A collocational based approach to salience-sensitive 
lexical selection 
Leo Wanner 
GMD/Institut ffir Integrierte Publikations- 
und Informationssysteme 
Dolivostrafie 15 
D-6100 Darmstadt, W. Germany 
e-mail: wanner@ipsi.darmstadt.gmd.dbp.de 
Abstract 
In this paper we address the organization and use of the 
lexicon giving special consideration to how the salience 
of certain aspects of abstract semantic structure may 
be expressed. We propose an organization of the lex- 
icon and its interaction with grammar and knowledge 
that makes extensive use of lexical functions from the 
Meaning-Text-Theory of Mel'~uk. We integrate this ap- 
proach with the architecture of the PENMAN text gen- 
eration system, showing some areas where that archi- 
tecture is insufficient, and illustrating how the lexicon 
can provide functionally oriented guidance for the gen- 
eration process. 
Introduction 
In natural language generation, the lexicon can be 
viewed, generally, as containing information for the 
verbalization of meanings. This information ranges 
over both the static organization of vocabulary -- 
including lexical knowledge, often handled separately 
as "lexical semantics" (see, e.g., \[Pustejovsky, 1988; 
Nirenburg and Raskin, 1987\]) or "structural semantics" 
-- and the process of lexical choice. To make allowance 
for this latter dynamic aspect of the lexical organiza- 
tion we will henceforth use the term lexis common in 
systemic linguistics \[Hasan, 1987; Matthiessen, 1988\] 
instead of "lexicon". Lexis thus represents lexical infor- 
mation at various different levels of abstraction (strata) 
and mapping structures that provide for the conversion 
between those levels. In this paper we address the or- 
ganization of lexis giving special consideration to the 
expresssion and choice of appropriate expressions as a 
function of the desired salience or prominence of seman- 
tic elements. The choice set of possible configurations 
of prominence we call the perspectives of the semantic 
structure. 
These have been addressed rarely in approaches in 
generation so far: for example, \[Jacobs, 1985\] discusses 
the verbs give and take as two different expressions of 
the same event; \[Nirenburg and Nirenburg, 1988\] sug- 
gest an approach to open-class lexical item selection for 
realization of conceptual input; and \[Iordanskaja et al., 
John A. Bateman 
USC/Information Sciences Institute 
4676 AdmirMty Way 
Marina del Rey 
CA 90292-6695, U.S.A. 
e-mail: bateman@isi.edu 
1988\] propose an approach to linguistic paraphrasing 
by adapting the Meaning-Text-Theory (MTT) \[Mel'~uk 
and Zholkovsky, 1970\] and its paraphrasing rules. Here, 
we make more extensive use of the MTT in order to 
provide a richer organization of lexis and its interaction 
with grammar and knowledge than has been proposed 
previously. Moreover, we develop this approach in the 
context of a concrete generation environment, the PEN- 
MAN system \[Mann and Matthiessen, 1985\], showing 
some areas where the existing architecture is insufficient 
and how the richer organization of lexis we propose can 
help. 
The following set of examples gives an impression of 
the variety of linguistic phenomena that we include un- 
der the term perspective. 1 All the sentences can be in- 
terpreted as verbalizations of a single abstract semantic 
structure with differing aspects of that structfire being 
given emphasis in each case. For example, in (4), the 
reader is made salient as a participant of the propo- 
sition; in (5), the 'manner of achievement' of the 'in- 
dication' is made salient; in (7), a particular temporal 
aspect of the process, namely the beginning, is made 
prominentput; and in (8), the intended purpose of the 
agent is made salient as a 'making clear'. While the 
variation that can be seen between (1), (2), and (3) can 
already be treated in, for example, the current PEN- 
MAN system by exercising meaning options available in 
the grammar (i.e., (2) exhibits passivization and (3) 
nominalization of 'use'), the variation shown in the re- 
maining examples cannot be functionally motivated as 
possible alternate grammatical realizations of the base 
semantic form. 
1. We use the adjective "electronic" to indicate that the dic- tionaries are deeply dedicated to computers. 
~. The adjective "electronic" is used to indicate that the die- 
tionarses are deeply dedicated to computers. 
3. The use of the adjective "electronic" indicates that the dictionaries are deeply dedicated to computers. 
4. The reader gets an indication that the dictionaries are 
1The basic sentence given under (1) is chosen from the 
introductory note of a text concerning the development of 
electronic dictionaries in Japan \[EDR, 1988\]. 
31 
deeply dedicated to computers by the adjective "elec- tronic". 
