: "Coherence and Coreference", 
Cognitive Science, Vol.3, 1979, pp.67-90. 
\[Kuhn 58\] Knhn, II.P. : "The Automatic Creation of Lit- 
erature Abstracts", IBM Journal, Apr. 1958, pp.159- 
165. 
\[I,elmert 80\] l,ehnert, W. : "Narrative Text Summariza- 
tion", Prec. of AAAI, I111..'137-339, 1980. 
\[Litman et al. 87\] l,ltman, D.J. and Allen, J.F.: "A 
Plan Recognition Model for Subdlalogues in Conver- 
sations", Cognitive Science, Vol.ll, 1987, pp.163-200. 
\[Mann et al. 87\] Mann, W.C. and Thompson, S.A. : 
"Rhetorical Structure Theory: A Framework for the 
Analysis of Texts", USC/lnfi)rmation Science lnsti- 
lute Research Report RI/-87-190, 1987. 
\[Sumita 92\] Sumita, K., et al. : "A Discourse Struc- 
ture Analyzer for Japanese Text", Pr~. h~t. Conf. 
Fifth Generation Computer Systems 1992 (FGCS'92), 
pp.1133-1140, 1992. 
348 