5. The indication that the dictionaries are deeply dedicated to computers is provided by the adjective "electronic". 
6. By the use of the adjective "electronic" toe illustrate the deep dedication of dictionaries to computers. 
7. We create an indication that the dictionaries are deeply dedicated to computers by the adjective "electronic". 
8. By the use o\] the adjective "electronic" we make clear that the dictionaries are deeply dedicated to computers. 
9. The reader should take the use o\]. the adjective "elec- tronic" as an indication that the dictionarses are deeply 
dedicated to computers. 
Some of the phenomena running through these ex- 
amples have been treated as lexleal eooeeurrenee 
\[Apresjan et al., 1969\] or collocation \[Firth, 1957; 
Halliday, 1966; Hausmann, 1985\]). Most extensively 
they are handled by I. Mel'~uk et al. in the scope of 
the Meaning-Text-Theory by means of lexleal func- 
tions (LFs). Our approach to generating this range 
of variation takes its starting point, therefore, from 
the notion of lexical cooccurrence relations addressed 
by Mel'~uk. There is a large body of descriptive work 
based on the notion of LFs which has been carried out 
for different languages \[Mel'~uk and Zholkovsky, 1984; 
Mel'~uk et al., 1988; Zholkovsky, 1970; Reuther, 1978; 
Janus, 1971\] and we will suggest how this body of 
knowledge can now provide significant input to work 
on text generation. 
In the next section we give an introduction to LFs as 
the means by which lexical cooccurrence dependencies 
are expressed within the MTT; we then describe some 
problems with the existing organization of LFs as de- 
fined by Mel'~uk eta/. and show how that organization 
can be developed further to be used for the modeling of 
various perspectives. In the section following, we then 
discuss the influence of lexis, when enriched by perspec- 
tives, on the generation process and, subsequently, we 
present a detailed example of the guidance this pro- 
vides. 
The Nature and Organization of Lexical 
Functions 
Lexical cooccurrence in the scope of MTT is provided 
in terms of lexical functions which Mel'~uk defines as 
follows \[Mel'~uk and Polgu6re, 1987\]: 
aA lexical ~_nction f is a dependency that associates with lexeme L, called the argument of f, another iexeme 
(or a set of (quasi.)synonymous iexemes) L' which ex- 
presses, with respect to L, a very abstract meaning (...) 
and plays a specific syntactic role. For instance, tor a noun N-denoting an action, the LF Opera specifies a 
verb (...) which takes as its grammatical subject the 
name of the agent of the said action and as its direct object, the lexeme N itself. 
The values for any particular application of a LF to a 
lexeme are provided by an Explanatory Combina- 
torial Dictionary (ECD); dictionaries of this type for 
a number of languages have already been compiled by 
MTT researchers. Thus, for example, the ECD for En- 
glish provides for the following applications of the LF 
Operl: Operl (influence) = exert 
Operl (punishment} = administer 
These give lexical verbs appropriate for use when the 
argument is to appear as a direct object to form a com- 
bination where an agent (optionally) acts upon some 
patient; e.g.: He exerted influence on P..., He ad- 
ministered a punishment..., but not, * he exerted a 
punishment..., * he administered an influence .... 
Cooccurrence relations of this kind are pervasive in 
natural language and need to be captured in the rep- 
resentation of a language's lexical resources. Such co- 
occurrence relations can be rather arbitrary and so are 
unlikely to be supportable by, for example, distinctions 
maintained in the knowledge base. Their meaning is 
not, however, arbitrary. An important claim of MTT is 
that each LF represents a particular abstract meaning 
which remains invariant across its various applications. 
Thus, for example, further LFs include: Fuse0 with 
the meaning 'something takes place' (Func0 (accident) 
= {occur, happen}, as in the sentence: The accident 
occured two hours ago.); Result standing for a state 
following the process addressed (Result (study) = mas- 
ter, as in the sentence: John mastered his subject.); and 
Liqu expressing an active process termination. This 
latter LF is often used in so called composed LFs where 
a number of LFs are combined in a predefined order 
(LiquFunc0 (Fire) = {extinguish, put out}, as in the 
sentence: The fire brigade could put out the fire quickly). 
MTT classifies LFs into two general types: lex- 
ieal parameters, which provide syntagmatie rela- 
tionships (e.g., Operi with i = 1,2,...), and lexi- 
eal substitutes, which provide paradigmatic relation- 
ships (e.g., Gener -- a specific generalization rela- 
tion) \[Mel'~uk and Zholkovsky, 1970\]. However, since 
LFs typically correspond to knowledge at varying lev- 
els of abstraction in addition to lexical information, 
these classes are still very heterogenous. Previous ap- 
roaches that have made use of LFs in generation (e.g., 
ittredge and Mel'~uk, 1983; Iordanskaja et al., 1988; 
Bourbean et al., 1989\]) have been hindered by this. In 
order to exploit the notion of LFs in generation more 
extensively, we need further organizational principles 
that emphasize the meanings distinct LFs possess. 
Work in progress at IPSI suggests that the large num- 
ber of heterogeneous LFs used within MTT can be or- 
ganized coherently in terms of the functions and seman- 
tic distinctions that they represent. Based on this, we 
have defined part of a general model of lexis with a 
taxonomic organization underlying it, within which the 
most general structures provide the representations of 
lexical semantics and the most delicate ones lexicaliza- 
tion. For the purposes of this paper, we will restrict 
attention to the organization of LFs that are particu- 
larly relevant for modeling situation perspectives as il- 
lustrated in our examples above. In Figure 1 we set out 
32 
in network form general distinctive features that clas- 
sify the meaning that the LFs we discuss here cover. 2 
The network explicates LFs by classifying each of them 
according to a particular set of semantic features. The 
general function of the network is thus to relate partic- 
ular LFs to the functional conditions for their applica- 
tion. This defines the meaning that any LF expresses 
and so provides a functionally organized key into the 
LF-oriented dictionaries being developed within MTT. 
The network also shows the hierarchical arrangement 
lying behind the meaning of LFs and so reflects the 
relation of perspectives to one another. 
We will now briefly describe in semantic terms a rep- 
resentative set of the LFs covered by the network, show- 
ing how the network relates perspectival presentation 
decisions to choices of LFs. 3 Then, with the organiza- 
tional network of perspectives in place and motivated, 
we show how it can be used to guide the generation 
process to produce the kinds of variation illustrated in (1)-(9). 
Situation introduction 
One of the basic terms used in the scope of MTT is 
that of abstract situations, circumscribed, roughly, as 
something that takes place. In the sense of Mel'~uk, 
abstract situations are defined by key terms and the 
participants of the situations; the key term is designated 
by the LF So, the participants as Si (i-th participant 
of the situation). We view this construct here as an 
abstract semantic partial specification of what is to be 
expressed linguistically. Thus, looking at the situation 
of teaching, the ECD for English offers us: 
So (teaching) = teaching, 
$1 (teaching) = teacher, 
SO (teaching) = pupil. 
The notion of situational key terms is closely related to 
term of processes in the tradition of Systemic Functional 
Grammar \[tlalliday, 1985; Steiner et al., 1987\]. 
When a situation is introduced, this may be done re- 
specting a number of varying attributions Of salience 
e.g., the salience of particular participants of a situation 
or the situation itself. 
The selection of particular combinations of process 
and participants for the realization of abstract situa- 
2The notation of Figure 1 follows that used within the 
NIGEL grammar of the PENMAN system for the specification 
of grammar possibilities. Names in capitals represent the 
names of choice points, and names in lower case features 
which may be selected: one from each choice point; also 
square brackets represent disjunction of features and braces 
conjunction. Such networks can be readily expressed in 
a number of distinct formalisms, e.g., FUG (cf. \[Kasper, 
1988\]), LOOM (cf. \[Kasper, 19895\]). 
3In the full version of this network, the consequences of 
each possible selection of features for LF selection is spec- 
ified; space precludes a detailed discussion at this point, 
although examples are given below. 
tions according to differing attributions of salience is 
then provided in the scope of the ECD by LFs of vari- 
ous groups. For example: Func, which has the effect of 
attributing salience to the term labeling the situation; 
Oper, which has the effect of attributing salience to 
one of the participants; and Labor which has the ef- 
fect of attributing salience to a combination of the par- 
ticipants. The selection of these broad groups is made 
in the network by the choices available under SITUA- 
TIONAL ORIENTATION, by the features 'situation ori- 
ented' (Func) and 'participant oriented' (Oper, Labor). 
These are further differentiated according to which 
participants are affected; e.g.: Operl makes the 'first' 
participant of the situation salient (i.e., the participant 
for which the LF $1 provides a lexeme) and Oper2 the 
'second' (i.e., the participant for which the LF $2 pro- 
vides a lexeme): Oper2 (influence) = be under. Simi- 
larly, Func0 makes the key term of the situation itself 
salient, while Func: introduces the situation with par- 
ticular respect to the first participant: Func0 (problem) 
= exist, FUnCl (problem) = come \[from\]. Labor12 makes 
the first and the second participant salient, the first 
more then the second, Labor21, on the contrary, makes 
the second participant more salient, e.g.: Laborl2 (pres- 
sure) = bring to bear \[on\], Labor21 (pressure) = get 
\[from\]. These options are controlled by the further se- 
lections of participants to be accorded salience in the 
choice points SITUATION ORIENTATION and PARTICI- 
PANT ORIENTATION. 
Finally, the third option in the SITUATIONAL ORIEN- 
TATION system, 'process orientation' is responsible for 
the neutral LF V0, which provides the most direct lex- 
ical verb for realizing the key term of a situation; e.g., 
Vo ( i.lzuence) = \[to\] influence. 
Temporal dependency 
LFs also address the global arrangement of a process on 
the temporal axes by the definition of its preceding and 
succeeding processes. These considerations are reached 
in the network by a feature selection of {global tempo- 
ral oriented, ..., } from the alternatives of the TEMPO- 
RAL ORIENTATION choice point. These alternatives call 
for the application of the LFs Prox and Perf; exam- 
ples of which from the ECD for English are: ProxFunc0 
(storm) = brew, Perf (storm) = subside. In addition, 
the internal temporal aspects of a process, represented 
by its stages, axe reflected by the corresponding triple 
of "phasal" LFs: Incep for the beginning, Cont for 
continuing, and Fin for the termination stage. These 
meanings are reached via the features under the 'stage 
oriented' option in the choice point PROCESS STAGES 
ORIENTATION in the network. 
Results and consequences 
Situations can also he expressed so as to give salience 
to their results. The treatment of this requires a con- 
sideration of the intended result of the situation 
33 
~CAUSALITY 
ORI~TATION 
CAUSATIONS ~ c~m~oa 
~~ ~' cmmmicm 
srruATIONAL I" ,~m,~-qal 
ORm~rrATION | sn'OATION | 
I 
I 
.... ORIENTATION I 
I 
PAl~ricIP~rr 
ORIENTATION 
nd ixmicil~ pmcemual 
o oN r 
,, 
L r ~ffiwr~ ~v,,,~,e~; ~,-,~ / 
ORIENTATION L pvc~,~ ~m,m 
PROCESS STAGT.$ 
ORIENTATION 
PARTICIPANT . ~.--.~---A 
On~ON t.~a ~ a 
RR.~.~T ORIENTATION 
E=ZZ 
Figure 1: A hierarchical organization of the meaning underlying lexical functions in network form 
the actual LF chosen depends on whether that result 
was achieved or not. These options are found under 
the choice point INTERNAL ORIENTATION and RESULT 
ORIENTATION. If the result of the process was the in- 
tended result (i.e., the ~purpose' of the carrying out 
the process), then the Real~, Labrealo, and Facts 
groups of LFs are applicable; in the opposite case, the 
AntiReal~, AntiLabrealo, and AntiFacti groups ap- 
ply. Each of these groups provide further the salience 
either of the key term of the situation itself or of the 
various participants of the situation as determined by 
the simultaneous selections of features made under (in 
this sense Reali and AntiReali correspond to Operl, 
Labreal 0 and AntiLabrealff to Laboro, and Fact~ and 
AntiFactl to Funci). For example: Real2 (order) = 
obey, AntiReal2 (order) = def~. 
Causality 
Situations can also be expressed so as to make the 
causality relationships that the situation enters into ex- 
plicit or not; these options are considered by the choice 
point CAUSALITY ORIENTATION, which is responsible 
for application of either the LF Caus or Perm. 
• The Cans function provides an active causation of the 
situation, as in the case of problem; e.g., CansFunc0 
(problem) = pose. 
• Perm presupposes a 'permission', or allowance or ac- 
ceptance, of the occurrence of the situation; e.g., 
PermPunco (problem) = tolerate. 
34 
Guiding the Generation Process by 
Lexis 
The concrete generation system in which we are realiz- 
ing organizational structures of lexis in order to sup- 
port the emphasis of various salience aspects of se- 
mantic structures is the PENMAN system \[Mann and 
Matthiessen, 1985\]. The linguistic core of PENMAN i8 
a large systemic-functional grammar of English, the 
NIGEL grammar \[Matthiessen, 1983\]. The semantic in- 
terface of NIGEL is defined by a set of inquiries which 
mediate the flow of information ,between the grammar 
and external sources of information. PENMAN provides 
structure for some of these external sources of informa- 
tion, including a conceptual hierarchy of relations and 
entities, called the Upper Model (UM) \[Bateman et aL, 
1990; Bateman, 1990\]; the UM hierarchy classifies con- 
cepts according to their possibilities for realization in 
natural language and may be used as an interface be- 
tween the organizational structures of Domain Knowl- 
edge (DK) and the grammar's inquiries. PENMAN ac- 
cepts demands for text to be generated in the notation 
of the PENMAN Sentence Plan Language (SPL) \[Kasper, 
1989a\]. SPL specifications are partial semantic repre- 
sentations of what is to be realized through the gram- 
matical resources of NIGEL. More formally, SPL expres- 
sions are lists of terms describing the types of entities 
and the particular features of those entities that are to 
be expressed in English. The features of SPL terms 
are either semantic relations to be expressed, which are 
drawn from the upper model or from domain concepts 
subordinated to the upper model, or direct specifica- 
tions of responses to NIGEL'S inquiries. 4 
To generate any of the sentences (1)-(9) above using 
PENMAN, therefore, we must define appropriate SPL in- 
put. However, as mentioned in the introduction, these 
input specifications do not, at present, capture the gen- 
eralization that these sentences share significant aspects 
of their meaning. To capture this, while still maintain- 
ing complete functional control of the generator, we in- 
troduce a more abstract input specification, from which 
particular SPL specifications are constructed depending 
on additional salience-oriented semantic distinctions. 
These semantic distinctions are specified in terms of the 
hierarchical organization of the meanings of LFs shown 
in the network of Figure 1. This organization provides 
a statement of semantic feature interdependencies that 
represents the perspectives available and the functional 
motivations for choosing one perspective over another. 
Each of the decision points in this network may place 
constraints on the mapping between the abstract in- 
put level and SPL. These decisions themselves need to 
be made by a text planning component -- the network 
represents the capability of generating variation under 
4For full details of the PENMAN system and its com- 
ponents, see the PENMAN documentation \[The Penman Project, 1989\]. 
control rather than the control process itself. In this 
sense, lexis as the stratum containing perspective infor- 
mation provides a controlling mechanism for the gener- 
ation process entirely analogously to the grammatical 
network defined by NIGEL. 
Example of perspective-guided 
generation 
We now illustrate the realization of some chosen per- 
spectives in detail. Consider the clauses (1), (4), (6), 
and (7) given above. The SPL input specifications nec- 
essary to generate each of these clauses are set out in 
Figure 2. 5 As we can see, there is no connection be- 
tween these since the generalization that they refer to 
the same situation is captured neither within the gram- 
mar, nor the upper model. Our new level of abstract in- 
put to the generation process, which corresponds more 
with Mel'~uk's conception of 'abstract situation' intro- 
duced above, provides this connection as follows. Ab- 
stract situations are represented in terms of a general 
type and a set of participants drawn from the lexemes 
defined with respect to the Domain Knowledge; for ex- 
ample, the abstract input for the situation underlying 
sentences (1), (4), (6), and (7) may be set out thus: 6 
SO use 
T $1 we T $2 adjective 'electronic' 
So indication T $2 reader 
TS3 \[So(deep) dedication\] T Ss T $1 dictionaries 
T $2 computers 
In order to generate sentences from this specification, 
we need to construct appropriate SPL expressions. This 
we achieve by following the semantic alternatives made 
in the LF network of Figure 1, applying the constraints 
that it specifies to compose a mapping between the ab- 
stract input and SPL. 
Thus, for example, consider the context of use where 
a text planner has determined, in addition to express- 
ing the situation shown in the abstract input, that 
that situation is to be presented textually as one in 
which the process is introduced neutrally, without re- 
spect for what preceded or succeeded, and with the pro- 
cess and the first participant (we: $1) made relatively 
more salient. This corresponds to the set of LF net-- 
work features {non-causal oriented, non-stage oriented, 
global temporal oriented, current process, introduction 
oriented, process-oriented, 1st participant processual). 
5Note that in this figure, in order to save space, we share 
the vaxables re, N1, A1, ASl across the distinct SPL spec- 
ifications; this would not normally be done. 
OThe notation T Si is used to indicate that the value 
given is not the value of the LF Si itself, it is rather the 
value of the role that the LF delivers; i.e., $1 (use) is user. 
35 
(Cl / use 
:actor 
:actee 
:purpose 
(C2 / get :actor 
(C3 / illustrate 
(C4 / create 
(we / person) 
(N1 / adjective 
:name electronic) 
(A1 /indicate 
: actor we 
: 8ubj ect -matt er 
(AS1 / dedicate 
:domain (dictionaries / thing) 
:range (computers. / thing) 
:manner (deep / sense-and-measure-quality) ) )) 
SPL specification for sentence (1) 
(r / reader) :means N1 :actee AI) 
SPL specification for sentence (4) 
:actor ee :actee AS1 :means NI) 
SPL specification for sentence (6) 
:actor we :actee A1 :means N1) 
SPL specification for sentence (7) 
Figure 2: SPL specifications for differing perspectives on a situation 
This set of features governs the selection of the LF V0, 
which is applied to the key-term of the situation, i.e., 
to So of the input form: the lexeme associated with the 
DK concept use. The ECD for the language then sup- 
plies a candidate lexical item -- in this case, the process 
USe. 
We integrate the information from the ECD by re- 
quiring lexical items to be linked to concepts which are 
subordinated to the PENMAN upper model. It is then 
possible to determine, by inheritance, the particular set 
of upper model/semantic role relations that are appro- 
priate for a process of any type. The concept for use 
is classified as a nondirected-acfio, in the upper model 
and so the role-set :actor, :actee is inherited. The 
fillers of these roles are then selected from the ordered 
set of participants specified in the abstract input under 
$1, $2. The process then recurses for the complex filler 
of $3 -- filling, in this case, the :purpose upper model 
relation -- and the SPL given in Figure 2 for sentence 
(1) is constructed. 7 
If the text planning component had determined that 
a different set of presentational LF features were neces- 
sary, then a different LF would be selected for applica- 
tion to the key-term of the abstract input. Thus, with 
the selection of the features {non-causal oriented, non- 
stage oriented, global temporal oriented, current pro- 
cess, result oriented, result intended, participant ori- 
ented, 1st participant oriented}, which expresses the 
7The association of the abstract situational roles S~ and 
the roles drawn from the upper model in fact offers another 
significant source of presentation variability which may also 
be addressed in terms of LFs. We do not discuss this further 
within the confines of the present paper however. 
intended effect of the process use with salience on its 
first participant, the LF Real1 is selected and, here, the 
ECD gives the process illustrate. This term is then, 
again, selected as the main term in the corresponding 
SPL specification and, as before, since it is also linked 
into the upper model, we know that the relevant role 
set is :actor, :actee, :moans. The further mapping 
of situational roles Si to available UM-roles then pro- 
vides the necessary fillers for the slots in the SPL. This 
gives the SPL for sentence (6). 
In sentences (4) and (7), the interaction between the 
lexical network and the situation subordinated under 
Ss in the abstract input is shown, s For the situation of 
'indication', then, when the LF features: {non-causal 
oriented, non-stage oriented, global temporal oriented, 
current process, introduction oriented, participant ori- 
ented, 2nd participant oriented} are required, express- 
ing that the situation is introduced with emphasis on its 
internal composition and participants and that the sec- 
ond of those participants is the more salient, then the 
LF Oper2 is selected for application to the filler of T $3 
(i.e., indication). The ECD in this case supplies get. 
Note that here, the LF Oper2 also has consequences for 
the latter mapping between situational roles and upper 
model roles; the key-term itself, So, is now associated 
with the role :actee. This provides the SPL specifica- 
tion for sentence (4). 
SWork elsewhere (e.g., \[Bateman and Paxis, 1989\]) has 
shown that propositionally embedded components of an in- 
put specification can be linguistically realized under certain 
textual conditions as unembedded, or as dominating, con- 
stituents. This is the case here, although space precludes a 
more thorough discussion. 
36 
Finally, with the selection of LF features {non-causal 
oriented, stage oriented, beginning, participant ori- 
ented, 1st participant oriented, global temporal ori- 
ented, current process, introduction oriented}, the LF 
IncepOperl is selected. When this is applied to indica- 
tion, the ECD gives the process create and the SPL for 
sentence (7) is set up accordingly. 
Conclusion 
We have shown how lexical cooccurrence relations can 
be used to express the salience of particular aspects of 
abstract semantic structures and how their underlying 
meaning and communicative function can be organized 
in order to influence the generation process. A spec- 
ification of perspectival presentatation features as de- 
fined in the network of Figure 1 makes it possible to 
generate rather varied surface realizational forms. We 
can view this network as a candidate for the textual 
organization \[Matthiessen, 1988\] of lexis -- which com- 
plements the more traditional 'propositional' organiza- 
tion found in lexical discrimination nets (e.g., \[Gold- 
man, 1975\]) and thesauri. The textual/communicative 
functional meanings of LFs we propose, although ar- 
guably inherent in the MTM, have not formerly been 
extracted as an explicit principle of organization. We 
suggest that this kind of organization may substan- 
tiMly enhance the information collected by MTM re- 
searchers. Finally, although we have restricted our- 
selves in this paper to details that are particularly rel- 
evant for modeling situation perspectives, we are work- 
ing towards a general model of lexis including, e.g., a 
semantically motivated classification of verbs, relations, 
etc. as proposed by, for example, \[Matthiessen, 1988; 
Hasan, 1987\] and pursued in a computational context 
by \[Fawcett and Tucker, 1989\]. For this we also use a 
set of further LFs represented on various levels of ab- 
straction. 
Acknowledgments. We would like to thank Elisa- 
beth Maier, Hans Miiller, Erich Steiner, and Elke Teich 
for fruitful discussions. We are also grateful to Igor 
Mel'euk and Alain Polgu~re for comments on an earlier 
draft of this paper. John Bateman acknowledges the 
additional financial support of IPSI during the devel- 
opment of the ideas reported here. 

References 
\[Apresjan et al., 1969\] Yu.D. Apresjan, 
A.K. Zholkovsky, and I.A. Mel'~uk. On a possible 
method of describing restricted lexical cooccurrence. 
Russkij Jazyk v Nacionalnoj Shcole, 6:61-72, 1969. 
\[Bateman and Paris, 1989\] John A. Bateman and 
C6cile L. Paris. Phrasing a text in terms the user 
can understand. In Proceedings of the Eleventh Inter- 
national Joint Conference on Artificial Intelligence, 
Detroit, Michigan, 1989. IJCAI-89. 
\[Bateman el al., 1990\] John A. Bateman, Robert T. 
Kasper, Johanna D. Moore, and Richard A. Whitney. 
A general organization of knowledge for natural lan- 
guage processing: the penman upper model. Techni- 
cal report, USC/Information Sciences Institute, Ma- 
rina del Rey, California, 1990. 
\[Bateman, 1990\] John A. Bateman. Upper modeling: 
organizing knowledge for natured language process- 
ing. In 5th. Natural Language Generation Workshop, 
June 1990, Pittsburgh, PA., 1990. Also available as 
technical report of USC/Information Sciences Insti- 
tute, Marina del Rey, CA 90292. 
\[Bourbeau et al., 1989\] L. Bourbeau, D. Carcagno, 
R. Kittredge, and A. Polgu~re. Text synthesis for 
marine weather forecast. Technical report, Odyssey 
Research Associates Inc., Montreal, 1989. Final Re- 
port, FOG project. 
\[EDIt, 1988\] Electronic dictionary project. Technical 
report, Japan Electronic Dictionary Research Insti- 
tute, Ltd., 1988. 
\[Fawcett and Tucker, 1989\] Robin P. Fawcett and Gor- 
don Tucker. Prototype generators 1 and 2. Technical 
Report COMMUNAL Report Number 10, Computa- 
tional Linguistics Unit, University of Wales College 
of Cardiff, 1989. 
\[Firth, 1957\] J.R. Firth. Modes of meaning (1951). In 
J.It. Firth, editor, Papers in linguistics 193~-1951, 
pages 190-215. Oxford University Press, 1957. 
\[Goldman, 1975\] Neil Goldman. Conceptual genera- 
tion. In R. C. Schank, editor, Conceptual Informa- 
tion Processing. North-Holland Publishing Co, Ams- 
terdam, 1975. 
\[Halliday, 1966\] Michael A.K. Halliday. Lexis as a lin- 
guistic level. In C. E. Bazell et al., editor, In Memory 
of J.R. Firth. Longman, London, 1966. 
\[Halliday, 1985\] Michael A.K. Halliday. Introduction 
to Functional Grammar. Edward Arnold, London, 
1985. 
\[Hasan, 1987\] Ituqaiya Hasan. The grammarian's 
dream: lexis as most delicate grammar. In 
Michael A.K. Halliday and Robin P. Fawcett, editors, 
New Developments in Systemic Linguistics. Volume 
1. Frances Pinter, London, 1987. 
\[Hausmann, 1985\] F.J. Hausmann. Kollokationen ira 
deutschen WSrterbuch: Ein Beitrag zur Theorie des 
lexikographischen Beispiels. In H. Bergenholtz and 
J. Mugdan, editors, Lezikographie und Grammatik, 
Akten des Essener Kolloquiums zur Grammatik im 
WJrterbueh, pages 118-129. 1985. 
\[Iordanskaja et al., 1988\] Lidija Iordanskaja, Richard 
Kittredge, and Polgu~re Alaln. Lexical selection 
and paraphrase in a meaning-text generation model, 
July 1988. Presented at the Fourth International 
Workshop on Natural Language Generation. Also ap- 
pears in selected papers from the workshop: Paris, 
Swartout and Mann (eds.)(1990)(op. cir.). 
\[Jacobs, 1985\] P.S. Jacobs. A knowledge-based ap- 
proach to language production. Technical Report 
UCB/CSD 86/254, Univ. of California at Berkeley, 
1985. 
\[Janus, 1971\] E. Janus. Five polish dictionary entries... 
Nau6no-techni6eskaja informacia, 2(11):21-24, 1971. 
\[Kasper, 1988\] Robert T. Kasper. An Experimental 
Parser for Systemic Grammars. In Proceedings of 
the 1Pth International Conference on Computational 
Linguistics, August 1988, Budapest, Hungary, 1988. 
Association for Computational Linguistics. Also 
available as Information Sciences Institute Technical 
Report No. ISI/RS-88-212, Marina del Rey, CA. 
\[Kasper, 1989a\] Robert T. Kasper. A flexible interface 
for linking applications to PENMAN'S sentence gen- 
erator. In Proceedings of the Darpa Workshop on 
Speech and Natural Language, 1989. Availabe from 
USC/Information Sciences Institute, Marina del Rey, 
CA. 
\[Kasper, 1989b\] Robert T. Kasper. Unification and 
classification: an experiment in information-based 
parsing. In Proceedings of the International Work- 
shop on Parsing Technologies, pages 1-7, 1989. 28- 
31 August, 1989, Carnegie-Mellon University, Pitts- 
burgh, Pennsylvania. 
\[Kittredge and Mel'~uk, 1983\] It. Kittredge and I.A. 
Mel'~uk. Towards a computable model of meaning- 
text relations within a natural sublanguage. In Pro- 
ceedings of the IJCAI 1983, 1983. 
\[Mann and Matthiessen, 1985\] William C. Mann and 
Christian M.I.M. Matthiessen. Demonstration of the 
nigel text generation computer program. In J. Ben- 
son and W. Greaves, editors, Systemic Perspectives 
on Discourse, Volume 1. Ablex, Norwood, New Jer- 
sey, 1985. 
\[Matthiessen, 1983\] Christian M.I.M. Matthiessen. 
Systemic grammar in computation: the nigel case. 
In Proceedings of the First Annual Conference of the 
European Chapter of the Association for Computa- 
tional Linguistics, 1983. 
\[Matthiessen, 1988\] Christian M.I.M. 
Matthiessen. Lexieo(grammatieal) choice in text 
generation, July 1988. Presented at the Fourth Inter- 
national Workshop on Natural Language Generation. 
Also appears in selected papers from the workshop: 
Paris, Swartout and Mann (eds.)(1990)(op. cir.). 
\[Mel'~uk and Polgu~re, 1987\] 
I.A. Mel'~uk and A. Polgu~re. A formal lexicon in 
the meaning-text theory (or how to do lexica with 
words). Computational Linguistics, 13(3-4):276-289, 
1987. 
\[Mel'Suk and Zholkovsky, 1970\] I.A. Mel'euk and A.K. 
Zholkovsky. Towards a functioning meaning-text 
model of language. Linguistics, 57:10-47, 1970. 
\[Mel'6uk and Zholkovsky, 1984\] I.A. Mel'~uk and A.K. 
Zholkovsky. Explanatory Combinatorial Dictionary 
of Modern Russian. Wiener Slawistischer Almanach, 
Vienna, 1984. 
\[Mel'~uk et al., 1988\] I.A. Mel'~uk, N. Arbatchewsky- 
Jumarie, L. Elnitsky, and A. Lessard. Diction- 
naire explicatif et combinatoire du francais contempo- 
rain. Presses de l'Universit~ de Montreal, MontrEal, 
Canada, 1988. 
\[Nirenburg and Nirenburg, 1988\] Sergei Nirenburg and 
Irene Nirenburg. A framework for lexicM selection in 
natural language generation. In Proceedings of COL- 
ING 88, Budapest, Hungary, August 1988. Associa- 
tion for Computational Linguistics. 
\[Nirenburg and Raskin, 1987\] Sergei Nirenburg and 
Victor Raskin. The subworld concept lexicon and 
the lexicon management system. Computational Lin- 
guistics, 13(3-4), 1987. 
\[Paris et al., 1990\] C~cile L. 
Paris, William It. Swartout, and William C. Mann, 
editors. Natural Language Generation in Artificial 
Intelligence and Computational Linguistics. Kluwer 
Academic Publishers, 1990. 
\[Pustejovsky, 1988\] James Pustejovsky. Event seman- 
tic structure. Technical report, Brandeis University, 
Waltham, MA., 1988. 
\[Reuther, 1978\] T. Reuther. Pl~doyer fiir das 
WSrterbuch. Lingnistisehe Berichte, 57:25-48, 1978. 
\[Steiner et aL, 1987\] Erich H. Steiner, Ursula Eckert, 
Birgit Week, and Jutta Winter. The development of 
the EUROTRA-D system of semantic relations. Tech- 
nical Report Eurotra-D Working Papers, No. 2, In- 
stitut der angewandten Informationsforschung, Uni- 
versitKt des Saarlandes, Sa~rbrficken, West Germany, 
1987. 
\[The Penman Project, 1989\] The Penman 
Project. The PENMAN documentation: User guide, 
primer, reference manual, and nigel manual. Techni- 
cal report, USC/Information Sciences Institute, Ma- 
rina del Rey, CA, 1989. 
\[Zholkovsky, 1970\] A.K. Zholkovsky. Materials for a 
russian-somali dictionary. Mashinnij perevod i prik- 
iadnaja lingvistika, 13:35--63, 1970. 
